From: Peter Maydell <peter.maydell@linaro.org>
To: qemu-arm@nongnu.org, qemu-devel@nongnu.org
Subject: [PATCH for-6.2 45/53] target/arm: Implement MVE FP max/min across vector
Date: Thu, 29 Jul 2021 12:15:04 +0100 [thread overview]
Message-ID: <20210729111512.16541-46-peter.maydell@linaro.org> (raw)
In-Reply-To: <20210729111512.16541-1-peter.maydell@linaro.org>
Implement the MVE VMAXNMV, VMINNMV, VMAXNMAV, VMINNMAV insns. These
calculate the maximum or minimum of floating point elements across a
vector, starting with a value in a general purpose register and
returning the result there.
The pseudocode silences a possible SNaN in the accumulating result
on every iteration (by calling FPConvertNaN), but we do it only
on the input ra, because if none of the inputs to float*_maxnum
or float*_minnum are SNaNs then the result can't be an SNaN.
Note that we can't use the float*_maxnuma() etc functions we defined
earlier for VMAXNMA and VMINNMA, because we mustn't take the absolute
value of the starting general-purpose register value, which could be
negative.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/helper-mve.h | 12 +++++++++++
target/arm/mve.decode | 12 +++++++++++
target/arm/mve_helper.c | 44 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-mve.c | 20 +++++++++++++++++
4 files changed, 88 insertions(+)
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index cb7b6423239..47fd18dddbf 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -614,6 +614,18 @@ DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32)
DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32)
DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vmaxnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vmaxnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vminnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vminnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vmaxnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vmaxnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32)
+
+DEF_HELPER_FLAGS_3(mve_vminnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vminnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32)
+
DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64)
DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index d2bd6815bc3..1a18c3b8eeb 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -137,6 +137,10 @@
@vmaxnma .... .... .... .... .... .... .... .... &2op \
qd=%qd qn=%qd qm=%qm
+# Here also we don't decode the bit 28 size in the format to avoid
+# awkward nested overlap groups
+@vmaxnmv .... .... .... .... rda:4 .... .... .... &vmaxv qm=%qm
+
@2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \
qd=%qd qn=%qn size=%2op_fp_scalar_size
@@ -440,6 +444,10 @@ VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz
VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz
{
+ VMAXNMAV 1110 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2
+ VMINNMAV 1110 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2
+ VMAXNMV 1110 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2
+ VMINNMV 1110 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2
VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv
VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv
VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv
@@ -449,6 +457,10 @@ VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz
}
{
+ VMAXNMAV 1111 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1
+ VMINNMAV 1111 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1
+ VMAXNMV 1111 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1
+ VMINNMV 1111 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1
VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv
VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv
VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 3b243aaefa2..6a73134c74a 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -3117,3 +3117,47 @@ DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, uint16_t, float16_muladd)
DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, uint32_t, float32_muladd)
DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, uint16_t, DO_VFMAS_SCALARH)
DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, uint32_t, DO_VFMAS_SCALARS)
+
+/* Floating point max/min across vector. */
+#define DO_FP_VMAXMINV(OP, ESIZE, TYPE, FTYPE, ABS, FN) \
+ uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \
+ uint32_t ra_in) \
