* [Qemu-devel] [PATCH v3 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-17 1:14 ` Richard Henderson
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c Mark Cave-Ayland
` (16 subsequent siblings)
17 siblings, 1 reply; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Since commit 8a14d31b00 "target/ppc: switch fpr/vsrl registers so all VSX
registers are in host endian order" functions getVSR() and putVSR() which used
to convert the VSR registers into host endian order are no longer required.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
---
target/ppc/fpu_helper.c | 762 +++++++++++++++++++++++-------------------------
1 file changed, 366 insertions(+), 396 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index ffbd19afa1..8da805d175 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -1803,35 +1803,35 @@ uint32_t helper_efdcmpeq(CPUPPCState *env, uint64_t op1, uint64_t op2)
#define VSX_ADD_SUB(name, op, nels, tp, fld, sfprf, r2sp) \
void helper_##name(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
float_status tstat = env->fp_status; \
set_float_exception_flags(0, &tstat); \
- xt.fld = tp##_##op(xa.fld, xb.fld, &tstat); \
+ t.fld = tp##_##op(xa->fld, xb->fld, &tstat); \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
float_invalid_op_addsub(env, sfprf, GETPC(), \
- tp##_classify(xa.fld) | \
- tp##_classify(xb.fld)); \
+ tp##_classify(xa->fld) | \
+ tp##_classify(xb->fld)); \
} \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -1846,12 +1846,12 @@ VSX_ADD_SUB(xvsubsp, sub, 4, float32, VsrW(i), 0, 0)
void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xa, xb;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = *xt;
float_status tstat;
- getVSR(rA(opcode) + 32, &xa, env);
- getVSR(rB(opcode) + 32, &xb, env);
- getVSR(rD(opcode) + 32, &xt, env);
helper_reset_fpstatus(env);
tstat = env->fp_status;
@@ -1860,18 +1860,18 @@ void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
}
set_float_exception_flags(0, &tstat);
- xt.f128 = float128_add(xa.f128, xb.f128, &tstat);
+ t.f128 = float128_add(xa->f128, xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
float_invalid_op_addsub(env, 1, GETPC(),
- float128_classify(xa.f128) |
- float128_classify(xb.f128));
+ float128_classify(xa->f128) |
+ float128_classify(xb->f128));
}
- helper_compute_fprf_float128(env, xt.f128);
+ helper_compute_fprf_float128(env, t.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ *xt = t;
do_float_check_status(env, GETPC());
}
@@ -1886,36 +1886,36 @@ void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
#define VSX_MUL(op, nels, tp, fld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
float_status tstat = env->fp_status; \
set_float_exception_flags(0, &tstat); \
- xt.fld = tp##_mul(xa.fld, xb.fld, &tstat); \
+ t.fld = tp##_mul(xa->fld, xb->fld, &tstat); \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
float_invalid_op_mul(env, sfprf, GETPC(), \
- tp##_classify(xa.fld) | \
- tp##_classify(xb.fld)); \
+ tp##_classify(xa->fld) | \
+ tp##_classify(xb->fld)); \
} \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -1926,13 +1926,12 @@ VSX_MUL(xvmulsp, 4, float32, VsrW(i), 0, 0)
void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xa, xb;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = *xt;
float_status tstat;
- getVSR(rA(opcode) + 32, &xa, env);
- getVSR(rB(opcode) + 32, &xb, env);
- getVSR(rD(opcode) + 32, &xt, env);
-
helper_reset_fpstatus(env);
tstat = env->fp_status;
if (unlikely(Rc(opcode) != 0)) {
@@ -1940,17 +1939,17 @@ void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
}
set_float_exception_flags(0, &tstat);
- xt.f128 = float128_mul(xa.f128, xb.f128, &tstat);
+ t.f128 = float128_mul(xa->f128, xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
float_invalid_op_mul(env, 1, GETPC(),
- float128_classify(xa.f128) |
- float128_classify(xb.f128));
+ float128_classify(xa->f128) |
+ float128_classify(xb->f128));
}
- helper_compute_fprf_float128(env, xt.f128);
+ helper_compute_fprf_float128(env, t.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ *xt = t;
do_float_check_status(env, GETPC());
}
@@ -1965,39 +1964,39 @@ void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
#define VSX_DIV(op, nels, tp, fld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
float_status tstat = env->fp_status; \
set_float_exception_flags(0, &tstat); \
- xt.fld = tp##_div(xa.fld, xb.fld, &tstat); \
+ t.fld = tp##_div(xa->fld, xb->fld, &tstat); \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
float_invalid_op_div(env, sfprf, GETPC(), \
- tp##_classify(xa.fld) | \
- tp##_classify(xb.fld)); \
+ tp##_classify(xa->fld) | \
+ tp##_classify(xb->fld)); \
} \
if (unlikely(tstat.float_exception_flags & float_flag_divbyzero)) { \
float_zero_divide_excp(env, GETPC()); \
} \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2008,13 +2007,12 @@ VSX_DIV(xvdivsp, 4, float32, VsrW(i), 0, 0)
void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xa, xb;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = *xt;
float_status tstat;
- getVSR(rA(opcode) + 32, &xa, env);
- getVSR(rB(opcode) + 32, &xb, env);
- getVSR(rD(opcode) + 32, &xt, env);
-
helper_reset_fpstatus(env);
tstat = env->fp_status;
if (unlikely(Rc(opcode) != 0)) {
@@ -2022,20 +2020,20 @@ void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
}
set_float_exception_flags(0, &tstat);
- xt.f128 = float128_div(xa.f128, xb.f128, &tstat);
+ t.f128 = float128_div(xa->f128, xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
float_invalid_op_div(env, 1, GETPC(),
- float128_classify(xa.f128) |
- float128_classify(xb.f128));
+ float128_classify(xa->f128) |
+ float128_classify(xb->f128));
}
if (unlikely(tstat.float_exception_flags & float_flag_divbyzero)) {
float_zero_divide_excp(env, GETPC());
}
- helper_compute_fprf_float128(env, xt.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ helper_compute_fprf_float128(env, t.f128);
+ *xt = t;
do_float_check_status(env, GETPC());
}
@@ -2050,29 +2048,29 @@ void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
#define VSX_RE(op, nels, tp, fld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
- if (unlikely(tp##_is_signaling_nan(xb.fld, &env->fp_status))) { \
+ if (unlikely(tp##_is_signaling_nan(xb->fld, &env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
} \
- xt.fld = tp##_div(tp##_one, xb.fld, &env->fp_status); \
+ t.fld = tp##_div(tp##_one, xb->fld, &env->fp_status); \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2092,37 +2090,37 @@ VSX_RE(xvresp, 4, float32, VsrW(i), 0, 0)
#define VSX_SQRT(op, nels, tp, fld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
float_status tstat = env->fp_status; \
set_float_exception_flags(0, &tstat); \
- xt.fld = tp##_sqrt(xb.fld, &tstat); \
+ t.fld = tp##_sqrt(xb->fld, &tstat); \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
- if (tp##_is_neg(xb.fld) && !tp##_is_zero(xb.fld)) { \
+ if (tp##_is_neg(xb->fld) && !tp##_is_zero(xb->fld)) { \
float_invalid_op_vxsqrt(env, sfprf, GETPC()); \
- } else if (tp##_is_signaling_nan(xb.fld, &tstat)) { \
+ } else if (tp##_is_signaling_nan(xb->fld, &tstat)) { \
float_invalid_op_vxsnan(env, GETPC()); \
} \
} \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2142,38 +2140,38 @@ VSX_SQRT(xvsqrtsp, 4, float32, VsrW(i), 0, 0)
#define VSX_RSQRTE(op, nels, tp, fld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
float_status tstat = env->fp_status; \
set_float_exception_flags(0, &tstat); \
- xt.fld = tp##_sqrt(xb.fld, &tstat); \
- xt.fld = tp##_div(tp##_one, xt.fld, &tstat); \
+ t.fld = tp##_sqrt(xb->fld, &tstat); \
+ t.fld = tp##_div(tp##_one, t.fld, &tstat); \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
- if (tp##_is_neg(xb.fld) && !tp##_is_zero(xb.fld)) { \
+ if (tp##_is_neg(xb->fld) && !tp##_is_zero(xb->fld)) { \
float_invalid_op_vxsqrt(env, sfprf, GETPC()); \
- } else if (tp##_is_signaling_nan(xb.fld, &tstat)) { \
+ } else if (tp##_is_signaling_nan(xb->fld, &tstat)) { \
float_invalid_op_vxsnan(env, GETPC()); \
} \
} \
\
if (r2sp) { \
- xt.fld = helper_frsp(env, xt.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2195,37 +2193,35 @@ VSX_RSQRTE(xvrsqrtesp, 4, float32, VsrW(i), 0, 0)
#define VSX_TDIV(op, nels, tp, fld, emin, emax, nbits) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xa, xb; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
int i; \
int fe_flag = 0; \
int fg_flag = 0; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- \
for (i = 0; i < nels; i++) { \
- if (unlikely(tp##_is_infinity(xa.fld) || \
- tp##_is_infinity(xb.fld) || \
- tp##_is_zero(xb.fld))) { \
+ if (unlikely(tp##_is_infinity(xa->fld) || \
+ tp##_is_infinity(xb->fld) || \
+ tp##_is_zero(xb->fld))) { \
fe_flag = 1; \
fg_flag = 1; \
} else { \
- int e_a = ppc_##tp##_get_unbiased_exp(xa.fld); \
- int e_b = ppc_##tp##_get_unbiased_exp(xb.fld); \
+ int e_a = ppc_##tp##_get_unbiased_exp(xa->fld); \
+ int e_b = ppc_##tp##_get_unbiased_exp(xb->fld); \
\
- if (unlikely(tp##_is_any_nan(xa.fld) || \
- tp##_is_any_nan(xb.fld))) { \
+ if (unlikely(tp##_is_any_nan(xa->fld) || \
+ tp##_is_any_nan(xb->fld))) { \
fe_flag = 1; \
} else if ((e_b <= emin) || (e_b >= (emax - 2))) { \
fe_flag = 1; \
- } else if (!tp##_is_zero(xa.fld) && \
+ } else if (!tp##_is_zero(xa->fld) && \
(((e_a - e_b) >= emax) || \
((e_a - e_b) <= (emin + 1)) || \
(e_a <= (emin + nbits)))) { \
fe_flag = 1; \
} \
\
- if (unlikely(tp##_is_zero_or_denormal(xb.fld))) { \
+ if (unlikely(tp##_is_zero_or_denormal(xb->fld))) { \
/* \
* XB is not zero because of the above check and so \
* must be denormalized. \
@@ -2255,34 +2251,31 @@ VSX_TDIV(xvtdivsp, 4, float32, VsrW(i), -126, 127, 23)
#define VSX_TSQRT(op, nels, tp, fld, emin, nbits) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xa, xb; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
int i; \
int fe_flag = 0; \
int fg_flag = 0; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- \
for (i = 0; i < nels; i++) { \
- if (unlikely(tp##_is_infinity(xb.fld) || \
- tp##_is_zero(xb.fld))) { \
+ if (unlikely(tp##_is_infinity(xb->fld) || \
+ tp##_is_zero(xb->fld))) { \
fe_flag = 1; \
fg_flag = 1; \
} else { \
- int e_b = ppc_##tp##_get_unbiased_exp(xb.fld); \
+ int e_b = ppc_##tp##_get_unbiased_exp(xb->fld); \
\
- if (unlikely(tp##_is_any_nan(xb.fld))) { \
+ if (unlikely(tp##_is_any_nan(xb->fld))) { \
fe_flag = 1; \
- } else if (unlikely(tp##_is_zero(xb.fld))) { \
+ } else if (unlikely(tp##_is_zero(xb->fld))) { \
fe_flag = 1; \
- } else if (unlikely(tp##_is_neg(xb.fld))) { \
+ } else if (unlikely(tp##_is_neg(xb->fld))) { \
fe_flag = 1; \
- } else if (!tp##_is_zero(xb.fld) && \
+ } else if (!tp##_is_zero(xb->fld) && \
(e_b <= (emin + nbits))) { \
fe_flag = 1; \
} \
\
- if (unlikely(tp##_is_zero_or_denormal(xb.fld))) { \
+ if (unlikely(tp##_is_zero_or_denormal(xb->fld))) { \
/* \
* XB is not zero because of the above check and \
* therefore must be denormalized. \
@@ -2313,24 +2306,20 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23)
#define VSX_MADD(op, nels, tp, fld, maddflgs, afrm, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt_in, xa, xb, xt_out; \
- ppc_vsr_t *b, *c; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt, *b, *c; \
int i; \
\
if (afrm) { /* AxB + T */ \
- b = &xb; \
- c = &xt_in; \
+ b = xb; \
+ c = xt; \
} else { /* AxT + B */ \
- b = &xt_in; \
- c = &xb; \
+ b = xt; \
+ c = xb; \
} \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt_in, env); \
- \
- xt_out = xt_in; \
- \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
@@ -2342,30 +2331,30 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
* result to odd. \
*/ \
set_float_rounding_mode(float_round_to_zero, &tstat); \
- xt_out.fld = tp##_muladd(xa.fld, b->fld, c->fld, \
- maddflgs, &tstat); \
- xt_out.fld |= (get_float_exception_flags(&tstat) & \
- float_flag_inexact) != 0; \
+ t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \
+ maddflgs, &tstat); \
+ t.fld |= (get_float_exception_flags(&tstat) & \
+ float_flag_inexact) != 0; \
} else { \
- xt_out.fld = tp##_muladd(xa.fld, b->fld, c->fld, \
- maddflgs, &tstat); \
+ t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \
+ maddflgs, &tstat); \
} \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
\
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { \
- tp##_maddsub_update_excp(env, xa.fld, b->fld, \
+ tp##_maddsub_update_excp(env, xa->fld, b->fld, \
c->fld, maddflgs, GETPC()); \
} \
\
if (r2sp) { \
- xt_out.fld = helper_frsp(env, xt_out.fld); \
+ t.fld = helper_frsp(env, t.fld); \
} \
\
if (sfprf) { \
- helper_compute_fprf_float64(env, xt_out.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
- putVSR(xT(opcode), &xt_out, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2415,22 +2404,21 @@ VSX_MADD(xvnmsubmsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0, 0)
#define VSX_SCALAR_CMP_DP(op, cmp, exp, svxvc) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vxvc_flag = false, vex_flag = false; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
- if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) || \
- float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \
+ if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status) || \
+ float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \
vxsnan_flag = true; \
if (fpscr_ve == 0 && svxvc) { \
vxvc_flag = true; \
} \
} else if (svxvc) { \
- vxvc_flag = float64_is_quiet_nan(xa.VsrD(0), &env->fp_status) || \
- float64_is_quiet_nan(xb.VsrD(0), &env->fp_status); \
+ vxvc_flag = float64_is_quiet_nan(xa->VsrD(0), &env->fp_status) || \
+ float64_is_quiet_nan(xb->VsrD(0), &env->fp_status); \
} \
if (vxsnan_flag) { \
float_invalid_op_vxsnan(env, GETPC()); \
@@ -2441,15 +2429,16 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
vex_flag = fpscr_ve && (vxvc_flag || vxsnan_flag); \
\
if (!vex_flag) { \
- if (float64_##cmp(xb.VsrD(0), xa.VsrD(0), &env->fp_status) == exp) { \
- xt.VsrD(0) = -1; \
- xt.VsrD(1) = 0; \
+ if (float64_##cmp(xb->VsrD(0), xa->VsrD(0), \
+ &env->fp_status) == exp) { \
+ t.VsrD(0) = -1; \
+ t.VsrD(1) = 0; \
} else { \
- xt.VsrD(0) = 0; \
- xt.VsrD(1) = 0; \
+ t.VsrD(0) = 0; \
+ t.VsrD(1) = 0; \
} \
} \
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2460,18 +2449,16 @@ VSX_SCALAR_CMP_DP(xscmpnedp, eq, 0, 0)
void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xa, xb;
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)];
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)];
int64_t exp_a, exp_b;
uint32_t cc;
- getVSR(xA(opcode), &xa, env);
- getVSR(xB(opcode), &xb, env);
-
- exp_a = extract64(xa.VsrD(0), 52, 11);
- exp_b = extract64(xb.VsrD(0), 52, 11);
+ exp_a = extract64(xa->VsrD(0), 52, 11);
+ exp_b = extract64(xb->VsrD(0), 52, 11);
- if (unlikely(float64_is_any_nan(xa.VsrD(0)) ||
- float64_is_any_nan(xb.VsrD(0)))) {
+ if (unlikely(float64_is_any_nan(xa->VsrD(0)) ||
+ float64_is_any_nan(xb->VsrD(0)))) {
cc = CRF_SO;
} else {
if (exp_a < exp_b) {
@@ -2492,18 +2479,16 @@ void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode)
void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xa, xb;
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
int64_t exp_a, exp_b;
uint32_t cc;
- getVSR(rA(opcode) + 32, &xa, env);
- getVSR(rB(opcode) + 32, &xb, env);
-
- exp_a = extract64(xa.VsrD(0), 48, 15);
- exp_b = extract64(xb.VsrD(0), 48, 15);
+ exp_a = extract64(xa->VsrD(0), 48, 15);
+ exp_b = extract64(xb->VsrD(0), 48, 15);
- if (unlikely(float128_is_any_nan(xa.f128) ||
- float128_is_any_nan(xb.f128))) {
+ if (unlikely(float128_is_any_nan(xa->f128) ||
+ float128_is_any_nan(xb->f128))) {
cc = CRF_SO;
} else {
if (exp_a < exp_b) {
@@ -2525,23 +2510,22 @@ void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode)
#define VSX_SCALAR_CMP(op, ordered) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xa, xb; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
uint32_t cc = 0; \
bool vxsnan_flag = false, vxvc_flag = false; \
\
helper_reset_fpstatus(env); \
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
\
- if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) || \
- float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \
+ if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status) || \
+ float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \
vxsnan_flag = true; \
cc = CRF_SO; \
if (fpscr_ve == 0 && ordered) { \
vxvc_flag = true; \
} \
- } else if (float64_is_quiet_nan(xa.VsrD(0), &env->fp_status) || \
- float64_is_quiet_nan(xb.VsrD(0), &env->fp_status)) { \
+ } else if (float64_is_quiet_nan(xa->VsrD(0), &env->fp_status) || \
+ float64_is_quiet_nan(xb->VsrD(0), &env->fp_status)) { \
cc = CRF_SO; \
if (ordered) { \
vxvc_flag = true; \
@@ -2554,9 +2538,9 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
float_invalid_op_vxvc(env, 0, GETPC()); \
} \
\
- if (float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) { \
+ if (float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status)) { \
cc |= CRF_LT; \
- } else if (!float64_le(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) { \
+ } else if (!float64_le(xa->VsrD(0), xb->VsrD(0), &env->fp_status)) { \
cc |= CRF_GT; \
} else { \
cc |= CRF_EQ; \
@@ -2575,23 +2559,22 @@ VSX_SCALAR_CMP(xscmpudp, 0)
#define VSX_SCALAR_CMPQ(op, ordered) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xa, xb; \
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
uint32_t cc = 0; \
bool vxsnan_flag = false, vxvc_flag = false; \
\
helper_reset_fpstatus(env); \
- getVSR(rA(opcode) + 32, &xa, env); \
- getVSR(rB(opcode) + 32, &xb, env); \
\
- if (float128_is_signaling_nan(xa.f128, &env->fp_status) || \
- float128_is_signaling_nan(xb.f128, &env->fp_status)) { \
+ if (float128_is_signaling_nan(xa->f128, &env->fp_status) || \
+ float128_is_signaling_nan(xb->f128, &env->fp_status)) { \
vxsnan_flag = true; \
cc = CRF_SO; \
if (fpscr_ve == 0 && ordered) { \
vxvc_flag = true; \
} \
- } else if (float128_is_quiet_nan(xa.f128, &env->fp_status) || \
- float128_is_quiet_nan(xb.f128, &env->fp_status)) { \
+ } else if (float128_is_quiet_nan(xa->f128, &env->fp_status) || \
+ float128_is_quiet_nan(xb->f128, &env->fp_status)) { \
cc = CRF_SO; \
if (ordered) { \
vxvc_flag = true; \
@@ -2604,9 +2587,9 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
float_invalid_op_vxvc(env, 0, GETPC()); \
} \
\
- if (float128_lt(xa.f128, xb.f128, &env->fp_status)) { \
+ if (float128_lt(xa->f128, xb->f128, &env->fp_status)) { \
cc |= CRF_LT; \
- } else if (!float128_le(xa.f128, xb.f128, &env->fp_status)) { \
