[PATCH 0/7] tcg: Clean up tcg_gen_gvec_dupi interface

[PATCH 0/7] tcg: Clean up tcg_gen_gvec_dupi interface

[Richard Henderson]

Replace 4 separate routines with a single routine taking a vece
parameter.  This avoids several targets needing to create this
interface internally.

I noticed this in particular reviewing the riscv code; I'm not
sure why it took three targets to notice.  ;-)


r~


Richard Henderson (7):
  tcg: Add tcg_gen_gvec_dup_imm
  target/s390x: Use tcg_gen_gvec_dup_imm
  target/ppc: Use tcg_gen_gvec_dup_imm
  target/arm: Use tcg_gen_gvec_dup_imm
  tcg: Use tcg_gen_gvec_dup_imm in logical simplifications
  tcg: Remove tcg_gen_gvec_dup{8,16,32,64}i
  tcg: Add tcg_gen_gvec_dup_tl

 include/tcg/tcg-op-gvec.h           | 11 +++++---
 target/arm/translate-a64.c          | 10 +++----
 target/arm/translate-sve.c          | 12 ++++-----
 target/arm/translate.c              |  9 ++++---
 target/ppc/translate/vmx-impl.inc.c | 32 ++++++++++++----------
 target/ppc/translate/vsx-impl.inc.c |  2 +-
 target/s390x/translate_vx.inc.c     | 41 ++++++-----------------------
 tcg/tcg-op-gvec.c                   | 35 +++++-------------------
 8 files changed, 57 insertions(+), 95 deletions(-)

-- 
2.20.1

[PATCH 1/7] tcg: Add tcg_gen_gvec_dup_imm

[Richard Henderson]

Add a version of tcg_gen_dup_* that takes both immediate and
a vector element size operand.  This will replace the set of
tcg_gen_gvec_dup{8,16,32,64}i functions that encode the element
size within the function name.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/tcg/tcg-op-gvec.h | 2 ++
 tcg/tcg-op-gvec.c         | 7 +++++++
 2 files changed, 9 insertions(+)

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index 74534e2480..eb0d47a42b 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -313,6 +313,8 @@ void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
 
 void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
                           uint32_t s, uint32_t m);
+void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s,
+                          uint32_t m, uint64_t imm);
 void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
                           uint32_t m, TCGv_i32);
 void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 327d9588e0..593bb4542e 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1569,6 +1569,13 @@ void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
     do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
 }
 
+void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
+                          uint32_t maxsz, uint64_t x)
+{
+    check_size_align(oprsz, maxsz, dofs);
+    do_dup(vece, dofs, oprsz, maxsz, NULL, NULL, x);
+}
+
 void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs,
                       uint32_t oprsz, uint32_t maxsz)
 {
-- 
2.20.1

[PATCH 2/7] target/s390x: Use tcg_gen_gvec_dup_imm

[Richard Henderson]

The gen_gvec_dupi switch is unnecessarily with the new function.
Replace it with a local gen_gvec_dup_imm that takes care of the
register to offset conversion and length arguments.

Drop zero_vec and use use gen_gvec_dup_imm with 0.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/s390x/translate_vx.inc.c | 41 +++++++--------------------------
 1 file changed, 8 insertions(+), 33 deletions(-)

diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 24558cce80..12347f8a03 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -231,8 +231,8 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
 #define gen_gvec_mov(v1, v2) \
     tcg_gen_gvec_mov(0, vec_full_reg_offset(v1), vec_full_reg_offset(v2), 16, \
                      16)
-#define gen_gvec_dup64i(v1, c) \
-    tcg_gen_gvec_dup64i(vec_full_reg_offset(v1), 16, 16, c)
+#define gen_gvec_dup_imm(es, v1, c) \
+    tcg_gen_gvec_dup_imm(es, vec_full_reg_offset(v1), 16, 16, c);
 #define gen_gvec_fn_2(fn, es, v1, v2) \
     tcg_gen_gvec_##fn(es, vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                       16, 16)
@@ -316,31 +316,6 @@ static void gen_gvec128_4_i64(gen_gvec128_4_i64_fn fn, uint8_t d, uint8_t a,
         tcg_temp_free_i64(cl);
 }
 