+ { \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ TYPE *m = vm; \
+ TYPE ra = (TYPE)ra_in; \
+ float_status *fpst = (ESIZE == 2) ? \
+ &env->vfp.standard_fp_status_f16 : \
+ &env->vfp.standard_fp_status; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ if (mask & 1) { \
+ TYPE v = m[H##ESIZE(e)]; \
+ if (FTYPE##_is_signaling_nan(ra, fpst)) { \
+ ra = FTYPE##_silence_nan(ra, fpst); \
+ float_raise(float_flag_invalid, fpst); \
+ } \
+ if (FTYPE##_is_signaling_nan(v, fpst)) { \
+ v = FTYPE##_silence_nan(v, fpst); \
+ float_raise(float_flag_invalid, fpst); \
+ } \
+ if (ABS) { \
+ v = FTYPE##_abs(v); \
+ } \
+ ra = FN(ra, v, fpst); \
+ } \
+ } \
+ mve_advance_vpt(env); \
+ return ra; \
+ } \
+
+#define NOP(X) (X)
+
+DO_FP_VMAXMINV(vmaxnmvh, 2, uint16_t, float16, false, float16_maxnum)
+DO_FP_VMAXMINV(vmaxnmvs, 4, uint32_t, float32, false, float32_maxnum)
+DO_FP_VMAXMINV(vminnmvh, 2, uint16_t, float16, false, float16_minnum)
+DO_FP_VMAXMINV(vminnmvs, 4, uint32_t, float32, false, float32_minnum)
+DO_FP_VMAXMINV(vmaxnmavh, 2, uint16_t, float16, true, float16_maxnum)
+DO_FP_VMAXMINV(vmaxnmavs, 4, uint32_t, float32, true, float32_maxnum)
+DO_FP_VMAXMINV(vminnmavh, 2, uint16_t, float16, true, float16_minnum)
+DO_FP_VMAXMINV(vminnmavs, 4, uint32_t, float32, true, float32_minnum)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 3627ba227f2..4e2aa2cae2d 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -1806,6 +1806,26 @@ DO_VMAXV(VMINV_S, vminvs)
DO_VMAXV(VMINV_U, vminvu)
DO_VMAXV(VMINAV, vminav)
+#define DO_VMAXV_FP(INSN, FN) \
+ static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \
+ { \
+ static MVEGenVADDVFn * const fns[] = { \
+ NULL, \
+ gen_helper_mve_##FN##h, \
+ gen_helper_mve_##FN##s, \
+ NULL, \
+ }; \
+ if (!dc_isar_feature(aa32_mve_fp, s)) { \
+ return false; \
+ } \
+ return do_vmaxv(s, a, fns[a->size]); \
+ }
+
+DO_VMAXV_FP(VMAXNMV, vmaxnmv)
+DO_VMAXV_FP(VMINNMV, vminnmv)
+DO_VMAXV_FP(VMAXNMAV, vmaxnmav)
+DO_VMAXV_FP(VMINNMAV, vminnmav)
+
static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn)
{
/* Absolute difference accumulated across vector */
--
2.20.1
next prev parent reply other threads:[~2021-07-29 11:52 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-29 11:14 [PATCH for-6.2 00/53] target/arm: MVE slices 3 and 4 Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 01/53] target/arm: Note that we handle VMOVL as a special case of VSHLL Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 02/53] target/arm: Print MVE VPR in CPU dumps Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 03/53] target/arm: Fix MVE VSLI by 0 and VSRI by <dt> Peter Maydell
2021-07-30 18:56 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 04/53] target/arm: Fix signed VADDV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 05/53] target/arm: Fix mask handling for MVE narrowing operations Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 06/53] target/arm: Fix 48-bit saturating shifts Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 07/53] target/arm: Fix MVE 48-bit SQRSHRL for small right shifts Peter Maydell
2021-07-30 19:07 ` Richard Henderson
2021-08-12 9:43 ` Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 08/53] target/arm: Fix calculation of LTP mask when LR is 0 Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 09/53] target/arm: Factor out mve_eci_mask() Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 10/53] target/arm: Fix VPT advance when ECI is non-zero Peter Maydell
2021-07-30 19:14 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 11/53] target/arm: Fix VLDRB/H/W for predicated elements Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 12/53] target/arm: Implement MVE VMULL (polynomial) Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 13/53] target/arm: Implement MVE incrementing/decrementing dup insns Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 14/53] target/arm: Factor out gen_vpst() Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 15/53] target/arm: Implement MVE integer vector comparisons Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 16/53] target/arm: Implement MVE integer vector-vs-scalar comparisons Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 17/53] target/arm: Implement MVE VPSEL Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 18/53] target/arm: Implement MVE VMLAS Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 19/53] target/arm: Implement MVE shift-by-scalar Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 20/53] target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 21/53] target/arm: Implement MVE integer min/max across vector Peter Maydell