+ } else if (!float128_le(xa->f128, xb->f128, &env->fp_status)) { \
cc |= CRF_GT; \
} else { \
cc |= CRF_EQ; \
@@ -2633,22 +2616,21 @@ VSX_SCALAR_CMPQ(xscmpuqp, 0)
#define VSX_MAX_MIN(name, op, nels, tp, fld) \
void helper_##name(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
for (i = 0; i < nels; i++) { \
- xt.fld = tp##_##op(xa.fld, xb.fld, &env->fp_status); \
- if (unlikely(tp##_is_signaling_nan(xa.fld, &env->fp_status) || \
- tp##_is_signaling_nan(xb.fld, &env->fp_status))) { \
+ t.fld = tp##_##op(xa->fld, xb->fld, &env->fp_status); \
+ if (unlikely(tp##_is_signaling_nan(xa->fld, &env->fp_status) || \
+ tp##_is_signaling_nan(xb->fld, &env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2662,27 +2644,26 @@ VSX_MAX_MIN(xvminsp, minnum, 4, float32, VsrW(i))
#define VSX_MAX_MINC(name, max) \
void helper_##name(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
+ ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vex_flag = false; \
\
- getVSR(rA(opcode) + 32, &xa, env); \
- getVSR(rB(opcode) + 32, &xb, env); \
- getVSR(rD(opcode) + 32, &xt, env); \
- \
- if (unlikely(float64_is_any_nan(xa.VsrD(0)) || \
- float64_is_any_nan(xb.VsrD(0)))) { \
- if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) || \
- float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \
+ if (unlikely(float64_is_any_nan(xa->VsrD(0)) || \
+ float64_is_any_nan(xb->VsrD(0)))) { \
+ if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status) || \
+ float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \
vxsnan_flag = true; \
} \
- xt.VsrD(0) = xb.VsrD(0); \
+ t.VsrD(0) = xb->VsrD(0); \
} else if ((max && \
- !float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) || \
+ !float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status)) || \
(!max && \
- float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status))) { \
- xt.VsrD(0) = xa.VsrD(0); \
+ float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status))) { \
+ t.VsrD(0) = xa->VsrD(0); \
} else { \
- xt.VsrD(0) = xb.VsrD(0); \
+ t.VsrD(0) = xb->VsrD(0); \
} \
\
vex_flag = fpscr_ve & vxsnan_flag; \
@@ -2690,7 +2671,7 @@ void helper_##name(CPUPPCState *env, uint32_t opcode) \
float_invalid_op_vxsnan(env, GETPC()); \
} \
if (!vex_flag) { \
- putVSR(rD(opcode) + 32, &xt, env); \
+ *xt = t; \
} \
} \
@@ -2700,44 +2681,46 @@ VSX_MAX_MINC(xsmincdp, 0);
#define VSX_MAX_MINJ(name, max) \
void helper_##name(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
+ ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vex_flag = false; \
\
- getVSR(rA(opcode) + 32, &xa, env); \
- getVSR(rB(opcode) + 32, &xb, env); \
- getVSR(rD(opcode) + 32, &xt, env); \
- \
- if (unlikely(float64_is_any_nan(xa.VsrD(0)))) { \
- if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status)) { \
+ if (unlikely(float64_is_any_nan(xa->VsrD(0)))) { \
+ if (float64_is_signaling_nan(xa->VsrD(0), &env->fp_status)) { \
vxsnan_flag = true; \
} \
- xt.VsrD(0) = xa.VsrD(0); \
- } else if (unlikely(float64_is_any_nan(xb.VsrD(0)))) { \
- if (float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \
+ t.VsrD(0) = xa->VsrD(0); \
+ } else if (unlikely(float64_is_any_nan(xb->VsrD(0)))) { \
+ if (float64_is_signaling_nan(xb->VsrD(0), &env->fp_status)) { \
vxsnan_flag = true; \
} \
- xt.VsrD(0) = xb.VsrD(0); \
- } else if (float64_is_zero(xa.VsrD(0)) && float64_is_zero(xb.VsrD(0))) { \
+ t.VsrD(0) = xb->VsrD(0); \
+ } else if (float64_is_zero(xa->VsrD(0)) && \
+ float64_is_zero(xb->VsrD(0))) { \
if (max) { \
- if (!float64_is_neg(xa.VsrD(0)) || !float64_is_neg(xb.VsrD(0))) { \
- xt.VsrD(0) = 0ULL; \
+ if (!float64_is_neg(xa->VsrD(0)) || \
+ !float64_is_neg(xb->VsrD(0))) { \
+ t.VsrD(0) = 0ULL; \
} else { \
- xt.VsrD(0) = 0x8000000000000000ULL; \
+ t.VsrD(0) = 0x8000000000000000ULL; \
} \
} else { \
- if (float64_is_neg(xa.VsrD(0)) || float64_is_neg(xb.VsrD(0))) { \
- xt.VsrD(0) = 0x8000000000000000ULL; \
+ if (float64_is_neg(xa->VsrD(0)) || \
+ float64_is_neg(xb->VsrD(0))) { \
+ t.VsrD(0) = 0x8000000000000000ULL; \
} else { \
- xt.VsrD(0) = 0ULL; \
+ t.VsrD(0) = 0ULL; \
} \
} \
} else if ((max && \
- !float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) || \
+ !float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status)) || \
(!max && \
- float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status))) { \
- xt.VsrD(0) = xa.VsrD(0); \
+ float64_lt(xa->VsrD(0), xb->VsrD(0), &env->fp_status))) { \
+ t.VsrD(0) = xa->VsrD(0); \
} else { \
- xt.VsrD(0) = xb.VsrD(0); \
+ t.VsrD(0) = xb->VsrD(0); \
} \
\
vex_flag = fpscr_ve & vxsnan_flag; \
@@ -2745,7 +2728,7 @@ void helper_##name(CPUPPCState *env, uint32_t opcode) \
float_invalid_op_vxsnan(env, GETPC()); \
} \
if (!vex_flag) { \
- putVSR(rD(opcode) + 32, &xt, env); \
+ *xt = t; \
} \
} \
@@ -2765,39 +2748,38 @@ VSX_MAX_MINJ(xsminjdp, 0);
#define VSX_CMP(op, nels, tp, fld, cmp, svxvc, exp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
int all_true = 1; \
int all_false = 1; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
for (i = 0; i < nels; i++) { \
- if (unlikely(tp##_is_any_nan(xa.fld) || \
- tp##_is_any_nan(xb.fld))) { \
- if (tp##_is_signaling_nan(xa.fld, &env->fp_status) || \
- tp##_is_signaling_nan(xb.fld, &env->fp_status)) { \
+ if (unlikely(tp##_is_any_nan(xa->fld) || \
+ tp##_is_any_nan(xb->fld))) { \
+ if (tp##_is_signaling_nan(xa->fld, &env->fp_status) || \
+ tp##_is_signaling_nan(xb->fld, &env->fp_status)) { \
float_invalid_op_vxsnan(env, GETPC()); \
} \
if (svxvc) { \
float_invalid_op_vxvc(env, 0, GETPC()); \
} \
- xt.fld = 0; \
+ t.fld = 0; \
all_true = 0; \
} else { \
- if (tp##_##cmp(xb.fld, xa.fld, &env->fp_status) == exp) { \
- xt.fld = -1; \
+ if (tp##_##cmp(xb->fld, xa->fld, &env->fp_status) == exp) { \
+ t.fld = -1; \
all_false = 0; \
} else { \
- xt.fld = 0; \
+ t.fld = 0; \
all_true = 0; \
} \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
if ((opcode >> (31 - 21)) & 1) { \
env->crf[6] = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0); \
} \
@@ -2826,25 +2808,24 @@ VSX_CMP(xvcmpnesp, 4, float32, VsrW(i), eq, 0, 0)
#define VSX_CVT_FP_TO_FP(op, nels, stp, ttp, sfld, tfld, sfprf) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
for (i = 0; i < nels; i++) { \
- xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \
- if (unlikely(stp##_is_signaling_nan(xb.sfld, \
+ t.tfld = stp##_to_##ttp(xb->sfld, &env->fp_status); \
+ if (unlikely(stp##_is_signaling_nan(xb->sfld, \
&env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
- xt.tfld = ttp##_snan_to_qnan(xt.tfld); \
+ t.tfld = ttp##_snan_to_qnan(t.tfld); \
} \
if (sfprf) { \
- helper_compute_fprf_##ttp(env, xt.tfld); \
+ helper_compute_fprf_##ttp(env, t.tfld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2866,25 +2847,24 @@ VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, VsrW(2 * i), VsrD(i), 0)
#define VSX_CVT_FP_TO_FP_VECTOR(op, nels, stp, ttp, sfld, tfld, sfprf) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(rB(opcode) + 32, &xb, env); \
- getVSR(rD(opcode) + 32, &xt, env); \
- \
for (i = 0; i < nels; i++) { \
- xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \
- if (unlikely(stp##_is_signaling_nan(xb.sfld, \
+ t.tfld = stp##_to_##ttp(xb->sfld, &env->fp_status); \
+ if (unlikely(stp##_is_signaling_nan(xb->sfld, \
&env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
- xt.tfld = ttp##_snan_to_qnan(xt.tfld); \
+ t.tfld = ttp##_snan_to_qnan(t.tfld); \
} \
if (sfprf) { \
- helper_compute_fprf_##ttp(env, xt.tfld); \
+ helper_compute_fprf_##ttp(env, t.tfld); \
} \
} \
\
- putVSR(rD(opcode) + 32, &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2904,25 +2884,24 @@ VSX_CVT_FP_TO_FP_VECTOR(xscvdpqp, 1, float64, float128, VsrD(0), f128, 1)
#define VSX_CVT_FP_TO_FP_HP(op, nels, stp, ttp, sfld, tfld, sfprf) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = { }; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- memset(&xt, 0, sizeof(xt)); \
- \
for (i = 0; i < nels; i++) { \
- xt.tfld = stp##_to_##ttp(xb.sfld, 1, &env->fp_status); \
- if (unlikely(stp##_is_signaling_nan(xb.sfld, \
+ t.tfld = stp##_to_##ttp(xb->sfld, 1, &env->fp_status); \
+ if (unlikely(stp##_is_signaling_nan(xb->sfld, \
&env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
- xt.tfld = ttp##_snan_to_qnan(xt.tfld); \
+ t.tfld = ttp##_snan_to_qnan(t.tfld); \
} \
if (sfprf) { \
- helper_compute_fprf_##ttp(env, xt.tfld); \
+ helper_compute_fprf_##ttp(env, t.tfld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -2937,26 +2916,25 @@ VSX_CVT_FP_TO_FP_HP(xvcvhpsp, 4, float16, float32, VsrH(2 * i + 1), VsrW(i), 0)
*/
void helper_xscvqpdp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xb;
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)];
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)];
+ ppc_vsr_t t = { };
float_status tstat;
- getVSR(rB(opcode) + 32, &xb, env);
- memset(&xt, 0, sizeof(xt));
-
tstat = env->fp_status;
if (unlikely(Rc(opcode) != 0)) {
tstat.float_rounding_mode = float_round_to_odd;
}
- xt.VsrD(0) = float128_to_float64(xb.f128, &tstat);
+ t.VsrD(0) = float128_to_float64(xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
- if (unlikely(float128_is_signaling_nan(xb.f128, &tstat))) {
+ if (unlikely(float128_is_signaling_nan(xb->f128, &tstat))) {
float_invalid_op_vxsnan(env, GETPC());
- xt.VsrD(0) = float64_snan_to_qnan(xt.VsrD(0));
+ t.VsrD(0) = float64_snan_to_qnan(t.VsrD(0));
}
- helper_compute_fprf_float64(env, xt.VsrD(0));
+ helper_compute_fprf_float64(env, t.VsrD(0));
- putVSR(rD(opcode) + 32, &xt, env);
+ *xt = t;
do_float_check_status(env, GETPC());
}
@@ -2990,24 +2968,23 @@ uint64_t helper_xscvspdpn(CPUPPCState *env, uint64_t xb)
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
int all_flags = env->fp_status.float_exception_flags, flags; \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
for (i = 0; i < nels; i++) { \
env->fp_status.float_exception_flags = 0; \
- xt.tfld = stp##_to_##ttp##_round_to_zero(xb.sfld, &env->fp_status); \
+ t.tfld = stp##_to_##ttp##_round_to_zero(xb->sfld, &env->fp_status); \
flags = env->fp_status.float_exception_flags; \
if (unlikely(flags & float_flag_invalid)) { \
- float_invalid_cvt(env, 0, GETPC(), stp##_classify(xb.sfld)); \
- xt.tfld = rnan; \
+ float_invalid_cvt(env, 0, GETPC(), stp##_classify(xb->sfld)); \
+ t.tfld = rnan; \
} \
all_flags |= flags; \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
env->fp_status.float_exception_flags = all_flags; \
do_float_check_status(env, GETPC()); \
}
@@ -3042,18 +3019,17 @@ VSX_CVT_FP_TO_INT(xvcvspuxws, 4, float32, uint32, VsrW(i), VsrW(i), 0U)
#define VSX_CVT_FP_TO_INT_VECTOR(op, stp, ttp, sfld, tfld, rnan) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
+ ppc_vsr_t t = { }; \
\
- getVSR(rB(opcode) + 32, &xb, env); \
- memset(&xt, 0, sizeof(xt)); \
- \
- xt.tfld = stp##_to_##ttp##_round_to_zero(xb.sfld, &env->fp_status); \
+ t.tfld = stp##_to_##ttp##_round_to_zero(xb->sfld, &env->fp_status); \
if (env->fp_status.float_exception_flags & float_flag_invalid) { \
- float_invalid_cvt(env, 0, GETPC(), stp##_classify(xb.sfld)); \
- xt.tfld = rnan; \
+ float_invalid_cvt(env, 0, GETPC(), stp##_classify(xb->sfld)); \
+ t.tfld = rnan; \
} \
\
- putVSR(rD(opcode) + 32, &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -3079,23 +3055,22 @@ VSX_CVT_FP_TO_INT_VECTOR(xscvqpuwz, float128, uint32, f128, VsrD(0), 0x0ULL)
#define VSX_CVT_INT_TO_FP(op, nels, stp, ttp, sfld, tfld, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
- \
for (i = 0; i < nels; i++) { \
- xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \
+ t.tfld = stp##_to_##ttp(xb->sfld, &env->fp_status); \
if (r2sp) { \
- xt.tfld = helper_frsp(env, xt.tfld); \
+ t.tfld = helper_frsp(env, t.tfld); \
} \
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.tfld); \
+ helper_compute_fprf_float64(env, t.tfld); \
} \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -3123,15 +3098,14 @@ VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, VsrW(i), VsrW(i), 0, 0)
#define VSX_CVT_INT_TO_FP_VECTOR(op, stp, ttp, sfld, tfld) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
- \
- getVSR(rB(opcode) + 32, &xb, env); \
- getVSR(rD(opcode) + 32, &xt, env); \
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
+ ppc_vsr_t t = *xt; \
\
- xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \
- helper_compute_fprf_##ttp(env, xt.tfld); \
+ t.tfld = stp##_to_##ttp(xb->sfld, &env->fp_status); \
+ helper_compute_fprf_##ttp(env, t.tfld); \
\
- putVSR(xT(opcode) + 32, &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -3157,25 +3131,25 @@ VSX_CVT_INT_TO_FP_VECTOR(xscvudqp, uint64, float128, VsrD(0), f128)
#define VSX_ROUND(op, nels, tp, fld, rmode, sfprf) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i; \
- getVSR(xB(opcode), &xb, env); \
- getVSR(xT(opcode), &xt, env); \
\
if (rmode != FLOAT_ROUND_CURRENT) { \
set_float_rounding_mode(rmode, &env->fp_status); \
} \
\
for (i = 0; i < nels; i++) { \
- if (unlikely(tp##_is_signaling_nan(xb.fld, \
+ if (unlikely(tp##_is_signaling_nan(xb->fld, \
&env->fp_status))) { \
float_invalid_op_vxsnan(env, GETPC()); \
- xt.fld = tp##_snan_to_qnan(xb.fld); \
+ t.fld = tp##_snan_to_qnan(xb->fld); \
} else { \
- xt.fld = tp##_round_to_int(xb.fld, &env->fp_status); \
+ t.fld = tp##_round_to_int(xb->fld, &env->fp_status); \
} \
if (sfprf) { \
- helper_compute_fprf_float64(env, xt.fld); \
+ helper_compute_fprf_float64(env, t.fld); \
} \
} \
\
@@ -3189,7 +3163,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
env->fp_status.float_exception_flags &= ~float_flag_inexact; \
} \
\
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
do_float_check_status(env, GETPC()); \
}
@@ -3225,21 +3199,21 @@ uint64_t helper_xsrsp(CPUPPCState *env, uint64_t xb)
#define VSX_XXPERM(op, indexed) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xa, pcv, xto; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
+ ppc_vsr_t *pcv = &env->vsr[xB(opcode)]; \
+ ppc_vsr_t t = *xt; \
int i, idx; \
\
- getVSR(xA(opcode), &xa, env); \
- getVSR(xT(opcode), &xt, env); \
- getVSR(xB(opcode), &pcv, env); \
- \
for (i = 0; i < 16; i++) { \
- idx = pcv.VsrB(i) & 0x1F; \
+ idx = pcv->VsrB(i) & 0x1F; \
if (indexed) { \
idx = 31 - idx; \
} \
- xto.VsrB(i) = (idx <= 15) ? xa.VsrB(idx) : xt.VsrB(idx - 16); \
+ t.VsrB(i) = (idx <= 15) ? xa->VsrB(idx) \
+ : xt->VsrB(idx - 16); \
} \
- putVSR(xT(opcode), &xto, env); \
+ *xt = t; \
}
VSX_XXPERM(xxperm, 0)
@@ -3247,22 +3221,21 @@ VSX_XXPERM(xxpermr, 1)
void helper_xvxsigsp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xb;
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)];
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)];
+ ppc_vsr_t t = { };
uint32_t exp, i, fraction;
- getVSR(xB(opcode), &xb, env);
- memset(&xt, 0, sizeof(xt));
-
for (i = 0; i < 4; i++) {
- exp = (xb.VsrW(i) >> 23) & 0xFF;
- fraction = xb.VsrW(i) & 0x7FFFFF;
+ exp = (xb->VsrW(i) >> 23) & 0xFF;
+ fraction = xb->VsrW(i) & 0x7FFFFF;
if (exp != 0 && exp != 255) {
- xt.VsrW(i) = fraction | 0x00800000;
+ t.VsrW(i) = fraction | 0x00800000;
} else {
- xt.VsrW(i) = fraction;
+ t.VsrW(i) = fraction;
}
}
- putVSR(xT(opcode), &xt, env);
+ *xt = t;
}
/*
@@ -3279,27 +3252,28 @@ void helper_xvxsigsp(CPUPPCState *env, uint32_t opcode)
#define VSX_TEST_DC(op, nels, xbn, tp, fld, tfld, fld_max, scrf) \
void helper_##op(CPUPPCState *env, uint32_t opcode) \
{ \
- ppc_vsr_t xt, xb; \
+ ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
+ ppc_vsr_t *xb = &env->vsr[xbn]; \
+ ppc_vsr_t t = { }; \
uint32_t i, sign, dcmx; \
uint32_t cc, match = 0; \
\
- getVSR(xbn, &xb, env); \
if (!scrf) { \
- memset(&xt, 0, sizeof(xt)); \
dcmx = DCMX_XV(opcode); \
} else { \
+ t = *xt; \
dcmx = DCMX(opcode); \
} \
\
for (i = 0; i < nels; i++) { \
- sign = tp##_is_neg(xb.fld); \
- if (tp##_is_any_nan(xb.fld)) { \
+ sign = tp##_is_neg(xb->fld); \
+ if (tp##_is_any_nan(xb->fld)) { \
match = extract32(dcmx, 6, 1); \
- } else if (tp##_is_infinity(xb.fld)) { \
+ } else if (tp##_is_infinity(xb->fld)) { \
match = extract32(dcmx, 4 + !sign, 1); \
- } else if (tp##_is_zero(xb.fld)) { \
+ } else if (tp##_is_zero(xb->fld)) { \
match = extract32(dcmx, 2 + !sign, 1); \
- } else if (tp##_is_zero_or_denormal(xb.fld)) { \
+ } else if (tp##_is_zero_or_denormal(xb->fld)) { \
match = extract32(dcmx, 0 + !sign, 1); \
} \
\
@@ -3309,12 +3283,12 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
env->fpscr |= cc << FPSCR_FPRF; \
env->crf[BF(opcode)] = cc; \
} else { \
- xt.tfld = match ? fld_max : 0; \
+ t.tfld = match ? fld_max : 0; \
} \
match = 0; \
} \
if (!scrf) { \
- putVSR(xT(opcode), &xt, env); \
+ *xt = t; \
} \
}
@@ -3325,29 +3299,28 @@ VSX_TEST_DC(xststdcqp, 1, (rB(opcode) + 32), float128, f128, VsrD(0), 0, 1)
void helper_xststdcsp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xb;
+ ppc_vsr_t *xb = &env->vsr[xB(opcode)];
uint32_t dcmx, sign, exp;
uint32_t cc, match = 0, not_sp = 0;
- getVSR(xB(opcode), &xb, env);
dcmx = DCMX(opcode);
- exp = (xb.VsrD(0) >> 52) & 0x7FF;
+ exp = (xb->VsrD(0) >> 52) & 0x7FF;
- sign = float64_is_neg(xb.VsrD(0));
- if (float64_is_any_nan(xb.VsrD(0))) {
+ sign = float64_is_neg(xb->VsrD(0));
+ if (float64_is_any_nan(xb->VsrD(0))) {
match = extract32(dcmx, 6, 1);
- } else if (float64_is_infinity(xb.VsrD(0))) {
+ } else if (float64_is_infinity(xb->VsrD(0))) {
match = extract32(dcmx, 4 + !sign, 1);
- } else if (float64_is_zero(xb.VsrD(0))) {
+ } else if (float64_is_zero(xb->VsrD(0))) {
match = extract32(dcmx, 2 + !sign, 1);
- } else if (float64_is_zero_or_denormal(xb.VsrD(0)) ||
+ } else if (float64_is_zero_or_denormal(xb->VsrD(0)) ||
(exp > 0 && exp < 0x381)) {
match = extract32(dcmx, 0 + !sign, 1);
}
- not_sp = !float64_eq(xb.VsrD(0),
+ not_sp = !float64_eq(xb->VsrD(0),
float32_to_float64(
- float64_to_float32(xb.VsrD(0), &env->fp_status),
+ float64_to_float32(xb->VsrD(0), &env->fp_status),
&env->fp_status), &env->fp_status);
cc = sign << CRF_LT_BIT | match << CRF_EQ_BIT | not_sp << CRF_SO_BIT;
@@ -3358,16 +3331,15 @@ void helper_xststdcsp(CPUPPCState *env, uint32_t opcode)
void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xb;
- ppc_vsr_t xt;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = { };
uint8_t r = Rrm(opcode);
uint8_t ex = Rc(opcode);
uint8_t rmc = RMC(opcode);
uint8_t rmode = 0;
float_status tstat;
- getVSR(rB(opcode) + 32, &xb, env);
- memset(&xt, 0, sizeof(xt));
helper_reset_fpstatus(env);
if (r == 0 && rmc == 0) {
@@ -3396,13 +3368,13 @@ void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
tstat = env->fp_status;
set_float_exception_flags(0, &tstat);