-static void gen_gvec_dupi(uint8_t es, uint8_t reg, uint64_t c)
-{
-    switch (es) {
-    case ES_8:
-        tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, c);
-        break;
-    case ES_16:
-        tcg_gen_gvec_dup16i(vec_full_reg_offset(reg), 16, 16, c);
-        break;
-    case ES_32:
-        tcg_gen_gvec_dup32i(vec_full_reg_offset(reg), 16, 16, c);
-        break;
-    case ES_64:
-        gen_gvec_dup64i(reg, c);
-        break;
-    default:
-        g_assert_not_reached();
-    }
-}
-
-static void zero_vec(uint8_t reg)
-{
-    tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, 0);
-}
-
 static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah,
                           uint64_t b)
 {
@@ -396,8 +371,8 @@ static DisasJumpType op_vgbm(DisasContext *s, DisasOps *o)
          * Masks for both 64 bit elements of the vector are the same.
          * Trust tcg to produce a good constant loading.
          */
-        gen_gvec_dup64i(get_field(s, v1),
-                        generate_byte_mask(i2 & 0xff));
+        gen_gvec_dup_imm(ES_64, get_field(s, v1),
+                         generate_byte_mask(i2 & 0xff));
     } else {
         TCGv_i64 t = tcg_temp_new_i64();
 
@@ -432,7 +407,7 @@ static DisasJumpType op_vgm(DisasContext *s, DisasOps *o)
         }
     }
 
-    gen_gvec_dupi(es, get_field(s, v1), mask);
+    gen_gvec_dup_imm(es, get_field(s, v1), mask);
     return DISAS_NEXT;
 }
 
@@ -585,7 +560,7 @@ static DisasJumpType op_vllez(DisasContext *s, DisasOps *o)
 
     t = tcg_temp_new_i64();
     tcg_gen_qemu_ld_i64(t, o->addr1, get_mem_index(s), MO_TE | es);
-    zero_vec(get_field(s, v1));
+    gen_gvec_dup_imm(es, get_field(s, v1), 0);
     write_vec_element_i64(t, get_field(s, v1), enr, es);
     tcg_temp_free_i64(t);
     return DISAS_NEXT;
@@ -892,7 +867,7 @@ static DisasJumpType op_vrepi(DisasContext *s, DisasOps *o)
         return DISAS_NORETURN;
     }
 
-    gen_gvec_dupi(es, get_field(s, v1), data);
+    gen_gvec_dup_imm(es, get_field(s, v1), data);
     return DISAS_NEXT;
 }
 
@@ -1372,7 +1347,7 @@ static DisasJumpType op_vcksm(DisasContext *s, DisasOps *o)
         read_vec_element_i32(tmp, get_field(s, v2), i, ES_32);
         tcg_gen_add2_i32(tmp, sum, sum, sum, tmp, tmp);
     }
-    zero_vec(get_field(s, v1));
+    gen_gvec_dup_imm(ES_32, get_field(s, v1), 0);
     write_vec_element_i32(sum, get_field(s, v1), 1, ES_32);
 
     tcg_temp_free_i32(tmp);
-- 
2.20.1

[PATCH 3/7] target/ppc: Use tcg_gen_gvec_dup_imm

[Richard Henderson]

We can now unify the implementation of the 3 VSPLTI instructions.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/translate/vmx-impl.inc.c | 32 ++++++++++++++++-------------
 target/ppc/translate/vsx-impl.inc.c |  2 +-
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
index 81d5a7a341..403ed3a01c 100644
--- a/target/ppc/translate/vmx-impl.inc.c
+++ b/target/ppc/translate/vmx-impl.inc.c
@@ -1035,21 +1035,25 @@ GEN_VXRFORM_DUAL(vcmpbfp, PPC_ALTIVEC, PPC_NONE, \
 GEN_VXRFORM_DUAL(vcmpgtfp, PPC_ALTIVEC, PPC_NONE, \
                  vcmpgtud, PPC_NONE, PPC2_ALTIVEC_207)
 