2021-07-30 19:15 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 22/53] target/arm: Implement MVE VABAV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 23/53] target/arm: Implement MVE narrowing moves Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 24/53] target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 25/53] target/arm: Implement MVE VMLADAV and VMLSLDAV Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 26/53] target/arm: Implement MVE VMLA Peter Maydell
2021-07-30 19:18 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 27/53] target/arm: Implement MVE saturating doubling multiply accumulates Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 28/53] target/arm: Implement MVE VQABS, VQNEG Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 29/53] target/arm: Implement MVE VMAXA, VMINA Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 30/53] target/arm: Implement MVE VMOV to/from 2 general-purpose registers Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 31/53] target/arm: Implement MVE VPNOT Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 32/53] target/arm: Implement MVE VCTP Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 33/53] target/arm: Implement MVE scatter-gather insns Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 34/53] target/arm: Implement MVE scatter-gather immediate forms Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 35/53] target/arm: Implement MVE interleaving loads/stores Peter Maydell
2021-07-29 11:14 ` [PATCH for-6.2 36/53] target/arm: Implement MVE VADD (floating-point) Peter Maydell
2021-07-30 19:27 ` Richard Henderson
2021-07-30 19:37 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 37/53] target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM Peter Maydell
2021-07-30 19:28 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 38/53] target/arm: Implement MVE VCADD Peter Maydell
2021-07-30 19:32 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 39/53] target/arm: Implement MVE VFMA and VFMS Peter Maydell
2021-07-30 19:34 ` Richard Henderson
2021-07-30 19:41 ` Richard Henderson
2021-07-29 11:14 ` [PATCH for-6.2 40/53] target/arm: Implement MVE VCMUL and VCMLA Peter Maydell
2021-07-30 19:47 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 41/53] target/arm: Implement MVE VMAXNMA and VMINNMA Peter Maydell
2021-07-30 19:50 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 42/53] target/arm: Implement MVE scalar fp insns Peter Maydell
2021-07-30 19:55 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 43/53] target/arm: Implement MVE fp-with-scalar VFMA, VFMAS Peter Maydell
2021-07-30 19:58 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 44/53] softfloat: Remove assertion preventing silencing of NaN in default-NaN mode Peter Maydell
2021-07-30 20:00 ` Richard Henderson
2021-07-29 11:15 ` Peter Maydell [this message]
2021-07-30 20:12 ` [PATCH for-6.2 45/53] target/arm: Implement MVE FP max/min across vector Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 46/53] target/arm: Implement MVE fp vector comparisons Peter Maydell
2021-07-30 20:21 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 47/53] target/arm: Implement MVE fp scalar comparisons Peter Maydell
2021-07-30 20:22 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 48/53] target/arm: Implement MVE VCVT between floating and fixed point Peter Maydell
2021-07-30 20:24 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 49/53] target/arm: Implement MVE VCVT between fp and integer Peter Maydell
2021-07-30 20:27 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 50/53] target/arm: Implement MVE VCVT with specified rounding mode Peter Maydell
2021-07-30 20:28 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 51/53] target/arm: Implement MVE VCVT between single and half precision Peter Maydell
2021-07-30 20:33 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 52/53] target/arm: Implement MVE VRINT insns Peter Maydell
2021-07-30 20:47 ` Richard Henderson
2021-07-29 11:15 ` [PATCH for-6.2 53/53] target/arm: Enable MVE in Cortex-M55 Peter Maydell
2021-07-30 20:48 ` Richard Henderson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210729111512.16541-46-peter.maydell@linaro.org \
--to=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.