set_float_rounding_mode(rmode, &tstat);
- xt.f128 = float128_round_to_int(xb.f128, &tstat);
+ t.f128 = float128_round_to_int(xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
- if (float128_is_signaling_nan(xb.f128, &tstat)) {
+ if (float128_is_signaling_nan(xb->f128, &tstat)) {
float_invalid_op_vxsnan(env, GETPC());
- xt.f128 = float128_snan_to_qnan(xt.f128);
+ t.f128 = float128_snan_to_qnan(t.f128);
}
}
@@ -3410,23 +3382,22 @@ void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
env->fp_status.float_exception_flags &= ~float_flag_inexact;
}
- helper_compute_fprf_float128(env, xt.f128);
+ helper_compute_fprf_float128(env, t.f128);
do_float_check_status(env, GETPC());
- putVSR(rD(opcode) + 32, &xt, env);
+ *xt = t;
}
void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xb;
- ppc_vsr_t xt;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = { };
uint8_t r = Rrm(opcode);
uint8_t rmc = RMC(opcode);
uint8_t rmode = 0;
floatx80 round_res;
float_status tstat;
- getVSR(rB(opcode) + 32, &xb, env);
- memset(&xt, 0, sizeof(xt));
helper_reset_fpstatus(env);
if (r == 0 && rmc == 0) {
@@ -3455,30 +3426,29 @@ void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode)
tstat = env->fp_status;
set_float_exception_flags(0, &tstat);
set_float_rounding_mode(rmode, &tstat);
- round_res = float128_to_floatx80(xb.f128, &tstat);
- xt.f128 = floatx80_to_float128(round_res, &tstat);
+ round_res = float128_to_floatx80(xb->f128, &tstat);
+ t.f128 = floatx80_to_float128(round_res, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
- if (float128_is_signaling_nan(xb.f128, &tstat)) {
+ if (float128_is_signaling_nan(xb->f128, &tstat)) {
float_invalid_op_vxsnan(env, GETPC());
- xt.f128 = float128_snan_to_qnan(xt.f128);
+ t.f128 = float128_snan_to_qnan(t.f128);
}
}
- helper_compute_fprf_float128(env, xt.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ helper_compute_fprf_float128(env, t.f128);
+ *xt = t;
do_float_check_status(env, GETPC());
}
void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xb;
- ppc_vsr_t xt;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = { };
float_status tstat;
- getVSR(rB(opcode) + 32, &xb, env);
- memset(&xt, 0, sizeof(xt));
helper_reset_fpstatus(env);
tstat = env->fp_status;
@@ -3487,34 +3457,34 @@ void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode)
}
set_float_exception_flags(0, &tstat);
- xt.f128 = float128_sqrt(xb.f128, &tstat);
+ t.f128 = float128_sqrt(xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
- if (float128_is_signaling_nan(xb.f128, &tstat)) {
+ if (float128_is_signaling_nan(xb->f128, &tstat)) {
float_invalid_op_vxsnan(env, GETPC());
- xt.f128 = float128_snan_to_qnan(xb.f128);
- } else if (float128_is_quiet_nan(xb.f128, &tstat)) {
- xt.f128 = xb.f128;
- } else if (float128_is_neg(xb.f128) && !float128_is_zero(xb.f128)) {
+ t.f128 = float128_snan_to_qnan(xb->f128);
+ } else if (float128_is_quiet_nan(xb->f128, &tstat)) {
+ t.f128 = xb->f128;
+ } else if (float128_is_neg(xb->f128) && !float128_is_zero(xb->f128)) {
float_invalid_op_vxsqrt(env, 1, GETPC());
- xt.f128 = float128_default_nan(&env->fp_status);
+ t.f128 = float128_default_nan(&env->fp_status);
}
}
- helper_compute_fprf_float128(env, xt.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ helper_compute_fprf_float128(env, t.f128);
+ *xt = t;
do_float_check_status(env, GETPC());
}
void helper_xssubqp(CPUPPCState *env, uint32_t opcode)
{
- ppc_vsr_t xt, xa, xb;
+ ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
+ ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
+ ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
+ ppc_vsr_t t = *xt;
float_status tstat;
- getVSR(rA(opcode) + 32, &xa, env);
- getVSR(rB(opcode) + 32, &xb, env);
- getVSR(rD(opcode) + 32, &xt, env);
helper_reset_fpstatus(env);
tstat = env->fp_status;
@@ -3523,16 +3493,16 @@ void helper_xssubqp(CPUPPCState *env, uint32_t opcode)
}
set_float_exception_flags(0, &tstat);
- xt.f128 = float128_sub(xa.f128, xb.f128, &tstat);
+ t.f128 = float128_sub(xa->f128, xb->f128, &tstat);
env->fp_status.float_exception_flags |= tstat.float_exception_flags;
if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {
float_invalid_op_addsub(env, 1, GETPC(),
- float128_classify(xa.f128) |
- float128_classify(xb.f128));
+ float128_classify(xa->f128) |
+ float128_classify(xb->f128));
}
- helper_compute_fprf_float128(env, xt.f128);
- putVSR(rD(opcode) + 32, &xt, env);
+ helper_compute_fprf_float128(env, t.f128);
+ *xt = t;
do_float_check_status(env, GETPC());
}
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [Qemu-devel] [PATCH v3 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c Mark Cave-Ayland
@ 2019-06-17 1:14 ` Richard Henderson
0 siblings, 0 replies; 21+ messages in thread
From: Richard Henderson @ 2019-06-17 1:14 UTC (permalink / raw)
To: Mark Cave-Ayland, qemu-devel, qemu-ppc, david, rth, gkurz
On 6/16/19 5:37 AM, Mark Cave-Ayland wrote:
> Since commit 8a14d31b00 "target/ppc: switch fpr/vsrl registers so all VSX
> registers are in host endian order" functions getVSR() and putVSR() which used
> to convert the VSR registers into host endian order are no longer required.
>
> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
> ---
> target/ppc/fpu_helper.c | 762 +++++++++++++++++++++++-------------------------
> 1 file changed, 366 insertions(+), 396 deletions(-)
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
r~
^ permalink raw reply [flat|nested] 21+ messages in thread
* [Qemu-devel] [PATCH v3 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-17 1:57 ` Richard Henderson
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 03/15] target/ppc: remove getVSR()/putVSR() from int_helper.c Mark Cave-Ayland
` (15 subsequent siblings)
17 siblings, 1 reply; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Since commit 8a14d31b00 "target/ppc: switch fpr/vsrl registers so all VSX
registers are in host endian order" functions getVSR() and putVSR() which used
to convert the VSR registers into host endian order are no longer required.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
---
target/ppc/mem_helper.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 5b0f9ee50d..87632ccf53 100644
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -417,26 +417,27 @@ STVE(stvewx, cpu_stl_data_ra, bswap32, u32)
void helper_##name(CPUPPCState *env, target_ulong addr, \
target_ulong xt_num, target_ulong rb) \
{ \
- int i; \
- ppc_vsr_t xt; \
+ ppc_vsr_t *xt = &env->vsr[xt_num]; \
+ ppc_vsr_t t; \
uint64_t nb = GET_NB(rb); \
+ int i; \
\
- xt.s128 = int128_zero(); \
+ t.s128 = int128_zero(); \
if (nb) { \
nb = (nb >= 16) ? 16 : nb; \
if (msr_le && !lj) { \
for (i = 16; i > 16 - nb; i--) { \
- xt.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC()); \
+ t.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC()); \
addr = addr_add(env, addr, 1); \
} \
} else { \
for (i = 0; i < nb; i++) { \
- xt.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC()); \
+ t.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC()); \
addr = addr_add(env, addr, 1); \
} \
} \
} \
- putVSR(xt_num, &xt, env); \
+ *xt = t; \
}
VSX_LXVL(lxvl, 0)
@@ -447,23 +448,23 @@ VSX_LXVL(lxvll, 1)
void helper_##name(CPUPPCState *env, target_ulong addr, \
target_ulong xt_num, target_ulong rb) \
{ \
- int i; \
- ppc_vsr_t xt; \
+ ppc_vsr_t *xt = &env->vsr[xt_num]; \
target_ulong nb = GET_NB(rb); \
+ int i; \
\
if (!nb) { \
return; \
} \
- getVSR(xt_num, &xt, env); \
+ \
nb = (nb >= 16) ? 16 : nb; \
if (msr_le && !lj) { \
for (i = 16; i > 16 - nb; i--) { \
- cpu_stb_data_ra(env, addr, xt.VsrB(i - 1), GETPC()); \
+ cpu_stb_data_ra(env, addr, xt->VsrB(i - 1), GETPC()); \
addr = addr_add(env, addr, 1); \
} \
} else { \
for (i = 0; i < nb; i++) { \
- cpu_stb_data_ra(env, addr, xt.VsrB(i), GETPC()); \
+ cpu_stb_data_ra(env, addr, xt->VsrB(i), GETPC()); \
addr = addr_add(env, addr, 1); \
} \
} \
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [Qemu-devel] [PATCH v3 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c Mark Cave-Ayland
@ 2019-06-17 1:57 ` Richard Henderson
0 siblings, 0 replies; 21+ messages in thread
From: Richard Henderson @ 2019-06-17 1:57 UTC (permalink / raw)
To: Mark Cave-Ayland, qemu-devel, qemu-ppc, david, rth, gkurz
On 6/16/19 5:37 AM, Mark Cave-Ayland wrote:
> Since commit 8a14d31b00 "target/ppc: switch fpr/vsrl registers so all VSX
> registers are in host endian order" functions getVSR() and putVSR() which used
> to convert the VSR registers into host endian order are no longer required.
>
> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
> ---
> target/ppc/mem_helper.c | 23 ++++++++++++-----------
> 1 file changed, 12 insertions(+), 11 deletions(-)
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
r~
^ permalink raw reply [flat|nested] 21+ messages in thread
* [Qemu-devel] [PATCH v3 03/15] target/ppc: remove getVSR()/putVSR() from int_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 01/15] target/ppc: remove getVSR()/putVSR() from fpu_helper.c Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 02/15] target/ppc: remove getVSR()/putVSR() from mem_helper.c Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 04/15] target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions Mark Cave-Ayland
` (14 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Since commit 8a14d31b00 "target/ppc: switch fpr/vsrl registers so all VSX
registers are in host endian order" functions getVSR() and putVSR() which used
to convert the VSR registers into host endian order are no longer required.
Now that there are now no more users of getVSR()/putVSR() these functions can
be completely removed.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/int_helper.c | 22 ++++++++++------------
target/ppc/internal.h | 12 ------------
2 files changed, 10 insertions(+), 24 deletions(-)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 8ce89f2ad9..3b8939edcc 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1902,38 +1902,36 @@ VEXTRACT(d, u64)
void helper_xxextractuw(CPUPPCState *env, target_ulong xtn,
target_ulong xbn, uint32_t index)
{
- ppc_vsr_t xt, xb;
+ ppc_vsr_t *xt = &env->vsr[xtn];
+ ppc_vsr_t *xb = &env->vsr[xbn];
+ ppc_vsr_t t = { };
size_t es = sizeof(uint32_t);
uint32_t ext_index;
int i;
- getVSR(xbn, &xb, env);
- memset(&xt, 0, sizeof(xt));
-
ext_index = index;
for (i = 0; i < es; i++, ext_index++) {
- xt.VsrB(8 - es + i) = xb.VsrB(ext_index % 16);
+ t.VsrB(8 - es + i) = xb->VsrB(ext_index % 16);
}
- putVSR(xtn, &xt, env);
+ *xt = t;
}
void helper_xxinsertw(CPUPPCState *env, target_ulong xtn,
target_ulong xbn, uint32_t index)
{
- ppc_vsr_t xt, xb;
+ ppc_vsr_t *xt = &env->vsr[xtn];
+ ppc_vsr_t *xb = &env->vsr[xbn];
+ ppc_vsr_t t = *xt;
size_t es = sizeof(uint32_t);
int ins_index, i = 0;
- getVSR(xbn, &xb, env);
- getVSR(xtn, &xt, env);
-
ins_index = index;
for (i = 0; i < es && ins_index < 16; i++, ins_index++) {
- xt.VsrB(ins_index) = xb.VsrB(8 - es + i);
+ t.VsrB(ins_index) = xb->VsrB(8 - es + i);
}
- putVSR(xtn, &xt, env);
+ *xt = t;
}
#define VEXT_SIGNED(name, element, cast) \
diff --git a/target/ppc/internal.h b/target/ppc/internal.h
index fb6f64ed1e..d3d327e548 100644
--- a/target/ppc/internal.h
+++ b/target/ppc/internal.h
@@ -204,18 +204,6 @@ EXTRACT_HELPER(IMM8, 11, 8);
EXTRACT_HELPER(DCMX, 16, 7);
EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1, 6, 6);
-static inline void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
-{
- vsr->VsrD(0) = env->vsr[n].VsrD(0);
- vsr->VsrD(1) = env->vsr[n].VsrD(1);
-}
-
-static inline void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env)
-{
- env->vsr[n].VsrD(0) = vsr->VsrD(0);
- env->vsr[n].VsrD(1) = vsr->VsrD(1);
-}
-
void helper_compute_fprf_float16(CPUPPCState *env, float16 arg);
void helper_compute_fprf_float32(CPUPPCState *env, float32 arg);
void helper_compute_fprf_float128(CPUPPCState *env, float128 arg);
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 04/15] target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (2 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 03/15] target/ppc: remove getVSR()/putVSR() from int_helper.c Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 05/15] target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c Mark Cave-Ayland
` (13 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new VSX_CMP macro which performs the decode based upon xT, xA
and xB at translation time.
Subsequent commits will make the same changes for other instructions however
the xvcmp* instructions are different in that they return a set of flags to be
optionally written back to the crf[6] register. Move this logic from the
helper function to the generator function, along with the float_status update.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 15 +++++-------
target/ppc/helper.h | 20 +++++++++------
target/ppc/translate/vsx-impl.inc.c | 49 +++++++++++++++++++++++++++++++------
3 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 8da805d175..b1ce954354 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2746,12 +2746,11 @@ VSX_MAX_MINJ(xsminjdp, 0);
* exp - expected result of comparison
*/
#define VSX_CMP(op, nels, tp, fld, cmp, svxvc, exp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+uint32_t helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
+ uint32_t crf6 = 0; \
int i; \
int all_true = 1; \
int all_false = 1; \
@@ -2780,11 +2779,9 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \
} \
\
*xt = t; \
- if ((opcode >> (31 - 21)) & 1) { \
- env->crf[6] = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0); \
- } \
- do_float_check_status(env, GETPC()); \
- }
+ crf6 = (all_true ? 0x8 : 0) | (all_false ? 0x2 : 0); \
+ return crf6; \
+}
VSX_CMP(xvcmpeqdp, 2, float64, VsrD(i), eq, 0, 1)
VSX_CMP(xvcmpgedp, 2, float64, VsrD(i), le, 1, 1)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 02b67a333e..8666415169 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -108,6 +108,10 @@ DEF_HELPER_FLAGS_1(ftsqrt, TCG_CALL_NO_RWG_SE, i32, i64)
#define dh_ctype_avr ppc_avr_t *
#define dh_is_signed_avr dh_is_signed_ptr
+#define dh_alias_vsr ptr
+#define dh_ctype_vsr ppc_vsr_t *
+#define dh_is_signed_vsr dh_is_signed_ptr
+
DEF_HELPER_3(vavgub, void, avr, avr, avr)
DEF_HELPER_3(vavguh, void, avr, avr, avr)
DEF_HELPER_3(vavguw, void, avr, avr, avr)
@@ -468,10 +472,10 @@ DEF_HELPER_2(xvnmsubadp, void, env, i32)
DEF_HELPER_2(xvnmsubmdp, void, env, i32)
DEF_HELPER_2(xvmaxdp, void, env, i32)
DEF_HELPER_2(xvmindp, void, env, i32)
-DEF_HELPER_2(xvcmpeqdp, void, env, i32)
-DEF_HELPER_2(xvcmpgedp, void, env, i32)
-DEF_HELPER_2(xvcmpgtdp, void, env, i32)
-DEF_HELPER_2(xvcmpnedp, void, env, i32)
+DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpgedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpgtdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpnedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_2(xvcvdpsp, void, env, i32)
DEF_HELPER_2(xvcvdpsxds, void, env, i32)
DEF_HELPER_2(xvcvdpsxws, void, env, i32)
@@ -506,10 +510,10 @@ DEF_HELPER_2(xvnmsubasp, void, env, i32)
DEF_HELPER_2(xvnmsubmsp, void, env, i32)
DEF_HELPER_2(xvmaxsp, void, env, i32)
DEF_HELPER_2(xvminsp, void, env, i32)
-DEF_HELPER_2(xvcmpeqsp, void, env, i32)
-DEF_HELPER_2(xvcmpgesp, void, env, i32)
-DEF_HELPER_2(xvcmpgtsp, void, env, i32)
-DEF_HELPER_2(xvcmpnesp, void, env, i32)
+DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpgesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpgtsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
+DEF_HELPER_FLAGS_4(xvcmpnesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_2(xvcvspdp, void, env, i32)
DEF_HELPER_2(xvcvsphp, void, env, i32)
DEF_HELPER_2(xvcvhpsp, void, env, i32)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index e9b7562f84..900ba07d40 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -20,6 +20,13 @@ static inline void set_cpu_vsrl(int n, TCGv_i64 src)
tcg_gen_st_i64(src, cpu_env, vsr64_offset(n, false));
}
+static inline TCGv_ptr gen_vsr_ptr(int reg)
+{
+ TCGv_ptr r = tcg_temp_new_ptr();
+ tcg_gen_addi_ptr(r, cpu_env, vsr_full_offset(reg));
+ return r;
+}
+
#define VSX_LOAD_SCALAR(name, operation) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -958,6 +965,40 @@ VSX_VECTOR_MOVE(xvnabssp, OP_NABS, SGN_MASK_SP)
VSX_VECTOR_MOVE(xvnegsp, OP_NEG, SGN_MASK_SP)
VSX_VECTOR_MOVE(xvcpsgnsp, OP_CPSGN, SGN_MASK_SP)
+#define VSX_CMP(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 ignored; \
+ TCGv_ptr xt, xa, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ xa = gen_vsr_ptr(xA(ctx->opcode)); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
+ if ((ctx->opcode >> (31 - 21)) & 1) { \
+ gen_helper_##name(cpu_crf[6], cpu_env, xt, xa, xb); \
+ } else { \
+ ignored = tcg_temp_new_i32(); \
+ gen_helper_##name(ignored, cpu_env, xt, xa, xb); \
+ tcg_temp_free_i32(ignored); \
+ } \
+ gen_helper_float_check_status(cpu_env); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(xb); \
+}
+
+VSX_CMP(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
+VSX_CMP(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
+VSX_CMP(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
+VSX_CMP(xvcmpnedp, 0x0C, 0x0F, 0, PPC2_ISA300)
+VSX_CMP(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
+VSX_CMP(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
+VSX_CMP(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
+VSX_CMP(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
+
#define GEN_VSX_HELPER_2(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1097,10 +1138,6 @@ GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpeqdp, 0x0C, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpgtdp, 0x0C, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpgedp, 0x0C, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpnedp, 0x0C, 0x0F, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
@@ -1135,10 +1172,6 @@ GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpeqsp, 0x0C, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300)
GEN_VSX_HELPER_2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 05/15] target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (3 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 04/15] target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 06/15] target/ppc: introduce separate generator and helper for xscvqpdp Mark Cave-Ayland
` (12 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_X3 macro which performs the decode based
upon xT, xA and xB at translation time.