-#define GEN_VXFORM_DUPI(name, tcg_op, opc2, opc3)                       \
-static void glue(gen_, name)(DisasContext *ctx)                         \
-    {                                                                   \
-        int simm;                                                       \
-        if (unlikely(!ctx->altivec_enabled)) {                          \
-            gen_exception(ctx, POWERPC_EXCP_VPU);                       \
-            return;                                                     \
-        }                                                               \
-        simm = SIMM5(ctx->opcode);                                      \
-        tcg_op(avr_full_offset(rD(ctx->opcode)), 16, 16, simm);         \
+static void gen_vsplti(DisasContext *ctx, int vece)
+{
+    int simm;
+
+    if (unlikely(!ctx->altivec_enabled)) {
+        gen_exception(ctx, POWERPC_EXCP_VPU);
+        return;
     }
 
-GEN_VXFORM_DUPI(vspltisb, tcg_gen_gvec_dup8i, 6, 12);
-GEN_VXFORM_DUPI(vspltish, tcg_gen_gvec_dup16i, 6, 13);
-GEN_VXFORM_DUPI(vspltisw, tcg_gen_gvec_dup32i, 6, 14);
+    simm = SIMM5(ctx->opcode);
+    tcg_gen_gvec_dup_imm(vece, avr_full_offset(rD(ctx->opcode)), 16, 16, simm);
+}
+
+#define GEN_VXFORM_VSPLTI(name, vece, opc2, opc3) \
+static void glue(gen_, name)(DisasContext *ctx) { gen_vsplti(ctx, vece); }
+
+GEN_VXFORM_VSPLTI(vspltisb, MO_8, 6, 12);
+GEN_VXFORM_VSPLTI(vspltish, MO_16, 6, 13);
+GEN_VXFORM_VSPLTI(vspltisw, MO_32, 6, 14);
 
 #define GEN_VXFORM_NOA(name, opc2, opc3)                                \
 static void glue(gen_, name)(DisasContext *ctx)                         \
@@ -1559,7 +1563,7 @@ GEN_VXFORM_DUAL(vsldoi, PPC_ALTIVEC, PPC_NONE,
 #undef GEN_VXRFORM_DUAL
 #undef GEN_VXRFORM1
 #undef GEN_VXRFORM
-#undef GEN_VXFORM_DUPI
+#undef GEN_VXFORM_VSPLTI
 #undef GEN_VXFORM_NOA
 #undef GEN_VXFORM_UIMM
 #undef GEN_VAFORM_PAIRED
diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
index 8287e272f5..b518de46db 100644
--- a/target/ppc/translate/vsx-impl.inc.c
+++ b/target/ppc/translate/vsx-impl.inc.c
@@ -1579,7 +1579,7 @@ static void gen_xxspltib(DisasContext *ctx)
             return;
         }
     }
-    tcg_gen_gvec_dup8i(vsr_full_offset(rt), 16, 16, uim8);
+    tcg_gen_gvec_dup_imm(MO_8, vsr_full_offset(rt), 16, 16, uim8);
 }
 
 static void gen_xxsldwi(DisasContext *ctx)
-- 
2.20.1

[PATCH 4/7] target/arm: Use tcg_gen_gvec_dup_imm

[Richard Henderson]

In a few cases, we're able to remove some manual replication.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-a64.c | 10 +++++-----
 target/arm/translate-sve.c | 12 +++++-------
 target/arm/translate.c     |  9 ++++++---
 3 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 7580e46367..095638e09a 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -519,7 +519,7 @@ static void clear_vec_high(DisasContext *s, bool is_q, int rd)
         tcg_temp_free_i64(tcg_zero);
     }
     if (vsz > 16) {
-        tcg_gen_gvec_dup8i(ofs + 16, vsz - 16, vsz - 16, 0);
+        tcg_gen_gvec_dup_imm(MO_64, ofs + 16, vsz - 16, vsz - 16, 0);
     }
 }
 