With the previous changes to the VSX_CMP generator and helper macros the
opcode parameter is no longer required in the common case and can be
removed.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 42 ++++-------
target/ppc/helper.h | 120 +++++++++++++++----------------
target/ppc/translate/vsx-impl.inc.c | 137 ++++++++++++++++++++----------------
3 files changed, 151 insertions(+), 148 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index b1ce954354..012dfdac3e 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -1801,11 +1801,9 @@ uint32_t helper_efdcmpeq(CPUPPCState *env, uint64_t op1, uint64_t op2)
* sfprf - set FPRF
*/
#define VSX_ADD_SUB(name, op, nels, tp, fld, sfprf, r2sp) \
-void helper_##name(CPUPPCState *env, uint32_t opcode) \
+void helper_##name(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -1884,11 +1882,9 @@ void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
* sfprf - set FPRF
*/
#define VSX_MUL(op, nels, tp, fld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -1962,11 +1958,9 @@ void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
* sfprf - set FPRF
*/
#define VSX_DIV(op, nels, tp, fld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2304,11 +2298,9 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23)
* sfprf - set FPRF
*/
#define VSX_MADD(op, nels, tp, fld, maddflgs, afrm, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt, *b, *c; \
int i; \
\
@@ -2402,11 +2394,9 @@ VSX_MADD(xvnmsubmsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0, 0)
* svxvc - set VXVC bit
*/
#define VSX_SCALAR_CMP_DP(op, cmp, exp, svxvc) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vxvc_flag = false, vex_flag = false; \
\
@@ -2614,11 +2604,9 @@ VSX_SCALAR_CMPQ(xscmpuqp, 0)
* fld - vsr_t field (VsrD(*) or VsrW(*))
*/
#define VSX_MAX_MIN(name, op, nels, tp, fld) \
-void helper_##name(CPUPPCState *env, uint32_t opcode) \
+void helper_##name(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -3194,11 +3182,9 @@ uint64_t helper_xsrsp(CPUPPCState *env, uint64_t xb)
}
#define VSX_XXPERM(op, indexed) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
+ ppc_vsr_t *xa, ppc_vsr_t *pcv) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *pcv = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i, idx; \
\
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 8666415169..f6a97cedc6 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -365,38 +365,38 @@ DEF_HELPER_4(bcdsr, i32, avr, avr, avr, i32)
DEF_HELPER_4(bcdtrunc, i32, avr, avr, avr, i32)
DEF_HELPER_4(bcdutrunc, i32, avr, avr, avr, i32)
-DEF_HELPER_2(xsadddp, void, env, i32)
+DEF_HELPER_4(xsadddp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsaddqp, void, env, i32)
-DEF_HELPER_2(xssubdp, void, env, i32)
-DEF_HELPER_2(xsmuldp, void, env, i32)
+DEF_HELPER_4(xssubdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmuldp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsmulqp, void, env, i32)
-DEF_HELPER_2(xsdivdp, void, env, i32)
+DEF_HELPER_4(xsdivdp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsdivqp, void, env, i32)
DEF_HELPER_2(xsredp, void, env, i32)
DEF_HELPER_2(xssqrtdp, void, env, i32)
DEF_HELPER_2(xsrsqrtedp, void, env, i32)
DEF_HELPER_2(xstdivdp, void, env, i32)
DEF_HELPER_2(xstsqrtdp, void, env, i32)
-DEF_HELPER_2(xsmaddadp, void, env, i32)
-DEF_HELPER_2(xsmaddmdp, void, env, i32)
-DEF_HELPER_2(xsmsubadp, void, env, i32)
-DEF_HELPER_2(xsmsubmdp, void, env, i32)
-DEF_HELPER_2(xsnmaddadp, void, env, i32)
-DEF_HELPER_2(xsnmaddmdp, void, env, i32)
-DEF_HELPER_2(xsnmsubadp, void, env, i32)
-DEF_HELPER_2(xsnmsubmdp, void, env, i32)
-DEF_HELPER_2(xscmpeqdp, void, env, i32)
-DEF_HELPER_2(xscmpgtdp, void, env, i32)
-DEF_HELPER_2(xscmpgedp, void, env, i32)
-DEF_HELPER_2(xscmpnedp, void, env, i32)
+DEF_HELPER_4(xsmaddadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmaddmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmsubadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmaddadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmaddmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmsubadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xscmpeqdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xscmpnedp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xscmpexpdp, void, env, i32)
DEF_HELPER_2(xscmpexpqp, void, env, i32)
DEF_HELPER_2(xscmpodp, void, env, i32)
DEF_HELPER_2(xscmpudp, void, env, i32)
DEF_HELPER_2(xscmpoqp, void, env, i32)
DEF_HELPER_2(xscmpuqp, void, env, i32)
-DEF_HELPER_2(xsmaxdp, void, env, i32)
-DEF_HELPER_2(xsmindp, void, env, i32)
+DEF_HELPER_4(xsmaxdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmindp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsmaxcdp, void, env, i32)
DEF_HELPER_2(xsmincdp, void, env, i32)
DEF_HELPER_2(xsmaxjdp, void, env, i32)
@@ -436,42 +436,42 @@ DEF_HELPER_2(xsrqpxp, void, env, i32)
DEF_HELPER_2(xssqrtqp, void, env, i32)
DEF_HELPER_2(xssubqp, void, env, i32)
-DEF_HELPER_2(xsaddsp, void, env, i32)
-DEF_HELPER_2(xssubsp, void, env, i32)
-DEF_HELPER_2(xsmulsp, void, env, i32)
-DEF_HELPER_2(xsdivsp, void, env, i32)
+DEF_HELPER_4(xsaddsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xssubsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmulsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsdivsp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsresp, void, env, i32)
DEF_HELPER_2(xsrsp, i64, env, i64)
DEF_HELPER_2(xssqrtsp, void, env, i32)
DEF_HELPER_2(xsrsqrtesp, void, env, i32)
-DEF_HELPER_2(xsmaddasp, void, env, i32)
-DEF_HELPER_2(xsmaddmsp, void, env, i32)
-DEF_HELPER_2(xsmsubasp, void, env, i32)
-DEF_HELPER_2(xsmsubmsp, void, env, i32)
-DEF_HELPER_2(xsnmaddasp, void, env, i32)
-DEF_HELPER_2(xsnmaddmsp, void, env, i32)
-DEF_HELPER_2(xsnmsubasp, void, env, i32)
-DEF_HELPER_2(xsnmsubmsp, void, env, i32)
+DEF_HELPER_4(xsmaddasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmaddmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmsubasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsmsubmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmaddasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmaddmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmsubasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xsnmsubmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xvadddp, void, env, i32)
-DEF_HELPER_2(xvsubdp, void, env, i32)
-DEF_HELPER_2(xvmuldp, void, env, i32)
-DEF_HELPER_2(xvdivdp, void, env, i32)
+DEF_HELPER_4(xvadddp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvsubdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmuldp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvdivdp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xvredp, void, env, i32)
DEF_HELPER_2(xvsqrtdp, void, env, i32)
DEF_HELPER_2(xvrsqrtedp, void, env, i32)
DEF_HELPER_2(xvtdivdp, void, env, i32)
DEF_HELPER_2(xvtsqrtdp, void, env, i32)
-DEF_HELPER_2(xvmaddadp, void, env, i32)
-DEF_HELPER_2(xvmaddmdp, void, env, i32)
-DEF_HELPER_2(xvmsubadp, void, env, i32)
-DEF_HELPER_2(xvmsubmdp, void, env, i32)
-DEF_HELPER_2(xvnmaddadp, void, env, i32)
-DEF_HELPER_2(xvnmaddmdp, void, env, i32)
-DEF_HELPER_2(xvnmsubadp, void, env, i32)
-DEF_HELPER_2(xvnmsubmdp, void, env, i32)
-DEF_HELPER_2(xvmaxdp, void, env, i32)
-DEF_HELPER_2(xvmindp, void, env, i32)
+DEF_HELPER_4(xvmaddadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmaddmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmsubadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmaddadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmaddmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmsubadp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmaxdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmindp, void, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgtdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
@@ -491,25 +491,25 @@ DEF_HELPER_2(xvrdpim, void, env, i32)
DEF_HELPER_2(xvrdpip, void, env, i32)
DEF_HELPER_2(xvrdpiz, void, env, i32)
-DEF_HELPER_2(xvaddsp, void, env, i32)
-DEF_HELPER_2(xvsubsp, void, env, i32)
-DEF_HELPER_2(xvmulsp, void, env, i32)
-DEF_HELPER_2(xvdivsp, void, env, i32)
+DEF_HELPER_4(xvaddsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvsubsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmulsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvdivsp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xvresp, void, env, i32)
DEF_HELPER_2(xvsqrtsp, void, env, i32)
DEF_HELPER_2(xvrsqrtesp, void, env, i32)
DEF_HELPER_2(xvtdivsp, void, env, i32)
DEF_HELPER_2(xvtsqrtsp, void, env, i32)
-DEF_HELPER_2(xvmaddasp, void, env, i32)
-DEF_HELPER_2(xvmaddmsp, void, env, i32)
-DEF_HELPER_2(xvmsubasp, void, env, i32)
-DEF_HELPER_2(xvmsubmsp, void, env, i32)
-DEF_HELPER_2(xvnmaddasp, void, env, i32)
-DEF_HELPER_2(xvnmaddmsp, void, env, i32)
-DEF_HELPER_2(xvnmsubasp, void, env, i32)
-DEF_HELPER_2(xvnmsubmsp, void, env, i32)
-DEF_HELPER_2(xvmaxsp, void, env, i32)
-DEF_HELPER_2(xvminsp, void, env, i32)
+DEF_HELPER_4(xvmaddasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmaddmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmsubasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmsubmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmaddasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmaddmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmsubasp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvnmsubmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvmaxsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xvminsp, void, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgtsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
@@ -532,8 +532,8 @@ DEF_HELPER_2(xvrspic, void, env, i32)
DEF_HELPER_2(xvrspim, void, env, i32)
DEF_HELPER_2(xvrspip, void, env, i32)
DEF_HELPER_2(xvrspiz, void, env, i32)
-DEF_HELPER_2(xxperm, void, env, i32)
-DEF_HELPER_2(xxpermr, void, env, i32)
+DEF_HELPER_4(xxperm, void, env, vsr, vsr, vsr)
+DEF_HELPER_4(xxpermr, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xxextractuw, void, env, tl, tl, i32)
DEF_HELPER_4(xxinsertw, void, env, tl, tl, i32)
DEF_HELPER_2(xvxsigsp, void, env, i32)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 900ba07d40..b24be00ccf 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1012,6 +1012,23 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_i32(opc); \
}
+#define GEN_VSX_HELPER_X3(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_ptr xt, xa, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ xa = gen_vsr_ptr(xA(ctx->opcode)); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
+ gen_helper_##name(cpu_env, xt, xa, xb); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1030,38 +1047,38 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_i64(t1); \
}
-GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsaddqp, 0x04, 0x00, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsmulqp, 0x04, 0x01, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmaddmdp, 0x04, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmsubadp, 0x04, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmsubmdp, 0x04, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsnmaddadp, 0x04, 0x14, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsnmaddmdp, 0x04, 0x15, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmaddmdp, 0x04, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmsubadp, 0x04, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmsubmdp, 0x04, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsnmaddadp, 0x04, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsnmaddmdp, 0x04, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsmincdp, 0x00, 0x11, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
@@ -1098,46 +1115,46 @@ GEN_VSX_HELPER_2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
GEN_VSX_HELPER_2(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsresp, 0x14, 0x01, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsmaddasp, 0x04, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsmaddmsp, 0x04, 0x01, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsmsubasp, 0x04, 0x02, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsmsubmsp, 0x04, 0x03, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsnmaddasp, 0x04, 0x10, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsnmaddmsp, 0x04, 0x11, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsmaddasp, 0x04, 0x00, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsmaddmsp, 0x04, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsmsubasp, 0x04, 0x02, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsmsubmsp, 0x04, 0x03, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsnmaddasp, 0x04, 0x10, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsnmaddmsp, 0x04, 0x11, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X3(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcdp, 0x14, 0x16, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcqp, 0x04, 0x16, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaddmdp, 0x04, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmsubadp, 0x04, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmsubmdp, 0x04, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmaddadp, 0x04, 0x1C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmaddmdp, 0x04, 0x1D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaddmdp, 0x04, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmsubadp, 0x04, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmsubmdp, 0x04, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmaddadp, 0x04, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmaddmdp, 0x04, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
@@ -1153,25 +1170,25 @@ GEN_VSX_HELPER_2(xvrdpim, 0x12, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvrdpip, 0x12, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvrdpiz, 0x12, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaddmsp, 0x04, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmsubasp, 0x04, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmsubmsp, 0x04, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmaddasp, 0x04, 0x18, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmaddmsp, 0x04, 0x19, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaddmsp, 0x04, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmsubasp, 0x04, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmsubmsp, 0x04, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmaddasp, 0x04, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmaddmsp, 0x04, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_X3(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300)
GEN_VSX_HELPER_2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300)
@@ -1190,8 +1207,8 @@ GEN_VSX_HELPER_2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtstdcsp, 0x14, 0x1A, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xxperm, 0x08, 0x03, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xxpermr, 0x08, 0x07, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xxperm, 0x08, 0x03, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X3(xxpermr, 0x08, 0x07, 0, PPC2_ISA300)
static void gen_xxbrd(DisasContext *ctx)
{
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 06/15] target/ppc: introduce separate generator and helper for xscvqpdp
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (4 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 05/15] target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 07/15] target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c Mark Cave-Ayland
` (11 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new generator and helper function which perform the decode based
upon xT and xB at translation time.
The xscvqpdp helper is the only 2 parameter xT/xB implementation that requires
the opcode to be passed as an additional parameter, so handling this separately
allows us to optimise the conversion in the next commit.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 5 ++---
target/ppc/helper.h | 2 +-
target/ppc/translate/vsx-impl.inc.c | 18 +++++++++++++++++-
3 files changed, 20 insertions(+), 5 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 012dfdac3e..230ee2f072 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2899,10 +2899,9 @@ VSX_CVT_FP_TO_FP_HP(xvcvhpsp, 4, float16, float32, VsrH(2 * i + 1), VsrW(i), 0)
* xscvqpdp isn't using VSX_CVT_FP_TO_FP() because xscvqpdpo will be
* added to this later.
*/
-void helper_xscvqpdp(CPUPPCState *env, uint32_t opcode)
+void helper_xscvqpdp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[xT(opcode)];
- ppc_vsr_t *xb = &env->vsr[xB(opcode)];
ppc_vsr_t t = { };
float_status tstat;
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index f6a97cedc6..5d15166988 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -405,7 +405,7 @@ DEF_HELPER_2(xscvdphp, void, env, i32)
DEF_HELPER_2(xscvdpqp, void, env, i32)
DEF_HELPER_2(xscvdpsp, void, env, i32)
DEF_HELPER_2(xscvdpspn, i64, env, i64)
-DEF_HELPER_2(xscvqpdp, void, env, i32)
+DEF_HELPER_4(xscvqpdp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xscvqpsdz, void, env, i32)
DEF_HELPER_2(xscvqpswz, void, env, i32)
DEF_HELPER_2(xscvqpudz, void, env, i32)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index b24be00ccf..ffbe3b0fac 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -999,6 +999,23 @@ VSX_CMP(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX)
VSX_CMP(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX)
VSX_CMP(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX)
+static void gen_xscvqpdp(DisasContext *ctx)
+{
+ TCGv_i32 opc;
+ TCGv_ptr xt, xb;
+ if (unlikely(!ctx->vsx_enabled)) {
+ gen_exception(ctx, POWERPC_EXCP_VSXU);
+ return;
+ }
+ opc = tcg_const_i32(ctx->opcode);
+ xt = gen_vsr_ptr(xT(ctx->opcode));
+ xb = gen_vsr_ptr(xB(ctx->opcode));
+ gen_helper_xscvqpdp(cpu_env, opc, xt, xb);
+ tcg_temp_free_i32(opc);
+ tcg_temp_free_ptr(xt);
+ tcg_temp_free_ptr(xb);
+}
+
#define GEN_VSX_HELPER_2(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1087,7 +1104,6 @@ GEN_VSX_HELPER_2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
GEN_VSX_HELPER_XT_XB_ENV(xscvdpspn, 0x16, 0x10, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xscvqpdp, 0x04, 0x1A, 0x14, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpudz, 0x04, 0x1A, 0x11, PPC2_ISA300)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 07/15] target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (5 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 06/15] target/ppc: introduce separate generator and helper for xscvqpdp Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 08/15] target/ppc: introduce GEN_VSX_HELPER_X2_AB " Mark Cave-Ayland
` (10 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_X2 macro which performs the decode based
upon xT and xB at translation time.