@@ -7794,8 +7794,8 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
 
     if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) {
         /* MOVI or MVNI, with MVNI negation handled above.  */
-        tcg_gen_gvec_dup64i(vec_full_reg_offset(s, rd), is_q ? 16 : 8,
-                            vec_full_reg_size(s), imm);
+        tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), is_q ? 16 : 8,
+                             vec_full_reg_size(s), imm);
     } else {
         /* ORR or BIC, with BIC negation to AND handled above.  */
         if (is_neg) {
@@ -10223,8 +10223,8 @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
         if (is_u) {
             if (shift == 8 << size) {
                 /* Shift count the same size as element size produces zero.  */
-                tcg_gen_gvec_dup8i(vec_full_reg_offset(s, rd),
-                                   is_q ? 16 : 8, vec_full_reg_size(s), 0);
+                tcg_gen_gvec_dup_imm(size, vec_full_reg_offset(s, rd),
+                                     is_q ? 16 : 8, vec_full_reg_size(s), 0);
             } else {
                 gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shri, size);
             }
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index b35bad245e..6c8bda4e4c 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -177,7 +177,7 @@ static bool do_mov_z(DisasContext *s, int rd, int rn)
 static void do_dupi_z(DisasContext *s, int rd, uint64_t word)
 {
     unsigned vsz = vec_full_reg_size(s);
-    tcg_gen_gvec_dup64i(vec_full_reg_offset(s, rd), vsz, vsz, word);
+    tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), vsz, vsz, word);
 }
 
 /* Invoke a vector expander on two Pregs.  */
@@ -1453,7 +1453,7 @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
         unsigned oprsz = size_for_gvec(setsz / 8);
 
         if (oprsz * 8 == setsz) {
-            tcg_gen_gvec_dup64i(ofs, oprsz, maxsz, word);
+            tcg_gen_gvec_dup_imm(MO_64, ofs, oprsz, maxsz, word);
             goto done;
         }
     }
@@ -2044,7 +2044,7 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
             unsigned nofs = vec_reg_offset(s, a->rn, index, esz);
             tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz);
         } else {
-            tcg_gen_gvec_dup64i(dofs, vsz, vsz, 0);
+            tcg_gen_gvec_dup_imm(esz, dofs, vsz, vsz, 0);
         }
     }
     return true;
@@ -3260,9 +3260,7 @@ static bool trans_FDUP(DisasContext *s, arg_FDUP *a)
 
         /* Decode the VFP immediate.  */
         imm = vfp_expand_imm(a->esz, a->imm);
-        imm = dup_const(a->esz, imm);
-
-        tcg_gen_gvec_dup64i(dofs, vsz, vsz, imm);
+        tcg_gen_gvec_dup_imm(a->esz, dofs, vsz, vsz, imm);
     }
     return true;
 }
@@ -3276,7 +3274,7 @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a)
         unsigned vsz = vec_full_reg_size(s);
         int dofs = vec_full_reg_offset(s, a->rd);
 
-        tcg_gen_gvec_dup64i(dofs, vsz, vsz, dup_const(a->esz, a->imm));
+        tcg_gen_gvec_dup_imm(a->esz, dofs, vsz, vsz, a->imm);
     }
     return true;
 }
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 9f9f4e19e0..af4d3ff4c9 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5386,7 +5386,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                                           MIN(shift, (8 << size) - 1),
                                           vec_size, vec_size);
                     } else if (shift >= 8 << size) {
-                        tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0);
+                        tcg_gen_gvec_dup_imm(MO_8, rd_ofs, vec_size,
+                                             vec_size, 0);
                     } else {
                         tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift,
                                           vec_size, vec_size);
@@ -5437,7 +5438,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                          * architecturally valid and results in zero.
                          */
                         if (shift >= 8 << size) {
-                            tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0);
+                            tcg_gen_gvec_dup_imm(size, rd_ofs,
+                                                 vec_size, vec_size, 0);
                         } else {
                             tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift,
                                               vec_size, vec_size);
@@ -5783,7 +5785,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                     }
                     tcg_temp_free_i64(t64);
                 } else {
-                    tcg_gen_gvec_dup32i(reg_ofs, vec_size, vec_size, imm);
+                    tcg_gen_gvec_dup_imm(MO_32, reg_ofs, vec_size,
+                                         vec_size, imm);
                 }
             }
         }
-- 
2.20.1

[PATCH 5/7] tcg: Use tcg_gen_gvec_dup_imm in logical simplifications

[Richard Henderson]

Replace the outgoing interface.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tcg-op-gvec.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 593bb4542e..de16c027b3 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -2326,7 +2326,7 @@ void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs,
     };
 
     if (aofs == bofs) {
-        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
+        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
     } else {
         tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
     }
@@ -2343,7 +2343,7 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs,
     };
 
     if (aofs == bofs) {
-        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
+        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
     } else {
         tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
     }
@@ -2360,7 +2360,7 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs,
     };
 
     if (aofs == bofs) {
-        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
+        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
     } else {
         tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
     }
@@ -2411,7 +2411,7 @@ void tcg_gen_gvec_eqv(unsigned vece, uint32_t dofs, uint32_t aofs,
     };
 
     if (aofs == bofs) {
-        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
+        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
     } else {
         tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
     }
-- 
2.20.1

[PATCH 6/7] tcg: Remove tcg_gen_gvec_dup{8,16,32,64}i

[Richard Henderson]

These interfaces are now unused.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/tcg/tcg-op-gvec.h |  5 -----
 tcg/tcg-op-gvec.c         | 28 ----------------------------
 2 files changed, 33 deletions(-)

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index eb0d47a42b..fa8a0c8d03 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -320,11 +320,6 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
 void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
                           uint32_t m, TCGv_i64);
 
-void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t s, uint32_t m, uint8_t x);
-void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t s, uint32_t m, uint16_t x);
-void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t s, uint32_t m, uint32_t x);
-void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t s, uint32_t m, uint64_t x);
-
 void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index de16c027b3..5a6cc19812 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1541,34 +1541,6 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
     }
 }
 
-void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t oprsz,
-                         uint32_t maxsz, uint64_t x)
-{
-    check_size_align(oprsz, maxsz, dofs);
-    do_dup(MO_64, dofs, oprsz, maxsz, NULL, NULL, x);
-}
-
-void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t oprsz,
-                         uint32_t maxsz, uint32_t x)
-{
-    check_size_align(oprsz, maxsz, dofs);
-    do_dup(MO_32, dofs, oprsz, maxsz, NULL, NULL, x);
-}
-
-void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t oprsz,
-                         uint32_t maxsz, uint16_t x)
-{
-    check_size_align(oprsz, maxsz, dofs);
-    do_dup(MO_16, dofs, oprsz, maxsz, NULL, NULL, x);
-}
-
-void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
-                         uint32_t maxsz, uint8_t x)
-{
-    check_size_align(oprsz, maxsz, dofs);
-    do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
-}
-
 void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
                           uint32_t maxsz, uint64_t x)
 {
-- 
2.20.1

[PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[Richard Henderson]

For use when a target needs to pass a configure-specific
target_ulong value to duplicate.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/tcg/tcg-op-gvec.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index fa8a0c8d03..d89f91f40e 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -320,6 +320,12 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
 void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
                           uint32_t m, TCGv_i64);
 
+#if TARGET_LONG_BITS == 64
+# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
+#else
+# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
+#endif
+
 void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
-- 
2.20.1

Re: [PATCH 1/7] tcg: Add tcg_gen_gvec_dup_imm

[LIU Zhiwei]

On 2020/4/18 23:04, Richard Henderson wrote:
> Add a version of tcg_gen_dup_* that takes both immediate and
> a vector element size operand.  This will replace the set of
> tcg_gen_gvec_dup{8,16,32,64}i functions that encode the element
> size within the function name.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Zhiwei
> ---
>   include/tcg/tcg-op-gvec.h | 2 ++
>   tcg/tcg-op-gvec.c         | 7 +++++++
>   2 files changed, 9 insertions(+)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index 74534e2480..eb0d47a42b 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -313,6 +313,8 @@ void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
>   
>   void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>                             uint32_t s, uint32_t m);
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s,
> +                          uint32_t m, uint64_t imm);
>   void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>                             uint32_t m, TCGv_i32);
>   void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index 327d9588e0..593bb4542e 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1569,6 +1569,13 @@ void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
>       do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
>   }
>   
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
> +                          uint32_t maxsz, uint64_t x)
> +{
> +    check_size_align(oprsz, maxsz, dofs);
> +    do_dup(vece, dofs, oprsz, maxsz, NULL, NULL, x);
> +}
> +
>   void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs,
>                         uint32_t oprsz, uint32_t maxsz)
>   {

Re: [PATCH 3/7] target/ppc: Use tcg_gen_gvec_dup_imm

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 3625 bytes --]

On Sat, Apr 18, 2020 at 08:04:07AM -0700, Richard Henderson wrote:
> We can now unify the implementation of the 3 VSPLTI instructions.
> 
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Acked-by: David Gibson <david@gibson.dropbear.id.au>