With the previous change to the xscvqpdp generator and helper functions the
opcode parameter is no longer required in the common case and can be
removed.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 36 +++-------
target/ppc/helper.h | 120 ++++++++++++++++----------------
target/ppc/translate/vsx-impl.inc.c | 135 ++++++++++++++++++++----------------
3 files changed, 144 insertions(+), 147 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 230ee2f072..44dff1b459 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2040,10 +2040,8 @@ void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
* sfprf - set FPRF
*/
#define VSX_RE(op, nels, tp, fld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2082,10 +2080,8 @@ VSX_RE(xvresp, 4, float32, VsrW(i), 0, 0)
* sfprf - set FPRF
*/
#define VSX_SQRT(op, nels, tp, fld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2132,10 +2128,8 @@ VSX_SQRT(xvsqrtsp, 4, float32, VsrW(i), 0, 0)
* sfprf - set FPRF
*/
#define VSX_RSQRTE(op, nels, tp, fld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2791,10 +2785,8 @@ VSX_CMP(xvcmpnesp, 4, float32, VsrW(i), eq, 0, 0)
* sfprf - set FPRF
*/
#define VSX_CVT_FP_TO_FP(op, nels, stp, ttp, sfld, tfld, sfprf) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2867,10 +2859,8 @@ VSX_CVT_FP_TO_FP_VECTOR(xscvdpqp, 1, float64, float128, VsrD(0), f128, 1)
* sfprf - set FPRF
*/
#define VSX_CVT_FP_TO_FP_HP(op, nels, stp, ttp, sfld, tfld, sfprf) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = { }; \
int i; \
\
@@ -2949,11 +2939,9 @@ uint64_t helper_xscvspdpn(CPUPPCState *env, uint64_t xb)
* rnan - resulting NaN
*/
#define VSX_CVT_FP_TO_INT(op, nels, stp, ttp, sfld, tfld, rnan) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
int all_flags = env->fp_status.float_exception_flags, flags; \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -3037,10 +3025,8 @@ VSX_CVT_FP_TO_INT_VECTOR(xscvqpuwz, float128, uint32, f128, VsrD(0), 0x0ULL)
* sfprf - set FPRF
*/
#define VSX_CVT_INT_TO_FP(op, nels, stp, ttp, sfld, tfld, sfprf, r2sp) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -3113,10 +3099,8 @@ VSX_CVT_INT_TO_FP_VECTOR(xscvudqp, uint64, float128, VsrD(0), f128)
* sfprf - set FPRF
*/
#define VSX_ROUND(op, nels, tp, fld, rmode, sfprf) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xT(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -3201,10 +3185,8 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
VSX_XXPERM(xxperm, 0)
VSX_XXPERM(xxpermr, 1)
-void helper_xvxsigsp(CPUPPCState *env, uint32_t opcode)
+void helper_xvxsigsp(CPUPPCState *env, ppc_vsr_t *xt, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[xT(opcode)];
- ppc_vsr_t *xb = &env->vsr[xB(opcode)];
ppc_vsr_t t = { };
uint32_t exp, i, fraction;
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 5d15166988..f56476ec41 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -372,9 +372,9 @@ DEF_HELPER_4(xsmuldp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsmulqp, void, env, i32)
DEF_HELPER_4(xsdivdp, void, env, vsr, vsr, vsr)
DEF_HELPER_2(xsdivqp, void, env, i32)
-DEF_HELPER_2(xsredp, void, env, i32)
-DEF_HELPER_2(xssqrtdp, void, env, i32)
-DEF_HELPER_2(xsrsqrtedp, void, env, i32)
+DEF_HELPER_3(xsredp, void, env, vsr, vsr)
+DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
+DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_2(xstdivdp, void, env, i32)
DEF_HELPER_2(xstsqrtdp, void, env, i32)
DEF_HELPER_4(xsmaddadp, void, env, vsr, vsr, vsr)
@@ -401,36 +401,36 @@ DEF_HELPER_2(xsmaxcdp, void, env, i32)
DEF_HELPER_2(xsmincdp, void, env, i32)
DEF_HELPER_2(xsmaxjdp, void, env, i32)
DEF_HELPER_2(xsminjdp, void, env, i32)
-DEF_HELPER_2(xscvdphp, void, env, i32)
+DEF_HELPER_3(xscvdphp, void, env, vsr, vsr)
DEF_HELPER_2(xscvdpqp, void, env, i32)
-DEF_HELPER_2(xscvdpsp, void, env, i32)
+DEF_HELPER_3(xscvdpsp, void, env, vsr, vsr)
DEF_HELPER_2(xscvdpspn, i64, env, i64)
DEF_HELPER_4(xscvqpdp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xscvqpsdz, void, env, i32)
DEF_HELPER_2(xscvqpswz, void, env, i32)
DEF_HELPER_2(xscvqpudz, void, env, i32)
DEF_HELPER_2(xscvqpuwz, void, env, i32)
-DEF_HELPER_2(xscvhpdp, void, env, i32)
+DEF_HELPER_3(xscvhpdp, void, env, vsr, vsr)
DEF_HELPER_2(xscvsdqp, void, env, i32)
-DEF_HELPER_2(xscvspdp, void, env, i32)
+DEF_HELPER_3(xscvspdp, void, env, vsr, vsr)
DEF_HELPER_2(xscvspdpn, i64, env, i64)
-DEF_HELPER_2(xscvdpsxds, void, env, i32)
-DEF_HELPER_2(xscvdpsxws, void, env, i32)
-DEF_HELPER_2(xscvdpuxds, void, env, i32)
-DEF_HELPER_2(xscvdpuxws, void, env, i32)
-DEF_HELPER_2(xscvsxddp, void, env, i32)
-DEF_HELPER_2(xscvuxdsp, void, env, i32)
-DEF_HELPER_2(xscvsxdsp, void, env, i32)
+DEF_HELPER_3(xscvdpsxds, void, env, vsr, vsr)
+DEF_HELPER_3(xscvdpsxws, void, env, vsr, vsr)
+DEF_HELPER_3(xscvdpuxds, void, env, vsr, vsr)
+DEF_HELPER_3(xscvdpuxws, void, env, vsr, vsr)
+DEF_HELPER_3(xscvsxddp, void, env, vsr, vsr)
+DEF_HELPER_3(xscvuxdsp, void, env, vsr, vsr)
+DEF_HELPER_3(xscvsxdsp, void, env, vsr, vsr)
DEF_HELPER_2(xscvudqp, void, env, i32)
-DEF_HELPER_2(xscvuxddp, void, env, i32)
+DEF_HELPER_3(xscvuxddp, void, env, vsr, vsr)
DEF_HELPER_2(xststdcsp, void, env, i32)
DEF_HELPER_2(xststdcdp, void, env, i32)
DEF_HELPER_2(xststdcqp, void, env, i32)
-DEF_HELPER_2(xsrdpi, void, env, i32)
-DEF_HELPER_2(xsrdpic, void, env, i32)
-DEF_HELPER_2(xsrdpim, void, env, i32)
-DEF_HELPER_2(xsrdpip, void, env, i32)
-DEF_HELPER_2(xsrdpiz, void, env, i32)
+DEF_HELPER_3(xsrdpi, void, env, vsr, vsr)
+DEF_HELPER_3(xsrdpic, void, env, vsr, vsr)
+DEF_HELPER_3(xsrdpim, void, env, vsr, vsr)
+DEF_HELPER_3(xsrdpip, void, env, vsr, vsr)
+DEF_HELPER_3(xsrdpiz, void, env, vsr, vsr)
DEF_HELPER_2(xsrqpi, void, env, i32)
DEF_HELPER_2(xsrqpxp, void, env, i32)
DEF_HELPER_2(xssqrtqp, void, env, i32)
@@ -440,10 +440,10 @@ DEF_HELPER_4(xsaddsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xssubsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmulsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsdivsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xsresp, void, env, i32)
+DEF_HELPER_3(xsresp, void, env, vsr, vsr)
DEF_HELPER_2(xsrsp, i64, env, i64)
-DEF_HELPER_2(xssqrtsp, void, env, i32)
-DEF_HELPER_2(xsrsqrtesp, void, env, i32)
+DEF_HELPER_3(xssqrtsp, void, env, vsr, vsr)
+DEF_HELPER_3(xsrsqrtesp, void, env, vsr, vsr)
DEF_HELPER_4(xsmaddasp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmaddmsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmsubasp, void, env, vsr, vsr, vsr)
@@ -457,9 +457,9 @@ DEF_HELPER_4(xvadddp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvsubdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmuldp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvdivdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xvredp, void, env, i32)
-DEF_HELPER_2(xvsqrtdp, void, env, i32)
-DEF_HELPER_2(xvrsqrtedp, void, env, i32)
+DEF_HELPER_3(xvredp, void, env, vsr, vsr)
+DEF_HELPER_3(xvsqrtdp, void, env, vsr, vsr)
+DEF_HELPER_3(xvrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_2(xvtdivdp, void, env, i32)
DEF_HELPER_2(xvtsqrtdp, void, env, i32)
DEF_HELPER_4(xvmaddadp, void, env, vsr, vsr, vsr)
@@ -476,28 +476,28 @@ DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgtdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpnedp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_2(xvcvdpsp, void, env, i32)
-DEF_HELPER_2(xvcvdpsxds, void, env, i32)
-DEF_HELPER_2(xvcvdpsxws, void, env, i32)
-DEF_HELPER_2(xvcvdpuxds, void, env, i32)
-DEF_HELPER_2(xvcvdpuxws, void, env, i32)
-DEF_HELPER_2(xvcvsxddp, void, env, i32)
-DEF_HELPER_2(xvcvuxddp, void, env, i32)
-DEF_HELPER_2(xvcvsxwdp, void, env, i32)
-DEF_HELPER_2(xvcvuxwdp, void, env, i32)
-DEF_HELPER_2(xvrdpi, void, env, i32)
-DEF_HELPER_2(xvrdpic, void, env, i32)
-DEF_HELPER_2(xvrdpim, void, env, i32)
-DEF_HELPER_2(xvrdpip, void, env, i32)
-DEF_HELPER_2(xvrdpiz, void, env, i32)
+DEF_HELPER_3(xvcvdpsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvdpsxds, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvdpsxws, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvdpuxds, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvdpuxws, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvsxddp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvuxddp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvsxwdp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvuxwdp, void, env, vsr, vsr)
+DEF_HELPER_3(xvrdpi, void, env, vsr, vsr)
+DEF_HELPER_3(xvrdpic, void, env, vsr, vsr)
+DEF_HELPER_3(xvrdpim, void, env, vsr, vsr)
+DEF_HELPER_3(xvrdpip, void, env, vsr, vsr)
+DEF_HELPER_3(xvrdpiz, void, env, vsr, vsr)
DEF_HELPER_4(xvaddsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvsubsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmulsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvdivsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xvresp, void, env, i32)
-DEF_HELPER_2(xvsqrtsp, void, env, i32)
-DEF_HELPER_2(xvrsqrtesp, void, env, i32)
+DEF_HELPER_3(xvresp, void, env, vsr, vsr)
+DEF_HELPER_3(xvsqrtsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvrsqrtesp, void, env, vsr, vsr)
DEF_HELPER_2(xvtdivsp, void, env, i32)
DEF_HELPER_2(xvtsqrtsp, void, env, i32)
DEF_HELPER_4(xvmaddasp, void, env, vsr, vsr, vsr)
@@ -514,29 +514,29 @@ DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpgtsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpnesp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
-DEF_HELPER_2(xvcvspdp, void, env, i32)
-DEF_HELPER_2(xvcvsphp, void, env, i32)
-DEF_HELPER_2(xvcvhpsp, void, env, i32)
-DEF_HELPER_2(xvcvspsxds, void, env, i32)
-DEF_HELPER_2(xvcvspsxws, void, env, i32)
-DEF_HELPER_2(xvcvspuxds, void, env, i32)
-DEF_HELPER_2(xvcvspuxws, void, env, i32)
-DEF_HELPER_2(xvcvsxdsp, void, env, i32)
-DEF_HELPER_2(xvcvuxdsp, void, env, i32)
-DEF_HELPER_2(xvcvsxwsp, void, env, i32)
-DEF_HELPER_2(xvcvuxwsp, void, env, i32)
+DEF_HELPER_3(xvcvspdp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvsphp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvhpsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvspsxds, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvspsxws, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvspuxds, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvspuxws, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvsxdsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvuxdsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvsxwsp, void, env, vsr, vsr)
+DEF_HELPER_3(xvcvuxwsp, void, env, vsr, vsr)
DEF_HELPER_2(xvtstdcsp, void, env, i32)
DEF_HELPER_2(xvtstdcdp, void, env, i32)
-DEF_HELPER_2(xvrspi, void, env, i32)
-DEF_HELPER_2(xvrspic, void, env, i32)
-DEF_HELPER_2(xvrspim, void, env, i32)
-DEF_HELPER_2(xvrspip, void, env, i32)
-DEF_HELPER_2(xvrspiz, void, env, i32)
+DEF_HELPER_3(xvrspi, void, env, vsr, vsr)
+DEF_HELPER_3(xvrspic, void, env, vsr, vsr)
+DEF_HELPER_3(xvrspim, void, env, vsr, vsr)
+DEF_HELPER_3(xvrspip, void, env, vsr, vsr)
+DEF_HELPER_3(xvrspiz, void, env, vsr, vsr)
DEF_HELPER_4(xxperm, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xxpermr, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xxextractuw, void, env, tl, tl, i32)
DEF_HELPER_4(xxinsertw, void, env, tl, tl, i32)
-DEF_HELPER_2(xvxsigsp, void, env, i32)
+DEF_HELPER_3(xvxsigsp, void, env, vsr, vsr)
DEF_HELPER_2(efscfsi, i32, env, i32)
DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index ffbe3b0fac..36fb740f6a 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1046,6 +1046,21 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_X2(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_ptr xt, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
+ gen_helper_##name(cpu_env, xt, xb); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1071,9 +1086,9 @@ GEN_VSX_HELPER_X3(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsmulqp, 0x04, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
@@ -1100,30 +1115,30 @@ GEN_VSX_HELPER_2(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsmincdp, 0x00, 0x11, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsminjdp, 0x00, 0x12, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
+GEN_VSX_HELPER_X2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
GEN_VSX_HELPER_XT_XB_ENV(xscvdpspn, 0x16, 0x10, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpudz, 0x04, 0x1A, 0x11, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvqpuwz, 0x04, 0x1A, 0x01, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300)
+GEN_VSX_HELPER_X2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300)
GEN_VSX_HELPER_2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_XT_XB_ENV(xscvspdpn, 0x16, 0x14, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xscvdpsxds, 0x10, 0x15, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvdpsxws, 0x10, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvdpsxds, 0x10, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvdpsxws, 0x10, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscvudqp, 0x04, 0x1A, 0x02, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrdpi, 0x12, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrdpic, 0x16, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrdpim, 0x12, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrdpi, 0x12, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrdpic, 0x16, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrdpim, 0x12, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_XT_XB_ENV(xsrsp, 0x12, 0x11, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
@@ -1135,9 +1150,9 @@ GEN_VSX_HELPER_X3(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsresp, 0x14, 0x01, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X2(xsresp, 0x14, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X2(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsmaddasp, 0x04, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsmaddmsp, 0x04, 0x01, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsmsubasp, 0x04, 0x02, 0, PPC2_VSX207)
@@ -1146,8 +1161,8 @@ GEN_VSX_HELPER_X3(xsnmaddasp, 0x04, 0x10, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsnmaddmsp, 0x04, 0x11, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
+GEN_VSX_HELPER_X2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcdp, 0x14, 0x16, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcqp, 0x04, 0x16, 0, PPC2_ISA300)
@@ -1156,9 +1171,9 @@ GEN_VSX_HELPER_X3(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
@@ -1171,28 +1186,28 @@ GEN_VSX_HELPER_X3(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvdpuxds, 0x10, 0x1C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvdpuxws, 0x10, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvsxddp, 0x10, 0x1F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvuxddp, 0x10, 0x1E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvsxwdp, 0x10, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvuxwdp, 0x10, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrdpi, 0x12, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrdpic, 0x16, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrdpim, 0x12, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrdpip, 0x12, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrdpiz, 0x12, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvdpsxds, 0x10, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvdpsxws, 0x10, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvdpuxds, 0x10, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvdpuxws, 0x10, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvsxddp, 0x10, 0x1F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvuxddp, 0x10, 0x1E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvsxwdp, 0x10, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvuxwdp, 0x10, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrdpi, 0x12, 0x0C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrdpic, 0x16, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrdpim, 0x12, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrdpip, 0x12, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrdpiz, 0x12, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
@@ -1205,22 +1220,22 @@ GEN_VSX_HELPER_X3(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300)
-GEN_VSX_HELPER_2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300)
-GEN_VSX_HELPER_2(xvcvspsxds, 0x10, 0x19, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvspsxws, 0x10, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvspuxds, 0x10, 0x18, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvspuxws, 0x10, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvsxdsp, 0x10, 0x1B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvuxdsp, 0x10, 0x1A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvsxwsp, 0x10, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvcvuxwsp, 0x10, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrspi, 0x12, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrspic, 0x16, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrspim, 0x12, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300)
+GEN_VSX_HELPER_X2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300)
+GEN_VSX_HELPER_X2(xvcvspsxds, 0x10, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvspsxws, 0x10, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvspuxds, 0x10, 0x18, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvspuxws, 0x10, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvsxdsp, 0x10, 0x1B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvuxdsp, 0x10, 0x1A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvsxwsp, 0x10, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvcvuxwsp, 0x10, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrspi, 0x12, 0x08, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrspic, 0x16, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrspim, 0x12, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtstdcsp, 0x14, 0x1A, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xxperm, 0x08, 0x03, 0, PPC2_ISA300)
@@ -1879,7 +1894,7 @@ static void gen_xvxexpdp(DisasContext *ctx)
tcg_temp_free_i64(xbl);
}
-GEN_VSX_HELPER_2(xvxsigsp, 0x00, 0x04, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X2(xvxsigsp, 0x00, 0x04, 0, PPC2_ISA300)
static void gen_xvxsigdp(DisasContext *ctx)
{
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 08/15] target/ppc: introduce GEN_VSX_HELPER_X2_AB macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (6 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 07/15] target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 09/15] target/ppc: introduce GEN_VSX_HELPER_X1 " Mark Cave-Ayland
` (9 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_X2_AB macro which performs the decode based
upon xA and xB at translation time.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 15 ++++++---------
target/ppc/helper.h | 12 ++++++------
target/ppc/translate/vsx-impl.inc.c | 30 ++++++++++++++++++++++++------
3 files changed, 36 insertions(+), 21 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 44dff1b459..902d63b139 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2179,10 +2179,9 @@ VSX_RSQRTE(xvrsqrtesp, 4, float32, VsrW(i), 0, 0)
* nbits - number of fraction bits
*/
#define VSX_TDIV(op, nels, tp, fld, emin, emax, nbits) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
int i; \
int fe_flag = 0; \
int fg_flag = 0; \
@@ -2431,10 +2430,9 @@ VSX_SCALAR_CMP_DP(xscmpgedp, le, 1, 1)
VSX_SCALAR_CMP_DP(xscmpgtdp, lt, 1, 1)
VSX_SCALAR_CMP_DP(xscmpnedp, eq, 0, 0)
-void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode)
+void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xa = &env->vsr[xA(opcode)];
- ppc_vsr_t *xb = &env->vsr[xB(opcode)];
int64_t exp_a, exp_b;
uint32_t cc;
@@ -2492,10 +2490,9 @@ void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode)
}
#define VSX_SCALAR_CMP(op, ordered) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xa = &env->vsr[xA(opcode)]; \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
uint32_t cc = 0; \
bool vxsnan_flag = false, vxvc_flag = false; \
\
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index f56476ec41..0ab1ef2aee 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -375,7 +375,7 @@ DEF_HELPER_2(xsdivqp, void, env, i32)
DEF_HELPER_3(xsredp, void, env, vsr, vsr)
DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
-DEF_HELPER_2(xstdivdp, void, env, i32)
+DEF_HELPER_4(xstdivdp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xstsqrtdp, void, env, i32)
DEF_HELPER_4(xsmaddadp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmaddmdp, void, env, vsr, vsr, vsr)
@@ -389,10 +389,10 @@ DEF_HELPER_4(xscmpeqdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpnedp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xscmpexpdp, void, env, i32)
+DEF_HELPER_4(xscmpexpdp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xscmpexpqp, void, env, i32)
-DEF_HELPER_2(xscmpodp, void, env, i32)
-DEF_HELPER_2(xscmpudp, void, env, i32)
+DEF_HELPER_4(xscmpodp, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xscmpudp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xscmpoqp, void, env, i32)
DEF_HELPER_2(xscmpuqp, void, env, i32)
DEF_HELPER_4(xsmaxdp, void, env, vsr, vsr, vsr)
@@ -460,7 +460,7 @@ DEF_HELPER_4(xvdivdp, void, env, vsr, vsr, vsr)
DEF_HELPER_3(xvredp, void, env, vsr, vsr)
DEF_HELPER_3(xvsqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtedp, void, env, vsr, vsr)
-DEF_HELPER_2(xvtdivdp, void, env, i32)
+DEF_HELPER_4(xvtdivdp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xvtsqrtdp, void, env, i32)
DEF_HELPER_4(xvmaddadp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmaddmdp, void, env, vsr, vsr, vsr)
@@ -498,7 +498,7 @@ DEF_HELPER_4(xvdivsp, void, env, vsr, vsr, vsr)
DEF_HELPER_3(xvresp, void, env, vsr, vsr)
DEF_HELPER_3(xvsqrtsp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtesp, void, env, vsr, vsr)
-DEF_HELPER_2(xvtdivsp, void, env, i32)
+DEF_HELPER_4(xvtdivsp, void, env, i32, vsr, vsr)
DEF_HELPER_2(xvtsqrtsp, void, env, i32)
DEF_HELPER_4(xvmaddasp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmaddmsp, void, env, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 36fb740f6a..9b4603ac33 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1061,6 +1061,24 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_X2_AB(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 opc; \
+ TCGv_ptr xa, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ opc = tcg_const_i32(ctx->opcode); \
+ xa = gen_vsr_ptr(xA(ctx->opcode)); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
+ gen_helper_##name(cpu_env, opc, xa, xb); \
+ tcg_temp_free_i32(opc); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1089,7 +1107,7 @@ GEN_VSX_HELPER_2(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2_AB(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaddmdp, 0x04, 0x05, 0, PPC2_VSX)
@@ -1103,10 +1121,10 @@ GEN_VSX_HELPER_X3(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X2_AB(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2_AB(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2_AB(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
@@ -1174,7 +1192,7 @@ GEN_VSX_HELPER_X3(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2_AB(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddmdp, 0x04, 0x0D, 0, PPC2_VSX)
@@ -1208,7 +1226,7 @@ GEN_VSX_HELPER_X3(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_X2_AB(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddmsp, 0x04, 0x09, 0, PPC2_VSX)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 09/15] target/ppc: introduce GEN_VSX_HELPER_X1 macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (7 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 08/15] target/ppc: introduce GEN_VSX_HELPER_X2_AB " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 10/15] target/ppc: introduce GEN_VSX_HELPER_R3 " Mark Cave-Ayland
` (8 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_X1 macro which performs the decode based
upon xB at translation time.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 6 ++----
target/ppc/helper.h | 8 ++++----
target/ppc/translate/vsx-impl.inc.c | 24 ++++++++++++++++++++----
3 files changed, 26 insertions(+), 12 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 902d63b139..5fb43b619e 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2236,9 +2236,8 @@ VSX_TDIV(xvtdivsp, 4, float32, VsrW(i), -126, 127, 23)
* nbits - number of fraction bits
*/
#define VSX_TSQRT(op, nels, tp, fld, emin, nbits) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xb = &env->vsr[xB(opcode)]; \
int i; \
int fe_flag = 0; \
int fg_flag = 0; \
@@ -3258,9 +3257,8 @@ VSX_TEST_DC(xvtstdcsp, 4, xB(opcode), float32, VsrW(i), VsrW(i), UINT32_MAX, 0)
VSX_TEST_DC(xststdcdp, 1, xB(opcode), float64, VsrD(0), VsrD(0), 0, 1)
VSX_TEST_DC(xststdcqp, 1, (rB(opcode) + 32), float128, f128, VsrD(0), 0, 1)
-void helper_xststdcsp(CPUPPCState *env, uint32_t opcode)
+void helper_xststdcsp(CPUPPCState *env, uint32_t opcode, ppc_vsr_t *xb)
{
- ppc_vsr_t *xb = &env->vsr[xB(opcode)];
uint32_t dcmx, sign, exp;
uint32_t cc, match = 0, not_sp = 0;
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 0ab1ef2aee..a8886c56ad 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -376,7 +376,7 @@ DEF_HELPER_3(xsredp, void, env, vsr, vsr)
DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_4(xstdivdp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xstsqrtdp, void, env, i32)
+DEF_HELPER_3(xstsqrtdp, void, env, i32, vsr)
DEF_HELPER_4(xsmaddadp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmaddmdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmsubadp, void, env, vsr, vsr, vsr)
@@ -423,7 +423,7 @@ DEF_HELPER_3(xscvuxdsp, void, env, vsr, vsr)
DEF_HELPER_3(xscvsxdsp, void, env, vsr, vsr)
DEF_HELPER_2(xscvudqp, void, env, i32)
DEF_HELPER_3(xscvuxddp, void, env, vsr, vsr)
-DEF_HELPER_2(xststdcsp, void, env, i32)
+DEF_HELPER_3(xststdcsp, void, env, i32, vsr)
DEF_HELPER_2(xststdcdp, void, env, i32)
DEF_HELPER_2(xststdcqp, void, env, i32)
DEF_HELPER_3(xsrdpi, void, env, vsr, vsr)
@@ -461,7 +461,7 @@ DEF_HELPER_3(xvredp, void, env, vsr, vsr)
DEF_HELPER_3(xvsqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_4(xvtdivdp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xvtsqrtdp, void, env, i32)
+DEF_HELPER_3(xvtsqrtdp, void, env, i32, vsr)
DEF_HELPER_4(xvmaddadp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmaddmdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmsubadp, void, env, vsr, vsr, vsr)
@@ -499,7 +499,7 @@ DEF_HELPER_3(xvresp, void, env, vsr, vsr)
DEF_HELPER_3(xvsqrtsp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtesp, void, env, vsr, vsr)
DEF_HELPER_4(xvtdivsp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xvtsqrtsp, void, env, i32)
+DEF_HELPER_3(xvtsqrtsp, void, env, i32, vsr)
DEF_HELPER_4(xvmaddasp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmaddmsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmsubasp, void, env, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 9b4603ac33..8af093d256 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1079,6 +1079,22 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_X1(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 opc; \
+ TCGv_ptr xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ opc = tcg_const_i32(ctx->opcode); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
+ gen_helper_##name(cpu_env, opc, xb); \
+ tcg_temp_free_i32(opc); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1108,7 +1124,7 @@ GEN_VSX_HELPER_X2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
+GEN_VSX_HELPER_X1(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaddmdp, 0x04, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmsubadp, 0x04, 0x06, 0, PPC2_VSX)
@@ -1181,7 +1197,7 @@ GEN_VSX_HELPER_X3(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
+GEN_VSX_HELPER_X1(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcdp, 0x14, 0x16, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xststdcqp, 0x04, 0x16, 0, PPC2_ISA300)
@@ -1193,7 +1209,7 @@ GEN_VSX_HELPER_X2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
+GEN_VSX_HELPER_X1(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddmdp, 0x04, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmsubadp, 0x04, 0x0E, 0, PPC2_VSX)
@@ -1227,7 +1243,7 @@ GEN_VSX_HELPER_X2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
+GEN_VSX_HELPER_X1(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaddmsp, 0x04, 0x09, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmsubasp, 0x04, 0x0A, 0, PPC2_VSX)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 10/15] target/ppc: introduce GEN_VSX_HELPER_R3 macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (8 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 09/15] target/ppc: introduce GEN_VSX_HELPER_X1 " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 11/15] target/ppc: introduce GEN_VSX_HELPER_R2 " Mark Cave-Ayland
` (7 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_R3 macro which performs the decode based
upon rD, rA and rB at translation time.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 36 ++++++++++++------------------------
target/ppc/helper.h | 16 ++++++++--------
target/ppc/translate/vsx-impl.inc.c | 36 ++++++++++++++++++++++++++++--------
3 files changed, 48 insertions(+), 40 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 5fb43b619e..44970ebec9 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -1842,11 +1842,9 @@ VSX_ADD_SUB(xssubsp, sub, 1, float64, VsrD(0), 1, 1)
VSX_ADD_SUB(xvsubdp, sub, 2, float64, VsrD(i), 0, 0)
VSX_ADD_SUB(xvsubsp, sub, 4, float32, VsrW(i), 0, 0)
-void helper_xsaddqp(CPUPPCState *env, uint32_t opcode)
+void helper_xsaddqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = *xt;
float_status tstat;
@@ -1920,11 +1918,9 @@ VSX_MUL(xsmulsp, 1, float64, VsrD(0), 1, 1)
VSX_MUL(xvmuldp, 2, float64, VsrD(i), 0, 0)
VSX_MUL(xvmulsp, 4, float32, VsrW(i), 0, 0)
-void helper_xsmulqp(CPUPPCState *env, uint32_t opcode)
+void helper_xsmulqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = *xt;
float_status tstat;
@@ -1999,11 +1995,9 @@ VSX_DIV(xsdivsp, 1, float64, VsrD(0), 1, 1)
VSX_DIV(xvdivdp, 2, float64, VsrD(i), 0, 0)
VSX_DIV(xvdivsp, 4, float32, VsrW(i), 0, 0)
-void helper_xsdivqp(CPUPPCState *env, uint32_t opcode)
+void helper_xsdivqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = *xt;
float_status tstat;
@@ -2620,11 +2614,9 @@ VSX_MAX_MIN(xvmindp, minnum, 2, float64, VsrD(i))
VSX_MAX_MIN(xvminsp, minnum, 4, float32, VsrW(i))
#define VSX_MAX_MINC(name, max) \
-void helper_##name(CPUPPCState *env, uint32_t opcode) \
+void helper_##name(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vex_flag = false; \
\
@@ -2657,11 +2649,9 @@ VSX_MAX_MINC(xsmaxcdp, 1);
VSX_MAX_MINC(xsmincdp, 0);
#define VSX_MAX_MINJ(name, max) \
-void helper_##name(CPUPPCState *env, uint32_t opcode) \
+void helper_##name(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
ppc_vsr_t t = *xt; \
bool vxsnan_flag = false, vex_flag = false; \
\
@@ -3436,11 +3426,9 @@ void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode)
do_float_check_status(env, GETPC());
}
-void helper_xssubqp(CPUPPCState *env, uint32_t opcode)
+void helper_xssubqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = *xt;
float_status tstat;
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index a8886c56ad..9134da9cbb 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -366,12 +366,12 @@ DEF_HELPER_4(bcdtrunc, i32, avr, avr, avr, i32)
DEF_HELPER_4(bcdutrunc, i32, avr, avr, avr, i32)
DEF_HELPER_4(xsadddp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xsaddqp, void, env, i32)
+DEF_HELPER_5(xsaddqp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_4(xssubdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmuldp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xsmulqp, void, env, i32)
+DEF_HELPER_5(xsmulqp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_4(xsdivdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xsdivqp, void, env, i32)
+DEF_HELPER_5(xsdivqp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_3(xsredp, void, env, vsr, vsr)
DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
@@ -397,10 +397,10 @@ DEF_HELPER_2(xscmpoqp, void, env, i32)
DEF_HELPER_2(xscmpuqp, void, env, i32)
DEF_HELPER_4(xsmaxdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmindp, void, env, vsr, vsr, vsr)
-DEF_HELPER_2(xsmaxcdp, void, env, i32)
-DEF_HELPER_2(xsmincdp, void, env, i32)
-DEF_HELPER_2(xsmaxjdp, void, env, i32)
-DEF_HELPER_2(xsminjdp, void, env, i32)
+DEF_HELPER_5(xsmaxcdp, void, env, i32, vsr, vsr, vsr)
+DEF_HELPER_5(xsmincdp, void, env, i32, vsr, vsr, vsr)
+DEF_HELPER_5(xsmaxjdp, void, env, i32, vsr, vsr, vsr)
+DEF_HELPER_5(xsminjdp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_3(xscvdphp, void, env, vsr, vsr)
DEF_HELPER_2(xscvdpqp, void, env, i32)
DEF_HELPER_3(xscvdpsp, void, env, vsr, vsr)
@@ -434,7 +434,7 @@ DEF_HELPER_3(xsrdpiz, void, env, vsr, vsr)
DEF_HELPER_2(xsrqpi, void, env, i32)
DEF_HELPER_2(xsrqpxp, void, env, i32)
DEF_HELPER_2(xssqrtqp, void, env, i32)
-DEF_HELPER_2(xssubqp, void, env, i32)
+DEF_HELPER_5(xssubqp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_4(xsaddsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xssubsp, void, env, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 8af093d256..8380651a8d 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1095,6 +1095,26 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_R3(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 opc; \
+ TCGv_ptr xt, xa, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ opc = tcg_const_i32(ctx->opcode); \
+ xt = gen_vsr_ptr(rD(ctx->opcode) + 32); \
+ xa = gen_vsr_ptr(rA(ctx->opcode) + 32); \
+ xb = gen_vsr_ptr(rB(ctx->opcode) + 32); \
+ gen_helper_##name(cpu_env, opc, xt, xa, xb); \
+ tcg_temp_free_i32(opc); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1114,12 +1134,12 @@ static void gen_##name(DisasContext *ctx) \
}
GEN_VSX_HELPER_X3(xsadddp, 0x00, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsaddqp, 0x04, 0x00, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsaddqp, 0x04, 0x00, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmulqp, 0x04, 0x01, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsmulqp, 0x04, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
@@ -1145,10 +1165,10 @@ GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsmincdp, 0x00, 0x11, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsminjdp, 0x00, 0x12, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsmincdp, 0x00, 0x11, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xsminjdp, 0x00, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
@@ -1178,7 +1198,7 @@ GEN_VSX_HELPER_XT_XB_ENV(xsrsp, 0x12, 0x11, 0, PPC2_VSX207)
GEN_VSX_HELPER_2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
-GEN_VSX_HELPER_2(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R3(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 11/15] target/ppc: introduce GEN_VSX_HELPER_R2 macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (9 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 10/15] target/ppc: introduce GEN_VSX_HELPER_R3 " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 12/15] target/ppc: introduce GEN_VSX_HELPER_R2_AB " Mark Cave-Ayland
` (6 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_R2 macro which performs the decode based
upon rD and rB at translation time.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 30 ++++++++++++-----------------
target/ppc/helper.h | 20 +++++++++----------
target/ppc/translate/vsx-impl.inc.c | 38 +++++++++++++++++++++++++++----------
3 files changed, 50 insertions(+), 38 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 44970ebec9..cb593517ae 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2808,10 +2808,9 @@ VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, VsrW(2 * i), VsrD(i), 0)
* sfprf - set FPRF
*/
#define VSX_CVT_FP_TO_FP_VECTOR(op, nels, stp, ttp, sfld, tfld, sfprf) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
ppc_vsr_t t = *xt; \
int i; \
\
@@ -2975,10 +2974,9 @@ VSX_CVT_FP_TO_INT(xvcvspuxws, 4, float32, uint32, VsrW(i), VsrW(i), 0U)
* rnan - resulting NaN
*/
#define VSX_CVT_FP_TO_INT_VECTOR(op, stp, ttp, sfld, tfld, rnan) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
ppc_vsr_t t = { }; \
\
t.tfld = stp##_to_##ttp##_round_to_zero(xb->sfld, &env->fp_status); \
@@ -3052,10 +3050,9 @@ VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, VsrW(i), VsrW(i), 0, 0)
* tfld - target vsr_t field
*/
#define VSX_CVT_INT_TO_FP_VECTOR(op, stp, ttp, sfld, tfld) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xt, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
ppc_vsr_t t = *xt; \
\
t.tfld = stp##_to_##ttp(xb->sfld, &env->fp_status); \
@@ -3278,10 +3275,9 @@ void helper_xststdcsp(CPUPPCState *env, uint32_t opcode, ppc_vsr_t *xb)
env->crf[BF(opcode)] = cc;
}
-void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
+void helper_xsrqpi(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = { };
uint8_t r = Rrm(opcode);
uint8_t ex = Rc(opcode);
@@ -3336,10 +3332,9 @@ void helper_xsrqpi(CPUPPCState *env, uint32_t opcode)
*xt = t;
}
-void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode)
+void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = { };
uint8_t r = Rrm(opcode);
uint8_t rmc = RMC(opcode);
@@ -3391,10 +3386,9 @@ void helper_xsrqpxp(CPUPPCState *env, uint32_t opcode)
do_float_check_status(env, GETPC());
}
-void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode)
+void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xt, ppc_vsr_t *xb)
{
- ppc_vsr_t *xt = &env->vsr[rD(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
ppc_vsr_t t = { };
float_status tstat;
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 9134da9cbb..2e0646f5eb 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -402,16 +402,16 @@ DEF_HELPER_5(xsmincdp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_5(xsmaxjdp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_5(xsminjdp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_3(xscvdphp, void, env, vsr, vsr)
-DEF_HELPER_2(xscvdpqp, void, env, i32)
+DEF_HELPER_4(xscvdpqp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xscvdpsp, void, env, vsr, vsr)
DEF_HELPER_2(xscvdpspn, i64, env, i64)
DEF_HELPER_4(xscvqpdp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xscvqpsdz, void, env, i32)
-DEF_HELPER_2(xscvqpswz, void, env, i32)
-DEF_HELPER_2(xscvqpudz, void, env, i32)
-DEF_HELPER_2(xscvqpuwz, void, env, i32)
+DEF_HELPER_4(xscvqpsdz, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xscvqpswz, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xscvqpudz, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xscvqpuwz, void, env, i32, vsr, vsr)
DEF_HELPER_3(xscvhpdp, void, env, vsr, vsr)
-DEF_HELPER_2(xscvsdqp, void, env, i32)
+DEF_HELPER_4(xscvsdqp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xscvspdp, void, env, vsr, vsr)
DEF_HELPER_2(xscvspdpn, i64, env, i64)
DEF_HELPER_3(xscvdpsxds, void, env, vsr, vsr)
@@ -421,7 +421,7 @@ DEF_HELPER_3(xscvdpuxws, void, env, vsr, vsr)
DEF_HELPER_3(xscvsxddp, void, env, vsr, vsr)
DEF_HELPER_3(xscvuxdsp, void, env, vsr, vsr)
DEF_HELPER_3(xscvsxdsp, void, env, vsr, vsr)
-DEF_HELPER_2(xscvudqp, void, env, i32)
+DEF_HELPER_4(xscvudqp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xscvuxddp, void, env, vsr, vsr)
DEF_HELPER_3(xststdcsp, void, env, i32, vsr)
DEF_HELPER_2(xststdcdp, void, env, i32)
@@ -431,9 +431,9 @@ DEF_HELPER_3(xsrdpic, void, env, vsr, vsr)
DEF_HELPER_3(xsrdpim, void, env, vsr, vsr)
DEF_HELPER_3(xsrdpip, void, env, vsr, vsr)
DEF_HELPER_3(xsrdpiz, void, env, vsr, vsr)
-DEF_HELPER_2(xsrqpi, void, env, i32)
-DEF_HELPER_2(xsrqpxp, void, env, i32)
-DEF_HELPER_2(xssqrtqp, void, env, i32)
+DEF_HELPER_4(xsrqpi, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xsrqpxp, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xssqrtqp, void, env, i32, vsr, vsr)
DEF_HELPER_5(xssubqp, void, env, i32, vsr, vsr, vsr)
DEF_HELPER_4(xsaddsp, void, env, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 8380651a8d..05db509a0c 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1115,6 +1115,24 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_R2(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 opc; \
+ TCGv_ptr xt, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ opc = tcg_const_i32(ctx->opcode); \
+ xt = gen_vsr_ptr(rD(ctx->opcode) + 32); \
+ xb = gen_vsr_ptr(rB(ctx->opcode) + 32); \
+ gen_helper_##name(cpu_env, opc, xt, xb); \
+ tcg_temp_free_i32(opc); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1171,14 +1189,14 @@ GEN_VSX_HELPER_R3(xsmaxjdp, 0x00, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_R3(xsminjdp, 0x00, 0x12, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300)
GEN_VSX_HELPER_XT_XB_ENV(xscvdpspn, 0x16, 0x10, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvqpudz, 0x04, 0x1A, 0x11, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvqpuwz, 0x04, 0x1A, 0x01, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvqpudz, 0x04, 0x1A, 0x11, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvqpuwz, 0x04, 0x1A, 0x01, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_XT_XB_ENV(xscvspdpn, 0x16, 0x14, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xscvdpsxds, 0x10, 0x15, 0, PPC2_VSX)
@@ -1186,7 +1204,7 @@ GEN_VSX_HELPER_X2(xscvdpsxws, 0x10, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscvudqp, 0x04, 0x1A, 0x02, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xscvudqp, 0x04, 0x1A, 0x02, PPC2_ISA300)
GEN_VSX_HELPER_X2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrdpi, 0x12, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrdpic, 0x16, 0x06, 0, PPC2_VSX)
@@ -1195,9 +1213,9 @@ GEN_VSX_HELPER_X2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_XT_XB_ENV(xsrsp, 0x12, 0x11, 0, PPC2_VSX207)
-GEN_VSX_HELPER_2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
GEN_VSX_HELPER_R3(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 12/15] target/ppc: introduce GEN_VSX_HELPER_R2_AB macro to fpu_helper.c
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (10 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 11/15] target/ppc: introduce GEN_VSX_HELPER_R2 " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 13/15] target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time Mark Cave-Ayland
` (5 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Rather than perform the VSR register decoding within the helper itself,
introduce a new GEN_VSX_HELPER_R2_AB macro which performs the decode based
upon rA and rB at translation time.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 10 ++++------
target/ppc/helper.h | 6 +++---
target/ppc/translate/vsx-impl.inc.c | 24 +++++++++++++++++++++---
3 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index cb593517ae..f0a897cb9a 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2452,10 +2452,9 @@ void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode,
do_float_check_status(env, GETPC());
}
-void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode)
+void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode,
+ ppc_vsr_t *xa, ppc_vsr_t *xb)
{
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32];
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32];
int64_t exp_a, exp_b;
uint32_t cc;
@@ -2531,10 +2530,9 @@ VSX_SCALAR_CMP(xscmpodp, 1)
VSX_SCALAR_CMP(xscmpudp, 0)
#define VSX_SCALAR_CMPQ(op, ordered) \
-void helper_##op(CPUPPCState *env, uint32_t opcode) \
+void helper_##op(CPUPPCState *env, uint32_t opcode, \
+ ppc_vsr_t *xa, ppc_vsr_t *xb) \
{ \
- ppc_vsr_t *xa = &env->vsr[rA(opcode) + 32]; \
- ppc_vsr_t *xb = &env->vsr[rB(opcode) + 32]; \
uint32_t cc = 0; \
bool vxsnan_flag = false, vxvc_flag = false; \
\
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 2e0646f5eb..a5e12a3933 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -390,11 +390,11 @@ DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpnedp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpexpdp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xscmpexpqp, void, env, i32)
+DEF_HELPER_4(xscmpexpqp, void, env, i32, vsr, vsr)
DEF_HELPER_4(xscmpodp, void, env, i32, vsr, vsr)
DEF_HELPER_4(xscmpudp, void, env, i32, vsr, vsr)
-DEF_HELPER_2(xscmpoqp, void, env, i32)
-DEF_HELPER_2(xscmpuqp, void, env, i32)
+DEF_HELPER_4(xscmpoqp, void, env, i32, vsr, vsr)
+DEF_HELPER_4(xscmpuqp, void, env, i32, vsr, vsr)
DEF_HELPER_4(xsmaxdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xsmindp, void, env, vsr, vsr, vsr)
DEF_HELPER_5(xsmaxcdp, void, env, i32, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 05db509a0c..5cf053e7f2 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1133,6 +1133,24 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(xb); \
}
+#define GEN_VSX_HELPER_R2_AB(name, op1, op2, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_i32 opc; \
+ TCGv_ptr xa, xb; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ opc = tcg_const_i32(ctx->opcode); \
+ xa = gen_vsr_ptr(rA(ctx->opcode) + 32); \
+ xb = gen_vsr_ptr(rB(ctx->opcode) + 32); \
+ gen_helper_##name(cpu_env, opc, xa, xb); \
+ tcg_temp_free_i32(opc); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(xb); \
+}
+
#define GEN_VSX_HELPER_XT_XB_ENV(name, op1, op2, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1176,11 +1194,11 @@ GEN_VSX_HELPER_X3(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2_AB(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300)
-GEN_VSX_HELPER_2(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300)
+GEN_VSX_HELPER_R2_AB(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300)
GEN_VSX_HELPER_X2_AB(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
+GEN_VSX_HELPER_R2_AB(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX)
+GEN_VSX_HELPER_R2_AB(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xsmindp, 0x00, 0x15, 0, PPC2_VSX)
GEN_VSX_HELPER_R3(xsmaxcdp, 0x00, 0x10, 0, PPC2_ISA300)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 13/15] target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (11 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 12/15] target/ppc: introduce GEN_VSX_HELPER_R2_AB " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 14/15] target/ppc: decode target register in VSX_EXTRACT_INSERT " Mark Cave-Ayland
` (4 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/helper.h | 8 +++----
target/ppc/mem_helper.c | 6 ++---
target/ppc/translate/vsx-impl.inc.c | 47 +++++++++++++++++++------------------
3 files changed, 30 insertions(+), 31 deletions(-)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index a5e12a3933..7ed9effff2 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -279,10 +279,10 @@ DEF_HELPER_3(stvebx, void, env, avr, tl)
DEF_HELPER_3(stvehx, void, env, avr, tl)
DEF_HELPER_3(stvewx, void, env, avr, tl)
#if defined(TARGET_PPC64)
-DEF_HELPER_4(lxvl, void, env, tl, tl, tl)
-DEF_HELPER_4(lxvll, void, env, tl, tl, tl)
-DEF_HELPER_4(stxvl, void, env, tl, tl, tl)
-DEF_HELPER_4(stxvll, void, env, tl, tl, tl)
+DEF_HELPER_4(lxvl, void, env, tl, vsr, tl)
+DEF_HELPER_4(lxvll, void, env, tl, vsr, tl)
+DEF_HELPER_4(stxvl, void, env, tl, vsr, tl)
+DEF_HELPER_4(stxvll, void, env, tl, vsr, tl)
#endif
DEF_HELPER_4(vsumsws, void, env, avr, avr, avr)
DEF_HELPER_4(vsum2sws, void, env, avr, avr, avr)
diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 87632ccf53..6f4ffa3661 100644
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -415,9 +415,8 @@ STVE(stvewx, cpu_stl_data_ra, bswap32, u32)
#define VSX_LXVL(name, lj) \
void helper_##name(CPUPPCState *env, target_ulong addr, \
- target_ulong xt_num, target_ulong rb) \
+ ppc_vsr_t *xt, target_ulong rb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xt_num]; \
ppc_vsr_t t; \
uint64_t nb = GET_NB(rb); \
int i; \
@@ -446,9 +445,8 @@ VSX_LXVL(lxvll, 1)
#define VSX_STXVL(name, lj) \
void helper_##name(CPUPPCState *env, target_ulong addr, \
- target_ulong xt_num, target_ulong rb) \
+ ppc_vsr_t *xt, target_ulong rb) \
{ \
- ppc_vsr_t *xt = &env->vsr[xt_num]; \
target_ulong nb = GET_NB(rb); \
int i; \
\
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 5cf053e7f2..e853ee1386 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -344,29 +344,30 @@ VSX_VECTOR_STORE(stxv, st_i64, 0)
VSX_VECTOR_STORE(stxvx, st_i64, 1)
#ifdef TARGET_PPC64
-#define VSX_VECTOR_LOAD_STORE_LENGTH(name) \
-static void gen_##name(DisasContext *ctx) \
-{ \
- TCGv EA, xt; \
- \
- if (xT(ctx->opcode) < 32) { \
- if (unlikely(!ctx->vsx_enabled)) { \
- gen_exception(ctx, POWERPC_EXCP_VSXU); \
- return; \
- } \
- } else { \
- if (unlikely(!ctx->altivec_enabled)) { \
- gen_exception(ctx, POWERPC_EXCP_VPU); \
- return; \
- } \
- } \
- EA = tcg_temp_new(); \
- xt = tcg_const_tl(xT(ctx->opcode)); \
- gen_set_access_type(ctx, ACCESS_INT); \
- gen_addr_register(ctx, EA); \
- gen_helper_##name(cpu_env, EA, xt, cpu_gpr[rB(ctx->opcode)]); \
- tcg_temp_free(EA); \
- tcg_temp_free(xt); \
+#define VSX_VECTOR_LOAD_STORE_LENGTH(name) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv EA; \
+ TCGv_ptr xt; \
+ \
+ if (xT(ctx->opcode) < 32) { \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ } else { \
+ if (unlikely(!ctx->altivec_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VPU); \
+ return; \
+ } \
+ } \
+ EA = tcg_temp_new(); \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ gen_set_access_type(ctx, ACCESS_INT); \
+ gen_addr_register(ctx, EA); \
+ gen_helper_##name(cpu_env, EA, xt, cpu_gpr[rB(ctx->opcode)]); \
+ tcg_temp_free(EA); \
+ tcg_temp_free_ptr(xt); \
}
VSX_VECTOR_LOAD_STORE_LENGTH(lxvl)
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 14/15] target/ppc: decode target register in VSX_EXTRACT_INSERT at translation time
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (12 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 13/15] target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 15/15] target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro Mark Cave-Ayland
` (3 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/helper.h | 4 ++--
target/ppc/int_helper.c | 12 ++++--------
target/ppc/translate/vsx-impl.inc.c | 10 +++++-----
3 files changed, 11 insertions(+), 15 deletions(-)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 7ed9effff2..3d5150a524 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -534,8 +534,8 @@ DEF_HELPER_3(xvrspip, void, env, vsr, vsr)
DEF_HELPER_3(xvrspiz, void, env, vsr, vsr)
DEF_HELPER_4(xxperm, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xxpermr, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xxextractuw, void, env, tl, tl, i32)
-DEF_HELPER_4(xxinsertw, void, env, tl, tl, i32)
+DEF_HELPER_4(xxextractuw, void, env, vsr, vsr, i32)
+DEF_HELPER_4(xxinsertw, void, env, vsr, vsr, i32)
DEF_HELPER_3(xvxsigsp, void, env, vsr, vsr)
DEF_HELPER_2(efscfsi, i32, env, i32)
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 3b8939edcc..5c07ef3e4d 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1899,11 +1899,9 @@ VEXTRACT(uw, u32)
VEXTRACT(d, u64)
#undef VEXTRACT
-void helper_xxextractuw(CPUPPCState *env, target_ulong xtn,
- target_ulong xbn, uint32_t index)
+void helper_xxextractuw(CPUPPCState *env, ppc_vsr_t *xt,
+ ppc_vsr_t *xb, uint32_t index)
{
- ppc_vsr_t *xt = &env->vsr[xtn];
- ppc_vsr_t *xb = &env->vsr[xbn];
ppc_vsr_t t = { };
size_t es = sizeof(uint32_t);
uint32_t ext_index;
@@ -1917,11 +1915,9 @@ void helper_xxextractuw(CPUPPCState *env, target_ulong xtn,
*xt = t;
}
-void helper_xxinsertw(CPUPPCState *env, target_ulong xtn,
- target_ulong xbn, uint32_t index)
+void helper_xxinsertw(CPUPPCState *env, ppc_vsr_t *xt,
+ ppc_vsr_t *xb, uint32_t index)
{
- ppc_vsr_t *xt = &env->vsr[xtn];
- ppc_vsr_t *xb = &env->vsr[xbn];
ppc_vsr_t t = *xt;
size_t es = sizeof(uint32_t);
int ins_index, i = 0;
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index e853ee1386..7a4b7cb8f9 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1632,7 +1632,7 @@ static void gen_xxsldwi(DisasContext *ctx)
#define VSX_EXTRACT_INSERT(name) \
static void gen_##name(DisasContext *ctx) \
{ \
- TCGv xt, xb; \
+ TCGv_ptr xt, xb; \
TCGv_i32 t0; \
TCGv_i64 t1; \
uint8_t uimm = UIMM4(ctx->opcode); \
@@ -1641,8 +1641,8 @@ static void gen_##name(DisasContext *ctx) \
gen_exception(ctx, POWERPC_EXCP_VSXU); \
return; \
} \
- xt = tcg_const_tl(xT(ctx->opcode)); \
- xb = tcg_const_tl(xB(ctx->opcode)); \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ xb = gen_vsr_ptr(xB(ctx->opcode)); \
t0 = tcg_temp_new_i32(); \
t1 = tcg_temp_new_i64(); \
/* \
@@ -1657,8 +1657,8 @@ static void gen_##name(DisasContext *ctx) \
} \
tcg_gen_movi_i32(t0, uimm); \
gen_helper_##name(cpu_env, xt, xb, t0); \
- tcg_temp_free(xb); \
- tcg_temp_free(xt); \
+ tcg_temp_free_ptr(xb); \
+ tcg_temp_free_ptr(xt); \
tcg_temp_free_i32(t0); \
tcg_temp_free_i64(t1); \
}
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* [Qemu-devel] [PATCH v3 15/15] target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (13 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 14/15] target/ppc: decode target register in VSX_EXTRACT_INSERT " Mark Cave-Ayland
@ 2019-06-16 12:37 ` Mark Cave-Ayland
2019-06-16 13:18 ` [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up no-reply
` (2 subsequent siblings)
17 siblings, 0 replies; 21+ messages in thread
From: Mark Cave-Ayland @ 2019-06-16 12:37 UTC (permalink / raw)
To: qemu-devel, qemu-ppc, david, rth, gkurz
Introduce a new GEN_VSX_HELPER_VSX_MADD macro for the generator function which
enables the source and destination registers to be decoded at translation time.