> ---
>  target/ppc/translate/vmx-impl.inc.c | 32 ++++++++++++++++-------------
>  target/ppc/translate/vsx-impl.inc.c |  2 +-
>  2 files changed, 19 insertions(+), 15 deletions(-)
> 
> diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
> index 81d5a7a341..403ed3a01c 100644
> --- a/target/ppc/translate/vmx-impl.inc.c
> +++ b/target/ppc/translate/vmx-impl.inc.c
> @@ -1035,21 +1035,25 @@ GEN_VXRFORM_DUAL(vcmpbfp, PPC_ALTIVEC, PPC_NONE, \
>  GEN_VXRFORM_DUAL(vcmpgtfp, PPC_ALTIVEC, PPC_NONE, \
>                   vcmpgtud, PPC_NONE, PPC2_ALTIVEC_207)
>  
> -#define GEN_VXFORM_DUPI(name, tcg_op, opc2, opc3)                       \
> -static void glue(gen_, name)(DisasContext *ctx)                         \
> -    {                                                                   \
> -        int simm;                                                       \
> -        if (unlikely(!ctx->altivec_enabled)) {                          \
> -            gen_exception(ctx, POWERPC_EXCP_VPU);                       \
> -            return;                                                     \
> -        }                                                               \
> -        simm = SIMM5(ctx->opcode);                                      \
> -        tcg_op(avr_full_offset(rD(ctx->opcode)), 16, 16, simm);         \
> +static void gen_vsplti(DisasContext *ctx, int vece)
> +{
> +    int simm;
> +
> +    if (unlikely(!ctx->altivec_enabled)) {
> +        gen_exception(ctx, POWERPC_EXCP_VPU);
> +        return;
>      }
>  
> -GEN_VXFORM_DUPI(vspltisb, tcg_gen_gvec_dup8i, 6, 12);
> -GEN_VXFORM_DUPI(vspltish, tcg_gen_gvec_dup16i, 6, 13);
> -GEN_VXFORM_DUPI(vspltisw, tcg_gen_gvec_dup32i, 6, 14);
> +    simm = SIMM5(ctx->opcode);
> +    tcg_gen_gvec_dup_imm(vece, avr_full_offset(rD(ctx->opcode)), 16, 16, simm);
> +}
> +
> +#define GEN_VXFORM_VSPLTI(name, vece, opc2, opc3) \
> +static void glue(gen_, name)(DisasContext *ctx) { gen_vsplti(ctx, vece); }
> +
> +GEN_VXFORM_VSPLTI(vspltisb, MO_8, 6, 12);
> +GEN_VXFORM_VSPLTI(vspltish, MO_16, 6, 13);
> +GEN_VXFORM_VSPLTI(vspltisw, MO_32, 6, 14);
>  
>  #define GEN_VXFORM_NOA(name, opc2, opc3)                                \
>  static void glue(gen_, name)(DisasContext *ctx)                         \
> @@ -1559,7 +1563,7 @@ GEN_VXFORM_DUAL(vsldoi, PPC_ALTIVEC, PPC_NONE,
>  #undef GEN_VXRFORM_DUAL
>  #undef GEN_VXRFORM1
>  #undef GEN_VXRFORM
> -#undef GEN_VXFORM_DUPI
> +#undef GEN_VXFORM_VSPLTI
>  #undef GEN_VXFORM_NOA
>  #undef GEN_VXFORM_UIMM
>  #undef GEN_VAFORM_PAIRED
> diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
> index 8287e272f5..b518de46db 100644
> --- a/target/ppc/translate/vsx-impl.inc.c
> +++ b/target/ppc/translate/vsx-impl.inc.c
> @@ -1579,7 +1579,7 @@ static void gen_xxspltib(DisasContext *ctx)
>              return;
>          }
>      }
> -    tcg_gen_gvec_dup8i(vsr_full_offset(rt), 16, 16, uim8);
> +    tcg_gen_gvec_dup_imm(MO_8, vsr_full_offset(rt), 16, 16, uim8);
>  }
>  
>  static void gen_xxsldwi(DisasContext *ctx)

-- 
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 --]