This enables the determination of a or m form to be made at translation time so
that a single helper function can now be used for both variants.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
target/ppc/fpu_helper.c | 68 ++++++++++---------------------
target/ppc/helper.h | 48 ++++++++--------------
target/ppc/translate/vsx-impl.inc.c | 81 +++++++++++++++++++++----------------
target/ppc/translate/vsx-ops.inc.c | 70 +++++++++++++++++---------------
4 files changed, 122 insertions(+), 145 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index f0a897cb9a..f437c88aad 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2280,24 +2280,15 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23)
* fld - vsr_t field (VsrD(*) or VsrW(*))
* maddflgs - flags for the float*muladd routine that control the
* various forms (madd, msub, nmadd, nmsub)
- * afrm - A form (1=A, 0=M)
* sfprf - set FPRF
*/
-#define VSX_MADD(op, nels, tp, fld, maddflgs, afrm, sfprf, r2sp) \
+#define VSX_MADD(op, nels, tp, fld, maddflgs, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
- ppc_vsr_t *xa, ppc_vsr_t *xb) \
+ ppc_vsr_t *xa, ppc_vsr_t *b, ppc_vsr_t *c) \
{ \
- ppc_vsr_t t = *xt, *b, *c; \
+ ppc_vsr_t t = *xt; \
int i; \
\
- if (afrm) { /* AxB + T */ \
- b = xb; \
- c = xt; \
- } else { /* AxT + B */ \
- b = xt; \
- c = xb; \
- } \
- \
helper_reset_fpstatus(env); \
\
for (i = 0; i < nels; i++) { \
@@ -2336,41 +2327,24 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
do_float_check_status(env, GETPC()); \
}
-VSX_MADD(xsmaddadp, 1, float64, VsrD(0), MADD_FLGS, 1, 1, 0)
-VSX_MADD(xsmaddmdp, 1, float64, VsrD(0), MADD_FLGS, 0, 1, 0)
-VSX_MADD(xsmsubadp, 1, float64, VsrD(0), MSUB_FLGS, 1, 1, 0)
-VSX_MADD(xsmsubmdp, 1, float64, VsrD(0), MSUB_FLGS, 0, 1, 0)
-VSX_MADD(xsnmaddadp, 1, float64, VsrD(0), NMADD_FLGS, 1, 1, 0)
-VSX_MADD(xsnmaddmdp, 1, float64, VsrD(0), NMADD_FLGS, 0, 1, 0)
-VSX_MADD(xsnmsubadp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1, 0)
-VSX_MADD(xsnmsubmdp, 1, float64, VsrD(0), NMSUB_FLGS, 0, 1, 0)
-
-VSX_MADD(xsmaddasp, 1, float64, VsrD(0), MADD_FLGS, 1, 1, 1)
-VSX_MADD(xsmaddmsp, 1, float64, VsrD(0), MADD_FLGS, 0, 1, 1)
-VSX_MADD(xsmsubasp, 1, float64, VsrD(0), MSUB_FLGS, 1, 1, 1)
-VSX_MADD(xsmsubmsp, 1, float64, VsrD(0), MSUB_FLGS, 0, 1, 1)
-VSX_MADD(xsnmaddasp, 1, float64, VsrD(0), NMADD_FLGS, 1, 1, 1)
-VSX_MADD(xsnmaddmsp, 1, float64, VsrD(0), NMADD_FLGS, 0, 1, 1)
-VSX_MADD(xsnmsubasp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1, 1)
-VSX_MADD(xsnmsubmsp, 1, float64, VsrD(0), NMSUB_FLGS, 0, 1, 1)
-
-VSX_MADD(xvmaddadp, 2, float64, VsrD(i), MADD_FLGS, 1, 0, 0)
-VSX_MADD(xvmaddmdp, 2, float64, VsrD(i), MADD_FLGS, 0, 0, 0)
-VSX_MADD(xvmsubadp, 2, float64, VsrD(i), MSUB_FLGS, 1, 0, 0)
-VSX_MADD(xvmsubmdp, 2, float64, VsrD(i), MSUB_FLGS, 0, 0, 0)
-VSX_MADD(xvnmaddadp, 2, float64, VsrD(i), NMADD_FLGS, 1, 0, 0)
-VSX_MADD(xvnmaddmdp, 2, float64, VsrD(i), NMADD_FLGS, 0, 0, 0)
-VSX_MADD(xvnmsubadp, 2, float64, VsrD(i), NMSUB_FLGS, 1, 0, 0)
-VSX_MADD(xvnmsubmdp, 2, float64, VsrD(i), NMSUB_FLGS, 0, 0, 0)
-
-VSX_MADD(xvmaddasp, 4, float32, VsrW(i), MADD_FLGS, 1, 0, 0)
-VSX_MADD(xvmaddmsp, 4, float32, VsrW(i), MADD_FLGS, 0, 0, 0)
-VSX_MADD(xvmsubasp, 4, float32, VsrW(i), MSUB_FLGS, 1, 0, 0)
-VSX_MADD(xvmsubmsp, 4, float32, VsrW(i), MSUB_FLGS, 0, 0, 0)
-VSX_MADD(xvnmaddasp, 4, float32, VsrW(i), NMADD_FLGS, 1, 0, 0)
-VSX_MADD(xvnmaddmsp, 4, float32, VsrW(i), NMADD_FLGS, 0, 0, 0)
-VSX_MADD(xvnmsubasp, 4, float32, VsrW(i), NMSUB_FLGS, 1, 0, 0)
-VSX_MADD(xvnmsubmsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0, 0)
+VSX_MADD(xsmadddp, 1, float64, VsrD(0), MADD_FLGS, 1, 0)
+VSX_MADD(xsmsubdp, 1, float64, VsrD(0), MSUB_FLGS, 1, 0)
+VSX_MADD(xsnmadddp, 1, float64, VsrD(0), NMADD_FLGS, 1, 0)
+VSX_MADD(xsnmsubdp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0)
+VSX_MADD(xsmaddsp, 1, float64, VsrD(0), MADD_FLGS, 1, 1)
+VSX_MADD(xsmsubsp, 1, float64, VsrD(0), MSUB_FLGS, 1, 1)
+VSX_MADD(xsnmaddsp, 1, float64, VsrD(0), NMADD_FLGS, 1, 1)
+VSX_MADD(xsnmsubsp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1)
+
+VSX_MADD(xvmadddp, 2, float64, VsrD(i), MADD_FLGS, 0, 0)
+VSX_MADD(xvmsubdp, 2, float64, VsrD(i), MSUB_FLGS, 0, 0)
+VSX_MADD(xvnmadddp, 2, float64, VsrD(i), NMADD_FLGS, 0, 0)
+VSX_MADD(xvnmsubdp, 2, float64, VsrD(i), NMSUB_FLGS, 0, 0)
+
+VSX_MADD(xvmaddsp, 4, float32, VsrW(i), MADD_FLGS, 0, 0)
+VSX_MADD(xvmsubsp, 4, float32, VsrW(i), MSUB_FLGS, 0, 0)
+VSX_MADD(xvnmaddsp, 4, float32, VsrW(i), NMADD_FLGS, 0, 0)
+VSX_MADD(xvnmsubsp, 4, float32, VsrW(i), NMSUB_FLGS, 0, 0)
/*
* VSX_SCALAR_CMP_DP - VSX scalar floating point compare double precision
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 3d5150a524..380c9b1e2a 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -377,14 +377,10 @@ DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_4(xstdivdp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xstsqrtdp, void, env, i32, vsr)
-DEF_HELPER_4(xsmaddadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmaddmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmsubadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmsubmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmaddadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmaddmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmsubadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_5(xsmadddp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsmsubdp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsnmadddp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsnmsubdp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xscmpeqdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr)
@@ -444,14 +440,10 @@ DEF_HELPER_3(xsresp, void, env, vsr, vsr)
DEF_HELPER_2(xsrsp, i64, env, i64)
DEF_HELPER_3(xssqrtsp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtesp, void, env, vsr, vsr)
-DEF_HELPER_4(xsmaddasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmaddmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmsubasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsmsubmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmaddasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmaddmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmsubasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xsnmsubmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_5(xsmaddsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsmsubsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsnmaddsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xsnmsubsp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xvadddp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvsubdp, void, env, vsr, vsr, vsr)
@@ -462,14 +454,10 @@ DEF_HELPER_3(xvsqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_4(xvtdivdp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xvtsqrtdp, void, env, i32, vsr)
-DEF_HELPER_4(xvmaddadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmaddmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmsubadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmsubmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmaddadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmaddmdp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmsubadp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmsubmdp, void, env, vsr, vsr, vsr)
+DEF_HELPER_5(xvmadddp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvmsubdp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvnmadddp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvnmsubdp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xvmaxdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvmindp, void, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpeqdp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
@@ -500,14 +488,10 @@ DEF_HELPER_3(xvsqrtsp, void, env, vsr, vsr)
DEF_HELPER_3(xvrsqrtesp, void, env, vsr, vsr)
DEF_HELPER_4(xvtdivsp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xvtsqrtsp, void, env, i32, vsr)
-DEF_HELPER_4(xvmaddasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmaddmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmsubasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvmsubmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmaddasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmaddmsp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmsubasp, void, env, vsr, vsr, vsr)
-DEF_HELPER_4(xvnmsubmsp, void, env, vsr, vsr, vsr)
+DEF_HELPER_5(xvmaddsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvmsubsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvnmaddsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(xvnmsubsp, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xvmaxsp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvminsp, void, env, vsr, vsr, vsr)
DEF_HELPER_FLAGS_4(xvcmpeqsp, TCG_CALL_NO_RWG, i32, env, vsr, vsr, vsr)
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 7a4b7cb8f9..3922686ad6 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1182,14 +1182,6 @@ GEN_VSX_HELPER_X2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xstdivdp, 0x14, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_X1(xstsqrtdp, 0x14, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsmaddadp, 0x04, 0x04, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsmaddmdp, 0x04, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsmsubadp, 0x04, 0x06, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsmsubmdp, 0x04, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsnmaddadp, 0x04, 0x14, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsnmaddmdp, 0x04, 0x15, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsnmsubadp, 0x04, 0x16, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xsnmsubmdp, 0x04, 0x17, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300)
@@ -1231,12 +1223,10 @@ GEN_VSX_HELPER_X2(xsrdpim, 0x12, 0x07, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrdpip, 0x12, 0x06, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xsrdpiz, 0x12, 0x05, 0, PPC2_VSX)
GEN_VSX_HELPER_XT_XB_ENV(xsrsp, 0x12, 0x11, 0, PPC2_VSX207)
-
GEN_VSX_HELPER_R2(xsrqpi, 0x05, 0x00, 0, PPC2_ISA300)
GEN_VSX_HELPER_R2(xsrqpxp, 0x05, 0x01, 0, PPC2_ISA300)
GEN_VSX_HELPER_R2(xssqrtqp, 0x04, 0x19, 0x1B, PPC2_ISA300)
GEN_VSX_HELPER_R3(xssubqp, 0x04, 0x10, 0, PPC2_ISA300)
-
GEN_VSX_HELPER_X3(xsaddsp, 0x00, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xssubsp, 0x00, 0x01, 0, PPC2_VSX207)
GEN_VSX_HELPER_X3(xsmulsp, 0x00, 0x02, 0, PPC2_VSX207)
@@ -1244,14 +1234,6 @@ GEN_VSX_HELPER_X3(xsdivsp, 0x00, 0x03, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xsresp, 0x14, 0x01, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xssqrtsp, 0x16, 0x00, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xsrsqrtesp, 0x14, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsmaddasp, 0x04, 0x00, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsmaddmsp, 0x04, 0x01, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsmsubasp, 0x04, 0x02, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsmsubmsp, 0x04, 0x03, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsnmaddasp, 0x04, 0x10, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsnmaddmsp, 0x04, 0x11, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207)
-GEN_VSX_HELPER_X3(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_X2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207)
GEN_VSX_HELPER_X1(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300)
@@ -1267,14 +1249,6 @@ GEN_VSX_HELPER_X2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtedp, 0x14, 0x0C, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xvtdivdp, 0x14, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_X1(xvtsqrtdp, 0x14, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmaddadp, 0x04, 0x0C, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmaddmdp, 0x04, 0x0D, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmsubadp, 0x04, 0x0E, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmsubmdp, 0x04, 0x0F, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmaddadp, 0x04, 0x1C, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmaddmdp, 0x04, 0x1D, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmsubadp, 0x04, 0x1E, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmsubmdp, 0x04, 0x1F, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaxdp, 0x00, 0x1C, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmindp, 0x00, 0x1D, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvcvdpsp, 0x12, 0x18, 0, PPC2_VSX)
@@ -1301,14 +1275,6 @@ GEN_VSX_HELPER_X2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvrsqrtesp, 0x14, 0x08, 0, PPC2_VSX)
GEN_VSX_HELPER_X2_AB(xvtdivsp, 0x14, 0x0B, 0, PPC2_VSX)
GEN_VSX_HELPER_X1(xvtsqrtsp, 0x14, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmaddasp, 0x04, 0x08, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmaddmsp, 0x04, 0x09, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmsubasp, 0x04, 0x0A, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvmsubmsp, 0x04, 0x0B, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmaddasp, 0x04, 0x18, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmaddmsp, 0x04, 0x19, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmsubasp, 0x04, 0x1A, 0, PPC2_VSX)
-GEN_VSX_HELPER_X3(xvnmsubmsp, 0x04, 0x1B, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvmaxsp, 0x00, 0x18, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xvminsp, 0x00, 0x19, 0, PPC2_VSX)
GEN_VSX_HELPER_X2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX)
@@ -1332,6 +1298,53 @@ GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xxperm, 0x08, 0x03, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xxpermr, 0x08, 0x07, 0, PPC2_ISA300)
+#define GEN_VSX_HELPER_VSX_MADD(name, op1, aop, mop, inval, type) \
+static void gen_##name(DisasContext *ctx) \
+{ \
+ TCGv_ptr xt, xa, b, c; \
+ if (unlikely(!ctx->vsx_enabled)) { \
+ gen_exception(ctx, POWERPC_EXCP_VSXU); \
+ return; \
+ } \
+ xt = gen_vsr_ptr(xT(ctx->opcode)); \
+ xa = gen_vsr_ptr(xA(ctx->opcode)); \
+ if (ctx->opcode & PPC_BIT(25)) { \
+ /* \
+ * AxT + B \
+ */ \
+ b = gen_vsr_ptr(xT(ctx->opcode)); \
+ c = gen_vsr_ptr(xB(ctx->opcode)); \
+ } else { \
+ /* \
+ * AxB + T \
+ */ \
+ b = gen_vsr_ptr(xB(ctx->opcode)); \
+ c = gen_vsr_ptr(xT(ctx->opcode)); \
+ } \
+ gen_helper_##name(cpu_env, xt, xa, b, c); \
+ tcg_temp_free_ptr(xt); \
+ tcg_temp_free_ptr(xa); \
+ tcg_temp_free_ptr(b); \
+ tcg_temp_free_ptr(c); \
+}
+
+GEN_VSX_HELPER_VSX_MADD(xsmadddp, 0x04, 0x04, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xsmsubdp, 0x04, 0x06, 0x07, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xsnmadddp, 0x04, 0x14, 0x15, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xsnmsubdp, 0x04, 0x16, 0x17, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xsmaddsp, 0x04, 0x00, 0x01, 0, PPC2_VSX207)
+GEN_VSX_HELPER_VSX_MADD(xsmsubsp, 0x04, 0x02, 0x03, 0, PPC2_VSX207)
+GEN_VSX_HELPER_VSX_MADD(xsnmaddsp, 0x04, 0x10, 0x11, 0, PPC2_VSX207)
+GEN_VSX_HELPER_VSX_MADD(xsnmsubsp, 0x04, 0x12, 0x13, 0, PPC2_VSX207)
+GEN_VSX_HELPER_VSX_MADD(xvmadddp, 0x04, 0x0C, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvmsubdp, 0x04, 0x0E, 0x0F, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvnmadddp, 0x04, 0x1C, 0x1D, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvnmsubdp, 0x04, 0x1E, 0x1F, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvmaddsp, 0x04, 0x08, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvmsubsp, 0x04, 0x0A, 0x0B, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvnmaddsp, 0x04, 0x18, 0x19, 0, PPC2_VSX)
+GEN_VSX_HELPER_VSX_MADD(xvnmsubsp, 0x04, 0x1A, 0x1B, 0, PPC2_VSX)
+
static void gen_xxbrd(DisasContext *ctx)
{
TCGv_i64 xth;
diff --git a/target/ppc/translate/vsx-ops.inc.c b/target/ppc/translate/vsx-ops.inc.c
index 5030c4aceb..7fd3942b84 100644
--- a/target/ppc/translate/vsx-ops.inc.c
+++ b/target/ppc/translate/vsx-ops.inc.c
@@ -63,6 +63,12 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
+#define GEN_XX3FORM_NAME(name, opcname, opc2, opc3, fl2) \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 0, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
+
#define GEN_XX2IFORM(name, opc2, opc3, fl2) \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0, opc3, 1, PPC_NONE, fl2), \
GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 1, PPC_NONE, fl2), \
@@ -182,14 +188,14 @@ GEN_XX2FORM(xssqrtdp, 0x16, 0x04, PPC2_VSX),
GEN_XX2FORM(xsrsqrtedp, 0x14, 0x04, PPC2_VSX),
GEN_XX3FORM(xstdivdp, 0x14, 0x07, PPC2_VSX),
GEN_XX2FORM(xstsqrtdp, 0x14, 0x06, PPC2_VSX),
-GEN_XX3FORM(xsmaddadp, 0x04, 0x04, PPC2_VSX),
-GEN_XX3FORM(xsmaddmdp, 0x04, 0x05, PPC2_VSX),
-GEN_XX3FORM(xsmsubadp, 0x04, 0x06, PPC2_VSX),
-GEN_XX3FORM(xsmsubmdp, 0x04, 0x07, PPC2_VSX),
-GEN_XX3FORM(xsnmaddadp, 0x04, 0x14, PPC2_VSX),
-GEN_XX3FORM(xsnmaddmdp, 0x04, 0x15, PPC2_VSX),
-GEN_XX3FORM(xsnmsubadp, 0x04, 0x16, PPC2_VSX),
-GEN_XX3FORM(xsnmsubmdp, 0x04, 0x17, PPC2_VSX),
+GEN_XX3FORM_NAME(xsmadddp, "xsmaddadp", 0x04, 0x04, PPC2_VSX),
+GEN_XX3FORM_NAME(xsmadddp, "xsmaddmdp", 0x04, 0x05, PPC2_VSX),
+GEN_XX3FORM_NAME(xsmsubdp, "xsmsubadp", 0x04, 0x06, PPC2_VSX),
+GEN_XX3FORM_NAME(xsmsubdp, "xsmsubmdp", 0x04, 0x07, PPC2_VSX),
+GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddadp", 0x04, 0x14, PPC2_VSX),
+GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddmdp", 0x04, 0x15, PPC2_VSX),
+GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubadp", 0x04, 0x16, PPC2_VSX),
+GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubmdp", 0x04, 0x17, PPC2_VSX),
GEN_XX3FORM(xscmpeqdp, 0x0C, 0x00, PPC2_ISA300),
GEN_XX3FORM(xscmpgtdp, 0x0C, 0x01, PPC2_ISA300),
GEN_XX3FORM(xscmpgedp, 0x0C, 0x02, PPC2_ISA300),
@@ -235,14 +241,14 @@ GEN_XX2FORM(xsresp, 0x14, 0x01, PPC2_VSX207),
GEN_XX2FORM(xsrsp, 0x12, 0x11, PPC2_VSX207),
GEN_XX2FORM(xssqrtsp, 0x16, 0x00, PPC2_VSX207),
GEN_XX2FORM(xsrsqrtesp, 0x14, 0x00, PPC2_VSX207),
-GEN_XX3FORM(xsmaddasp, 0x04, 0x00, PPC2_VSX207),
-GEN_XX3FORM(xsmaddmsp, 0x04, 0x01, PPC2_VSX207),
-GEN_XX3FORM(xsmsubasp, 0x04, 0x02, PPC2_VSX207),
-GEN_XX3FORM(xsmsubmsp, 0x04, 0x03, PPC2_VSX207),
-GEN_XX3FORM(xsnmaddasp, 0x04, 0x10, PPC2_VSX207),
-GEN_XX3FORM(xsnmaddmsp, 0x04, 0x11, PPC2_VSX207),
-GEN_XX3FORM(xsnmsubasp, 0x04, 0x12, PPC2_VSX207),
-GEN_XX3FORM(xsnmsubmsp, 0x04, 0x13, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsmaddsp, "xsmaddasp", 0x04, 0x00, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsmaddsp, "xsmaddmsp", 0x04, 0x01, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsmsubsp, "xsmsubasp", 0x04, 0x02, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsmsubsp, "xsmsubmsp", 0x04, 0x03, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddasp", 0x04, 0x10, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddmsp", 0x04, 0x11, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubasp", 0x04, 0x12, PPC2_VSX207),
+GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubmsp", 0x04, 0x13, PPC2_VSX207),
GEN_XX2FORM(xscvsxdsp, 0x10, 0x13, PPC2_VSX207),
GEN_XX2FORM(xscvuxdsp, 0x10, 0x12, PPC2_VSX207),
@@ -255,14 +261,14 @@ GEN_XX2FORM(xvsqrtdp, 0x16, 0x0C, PPC2_VSX),
GEN_XX2FORM(xvrsqrtedp, 0x14, 0x0C, PPC2_VSX),
GEN_XX3FORM(xvtdivdp, 0x14, 0x0F, PPC2_VSX),
GEN_XX2FORM(xvtsqrtdp, 0x14, 0x0E, PPC2_VSX),
-GEN_XX3FORM(xvmaddadp, 0x04, 0x0C, PPC2_VSX),
-GEN_XX3FORM(xvmaddmdp, 0x04, 0x0D, PPC2_VSX),
-GEN_XX3FORM(xvmsubadp, 0x04, 0x0E, PPC2_VSX),
-GEN_XX3FORM(xvmsubmdp, 0x04, 0x0F, PPC2_VSX),
-GEN_XX3FORM(xvnmaddadp, 0x04, 0x1C, PPC2_VSX),
-GEN_XX3FORM(xvnmaddmdp, 0x04, 0x1D, PPC2_VSX),
-GEN_XX3FORM(xvnmsubadp, 0x04, 0x1E, PPC2_VSX),
-GEN_XX3FORM(xvnmsubmdp, 0x04, 0x1F, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmadddp, "xvmaddadp", 0x04, 0x0C, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmadddp, "xvmaddmdp", 0x04, 0x0D, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmsubdp, "xvmsubadp", 0x04, 0x0E, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmsubdp, "xvmsubmdp", 0x04, 0x0F, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmadddp, "xvnmaddadp", 0x04, 0x1C, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmadddp, "xvnmaddmdp", 0x04, 0x1D, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmsubdp, "xvnmsubadp", 0x04, 0x1E, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmsubdp, "xvnmsubmdp", 0x04, 0x1F, PPC2_VSX),
GEN_XX3FORM(xvmaxdp, 0x00, 0x1C, PPC2_VSX),
GEN_XX3FORM(xvmindp, 0x00, 0x1D, PPC2_VSX),
GEN_XX3_RC_FORM(xvcmpeqdp, 0x0C, 0x0C, PPC2_VSX),
@@ -293,14 +299,14 @@ GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),
GEN_XX2FORM(xvrsqrtesp, 0x14, 0x08, PPC2_VSX),
GEN_XX3FORM(xvtdivsp, 0x14, 0x0B, PPC2_VSX),
GEN_XX2FORM(xvtsqrtsp, 0x14, 0x0A, PPC2_VSX),
-GEN_XX3FORM(xvmaddasp, 0x04, 0x08, PPC2_VSX),
-GEN_XX3FORM(xvmaddmsp, 0x04, 0x09, PPC2_VSX),
-GEN_XX3FORM(xvmsubasp, 0x04, 0x0A, PPC2_VSX),
-GEN_XX3FORM(xvmsubmsp, 0x04, 0x0B, PPC2_VSX),
-GEN_XX3FORM(xvnmaddasp, 0x04, 0x18, PPC2_VSX),
-GEN_XX3FORM(xvnmaddmsp, 0x04, 0x19, PPC2_VSX),
-GEN_XX3FORM(xvnmsubasp, 0x04, 0x1A, PPC2_VSX),
-GEN_XX3FORM(xvnmsubmsp, 0x04, 0x1B, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmaddsp, "xvmaddasp", 0x04, 0x08, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmaddsp, "xvmaddmsp", 0x04, 0x09, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmsubsp, "xvmsubasp", 0x04, 0x0A, PPC2_VSX),
+GEN_XX3FORM_NAME(xvmsubsp, "xvmsubmsp", 0x04, 0x0B, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmaddsp, "xvnmaddasp", 0x04, 0x18, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmaddsp, "xvnmaddmsp", 0x04, 0x19, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmsubsp, "xvnmsubasp", 0x04, 0x1A, PPC2_VSX),
+GEN_XX3FORM_NAME(xvnmsubsp, "xvnmsubmsp", 0x04, 0x1B, PPC2_VSX),
GEN_XX3FORM(xvmaxsp, 0x00, 0x18, PPC2_VSX),
GEN_XX3FORM(xvminsp, 0x00, 0x19, PPC2_VSX),
GEN_XX3_RC_FORM(xvcmpeqsp, 0x0C, 0x08, PPC2_VSX),
--
2.11.0
^ permalink raw reply related [flat|nested] 21+ messages in thread* Re: [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (14 preceding siblings ...)
2019-06-16 12:37 ` [Qemu-devel] [PATCH v3 15/15] target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro Mark Cave-Ayland
@ 2019-06-16 13:18 ` no-reply
2019-06-18 8:43 ` David Gibson
2019-06-28 2:19 ` David Gibson
17 siblings, 0 replies; 21+ messages in thread
From: no-reply @ 2019-06-16 13:18 UTC (permalink / raw)
To: mark.cave-ayland; +Cc: gkurz, rth, qemu-ppc, qemu-devel, david
Patchew URL: https://patchew.org/QEMU/20190616123751.781-1-mark.cave-ayland@ilande.co.uk/
Hi,
This series seems to have some coding style problems. See output below for
more information:
Subject: [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up
Type: series
Message-id: 20190616123751.781-1-mark.cave-ayland@ilande.co.uk
=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram
./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===
From https://github.com/patchew-project/qemu
* [new tag] patchew/20190616123751.781-1-mark.cave-ayland@ilande.co.uk -> patchew/20190616123751.781-1-mark.cave-ayland@ilande.co.uk
Switched to a new branch 'test'
cf215f0211 target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro
6181c072c0 target/ppc: decode target register in VSX_EXTRACT_INSERT at translation time
172bdc4e29 target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time
14ca2eedff target/ppc: introduce GEN_VSX_HELPER_R2_AB macro to fpu_helper.c
e2c44f0799 target/ppc: introduce GEN_VSX_HELPER_R2 macro to fpu_helper.c
2f79ed9a9a target/ppc: introduce GEN_VSX_HELPER_R3 macro to fpu_helper.c
17abdcb489 target/ppc: introduce GEN_VSX_HELPER_X1 macro to fpu_helper.c
2090258624 target/ppc: introduce GEN_VSX_HELPER_X2_AB macro to fpu_helper.c
0195869440 target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c
dacf650f62 target/ppc: introduce separate generator and helper for xscvqpdp
8274d1ddd3 target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c
25605f2cb6 target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions
b87783ade3 target/ppc: remove getVSR()/putVSR() from int_helper.c
27f85ba7f7 target/ppc: remove getVSR()/putVSR() from mem_helper.c
c11cf2467d target/ppc: remove getVSR()/putVSR() from fpu_helper.c
=== OUTPUT BEGIN ===
1/15 Checking commit c11cf2467d33 (target/ppc: remove getVSR()/putVSR() from fpu_helper.c)
2/15 Checking commit 27f85ba7f7ce (target/ppc: remove getVSR()/putVSR() from mem_helper.c)
3/15 Checking commit b87783ade3f7 (target/ppc: remove getVSR()/putVSR() from int_helper.c)
4/15 Checking commit 25605f2cb6af (target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions)
5/15 Checking commit 8274d1ddd37f (target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c)
6/15 Checking commit dacf650f62e2 (target/ppc: introduce separate generator and helper for xscvqpdp)
7/15 Checking commit 0195869440db (target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c)
8/15 Checking commit 209025862401 (target/ppc: introduce GEN_VSX_HELPER_X2_AB macro to fpu_helper.c)
9/15 Checking commit 17abdcb48935 (target/ppc: introduce GEN_VSX_HELPER_X1 macro to fpu_helper.c)
10/15 Checking commit 2f79ed9a9aff (target/ppc: introduce GEN_VSX_HELPER_R3 macro to fpu_helper.c)
11/15 Checking commit e2c44f079928 (target/ppc: introduce GEN_VSX_HELPER_R2 macro to fpu_helper.c)
12/15 Checking commit 14ca2eedff9c (target/ppc: introduce GEN_VSX_HELPER_R2_AB macro to fpu_helper.c)
13/15 Checking commit 172bdc4e2952 (target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at translation time)
14/15 Checking commit 6181c072c009 (target/ppc: decode target register in VSX_EXTRACT_INSERT at translation time)
15/15 Checking commit cf215f0211f2 (target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro)
WARNING: Block comments use a leading /* on a separate line
#279: FILE: target/ppc/translate/vsx-impl.inc.c:1312:
+ /* \
WARNING: Block comments use a leading /* on a separate line
#285: FILE: target/ppc/translate/vsx-impl.inc.c:1318:
+ /* \
ERROR: Macros with complex values should be enclosed in parenthesis
#326: FILE: target/ppc/translate/vsx-ops.inc.c:66:
+#define GEN_XX3FORM_NAME(name, opcname, opc2, opc3, fl2) \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 0, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 2, opc3, 0, PPC_NONE, fl2), \
+GEN_HANDLER2_E(name, opcname, 0x3C, opc2 | 3, opc3, 0, PPC_NONE, fl2)
total: 1 errors, 2 warnings, 377 lines checked
Patch 15/15 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
=== OUTPUT END ===
Test command exited with code: 1
The full log is available at
http://patchew.org/logs/20190616123751.781-1-mark.cave-ayland@ilande.co.uk/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com
^ permalink raw reply [flat|nested] 21+ messages in thread* Re: [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (15 preceding siblings ...)
2019-06-16 13:18 ` [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up no-reply
@ 2019-06-18 8:43 ` David Gibson
2019-06-28 2:19 ` David Gibson
17 siblings, 0 replies; 21+ messages in thread
From: David Gibson @ 2019-06-18 8:43 UTC (permalink / raw)
To: Mark Cave-Ayland; +Cc: gkurz, qemu-ppc, qemu-devel, rth
[-- Attachment #1: Type: text/plain, Size: 4112 bytes --]
On Sun, Jun 16, 2019 at 01:37:36PM +0100, Mark Cave-Ayland wrote:
> With the conversion of PPC VSX registers to host endian during the 4.0 development
> cycle, the VSX helpers getVSR() and putVSR() which were used to convert between big
> endian and host endian (and are currently just a no-op) can now be removed. This
> eliminates an extra copy for each VSX source register at runtime.
>
> Patches 1-3 do the elimination work on a per-file basis and switch VSX register
> accesses to be via pointers rather than on copies managed using getVSR()/putVSR().
>
> After this patches 4-14 change the VSX registers to be passed to helpers via pointers
> rather than register number so that the decode of the vector register pointers occurs
> at translation time instead of at runtime. This matches how VMX instructions are
> currently decoded.
>
> Finally patch 15 performs some related tidy-up around VSX_FMADD which decodes the
> a or m form at translation time, allowing a single helper function to be used for
> both implementations.
>
> Greg: I've added you as CC since you managed to find a bug in my last series. This
> one is much more mechanical, but if you are able to confirm this doesn't introduce
> any regressions in your test images then that would be great.
>
> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Patches 1 & 2 applied.
>
> v3:
> - Rebase onto master
> - Add latest R-B tags from Richard
> - Fix zero init in helper_xvxsigsp() in patch 1
> - Preserve order of do_float_check_status() in helper_xsrqpi() in patch 1
> - Remove accidental write after store in VSX_STXVL() macro, and also just use
> the xt pointer directly in patch 2
>
> v2:
> - Rebase onto master
> - Use working copy of VSX destination registers in patches 1-3 to keep current
> semantics where src == dest and exception handling
> - Add patches 4 and 6 to split out helper functions still requiring an opcode
> parameter
> - Remove opcode parameter from GEN_VSX_HELPER_X3 and GEN_VSX_HELPER_X2 as it
> isn't required for the common case
> - Drop VSX_TEST_DC improvement patch since it is no longer applicable with the
> removal of opcode from the above macros
> - Rework VSX_MADD improvement patch to use a single helper for both a and m
> forms as suggested by Richard
>
>
> Mark Cave-Ayland (15):
> target/ppc: remove getVSR()/putVSR() from fpu_helper.c
> target/ppc: remove getVSR()/putVSR() from mem_helper.c
> target/ppc: remove getVSR()/putVSR() from int_helper.c
> target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions
> target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c
> target/ppc: introduce separate generator and helper for xscvqpdp
> target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_X2_AB macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_X1 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R3 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R2 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R2_AB macro to fpu_helper.c
> target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at
> translation time
> target/ppc: decode target register in VSX_EXTRACT_INSERT at
> translation time
> target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro
>
> target/ppc/fpu_helper.c | 841 ++++++++++++++++--------------------
> target/ppc/helper.h | 320 +++++++-------
> target/ppc/int_helper.c | 26 +-
> target/ppc/internal.h | 12 -
> target/ppc/mem_helper.c | 25 +-
> target/ppc/translate/vsx-impl.inc.c | 567 ++++++++++++++++--------
> target/ppc/translate/vsx-ops.inc.c | 70 +--
> 7 files changed, 952 insertions(+), 909 deletions(-)
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply [flat|nested] 21+ messages in thread* Re: [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up
2019-06-16 12:37 [Qemu-devel] [PATCH v3 00/15] target/ppc: remove getVSR()/putVSR() and further tidy-up Mark Cave-Ayland
` (16 preceding siblings ...)
2019-06-18 8:43 ` David Gibson
@ 2019-06-28 2:19 ` David Gibson
17 siblings, 0 replies; 21+ messages in thread
From: David Gibson @ 2019-06-28 2:19 UTC (permalink / raw)
To: Mark Cave-Ayland; +Cc: gkurz, qemu-ppc, qemu-devel, rth
[-- Attachment #1: Type: text/plain, Size: 4155 bytes --]
On Sun, Jun 16, 2019 at 01:37:36PM +0100, Mark Cave-Ayland wrote:
> With the conversion of PPC VSX registers to host endian during the 4.0 development
> cycle, the VSX helpers getVSR() and putVSR() which were used to convert between big
> endian and host endian (and are currently just a no-op) can now be removed. This
> eliminates an extra copy for each VSX source register at runtime.
>
> Patches 1-3 do the elimination work on a per-file basis and switch VSX register
> accesses to be via pointers rather than on copies managed using getVSR()/putVSR().
>
> After this patches 4-14 change the VSX registers to be passed to helpers via pointers
> rather than register number so that the decode of the vector register pointers occurs
> at translation time instead of at runtime. This matches how VMX instructions are
> currently decoded.
>
> Finally patch 15 performs some related tidy-up around VSX_FMADD which decodes the
> a or m form at translation time, allowing a single helper function to be used for
> both implementations.
>
> Greg: I've added you as CC since you managed to find a bug in my last series. This
> one is much more mechanical, but if you are able to confirm this doesn't introduce
> any regressions in your test images then that would be great.
>
> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
>
I've now applied the rest of this series to my ppc-for-4.1 tree.
> v3:
> - Rebase onto master
> - Add latest R-B tags from Richard
> - Fix zero init in helper_xvxsigsp() in patch 1
> - Preserve order of do_float_check_status() in helper_xsrqpi() in patch 1
> - Remove accidental write after store in VSX_STXVL() macro, and also just use
> the xt pointer directly in patch 2
>
> v2:
> - Rebase onto master
> - Use working copy of VSX destination registers in patches 1-3 to keep current
> semantics where src == dest and exception handling
> - Add patches 4 and 6 to split out helper functions still requiring an opcode
> parameter
> - Remove opcode parameter from GEN_VSX_HELPER_X3 and GEN_VSX_HELPER_X2 as it
> isn't required for the common case
> - Drop VSX_TEST_DC improvement patch since it is no longer applicable with the
> removal of opcode from the above macros
> - Rework VSX_MADD improvement patch to use a single helper for both a and m
> forms as suggested by Richard
>
>
> Mark Cave-Ayland (15):
> target/ppc: remove getVSR()/putVSR() from fpu_helper.c
> target/ppc: remove getVSR()/putVSR() from mem_helper.c
> target/ppc: remove getVSR()/putVSR() from int_helper.c
> target/ppc: introduce separate VSX_CMP macro for xvcmp* instructions
> target/ppc: introduce GEN_VSX_HELPER_X3 macro to fpu_helper.c
> target/ppc: introduce separate generator and helper for xscvqpdp
> target/ppc: introduce GEN_VSX_HELPER_X2 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_X2_AB macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_X1 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R3 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R2 macro to fpu_helper.c
> target/ppc: introduce GEN_VSX_HELPER_R2_AB macro to fpu_helper.c
> target/ppc: decode target register in VSX_VECTOR_LOAD_STORE_LENGTH at
> translation time
> target/ppc: decode target register in VSX_EXTRACT_INSERT at
> translation time
> target/ppc: improve VSX_FMADD with new GEN_VSX_HELPER_VSX_MADD macro
>
> target/ppc/fpu_helper.c | 841 ++++++++++++++++--------------------
> target/ppc/helper.h | 320 +++++++-------
> target/ppc/int_helper.c | 26 +-
> target/ppc/internal.h | 12 -
> target/ppc/mem_helper.c | 25 +-
> target/ppc/translate/vsx-impl.inc.c | 567 ++++++++++++++++--------
> target/ppc/translate/vsx-ops.inc.c | 70 +--
> 7 files changed, 952 insertions(+), 909 deletions(-)
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply [flat|nested] 21+ messages in thread