Re: [PATCH 5/7] tcg: Use tcg_gen_gvec_dup_imm in logical simplifications

[LIU Zhiwei]

On 2020/4/18 23:04, Richard Henderson wrote:
> Replace the outgoing interface.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Zhiwei
> ---
>   tcg/tcg-op-gvec.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index 593bb4542e..de16c027b3 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -2326,7 +2326,7 @@ void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs,
>       };
>   
>       if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
>       } else {
>           tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>       }
> @@ -2343,7 +2343,7 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs,
>       };
>   
>       if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
>       } else {
>           tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>       }
> @@ -2360,7 +2360,7 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs,
>       };
>   
>       if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
>       } else {
>           tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>       }
> @@ -2411,7 +2411,7 @@ void tcg_gen_gvec_eqv(unsigned vece, uint32_t dofs, uint32_t aofs,
>       };
>   
>       if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
>       } else {
>           tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>       }

Re: [PATCH 6/7] tcg: Remove tcg_gen_gvec_dup{8,16,32,64}i

[LIU Zhiwei]

On 2020/4/18 23:04, Richard Henderson wrote:
> These interfaces are now unused.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Zhiwei
> ---
>   include/tcg/tcg-op-gvec.h |  5 -----
>   tcg/tcg-op-gvec.c         | 28 ----------------------------
>   2 files changed, 33 deletions(-)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index eb0d47a42b..fa8a0c8d03 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,11 +320,6 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>   void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                             uint32_t m, TCGv_i64);
>   
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t s, uint32_t m, uint8_t x);
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t s, uint32_t m, uint16_t x);
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t s, uint32_t m, uint32_t x);
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t s, uint32_t m, uint64_t x);
> -
>   void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
>                          int64_t shift, uint32_t oprsz, uint32_t maxsz);
>   void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index de16c027b3..5a6cc19812 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1541,34 +1541,6 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>       }
>   }
>   
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint64_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_64, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint32_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_32, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint16_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_16, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint8_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
>   void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
>                             uint32_t maxsz, uint64_t x)
>   {

Re: [PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[LIU Zhiwei]

On 2020/4/18 23:04, Richard Henderson wrote:
> For use when a target needs to pass a configure-specific
> target_ulong value to duplicate.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: LIU Zhiwei <zhiwei_liu@c-sky.com>

Zhiwei
> ---
>   include/tcg/tcg-op-gvec.h | 6 ++++++
>   1 file changed, 6 insertions(+)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index fa8a0c8d03..d89f91f40e 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,6 +320,12 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>   void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                             uint32_t m, TCGv_i64);
>   
> +#if TARGET_LONG_BITS == 64
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
> +#else
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
> +#endif
> +
>   void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
>                          int64_t shift, uint32_t oprsz, uint32_t maxsz);
>   void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,

Re: [PATCH 2/7] target/s390x: Use tcg_gen_gvec_dup_imm

[David Hildenbrand]

On 18.04.20 17:04, Richard Henderson wrote:
> The gen_gvec_dupi switch is unnecessarily with the new function.
> Replace it with a local gen_gvec_dup_imm that takes care of the
> register to offset conversion and length arguments.
> 
> Drop zero_vec and use use gen_gvec_dup_imm with 0.
> 
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Nice cleanup, thanks!

Reviewed-by: David Hildenbrand <david@redhat.com>


-- 
Thanks,

David / dhildenb

Re: [PATCH 1/7] tcg: Add tcg_gen_gvec_dup_imm

[David Hildenbrand]

On 18.04.20 17:04, Richard Henderson wrote:
> Add a version of tcg_gen_dup_* that takes both immediate and
> a vector element size operand.  This will replace the set of
> tcg_gen_gvec_dup{8,16,32,64}i functions that encode the element
> size within the function name.
> 
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  include/tcg/tcg-op-gvec.h | 2 ++
>  tcg/tcg-op-gvec.c         | 7 +++++++
>  2 files changed, 9 insertions(+)
> 
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index 74534e2480..eb0d47a42b 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -313,6 +313,8 @@ void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
>  
>  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>                            uint32_t s, uint32_t m);
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s,
> +                          uint32_t m, uint64_t imm);
>  void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i32);
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index 327d9588e0..593bb4542e 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1569,6 +1569,13 @@ void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
>      do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
>  }
>  
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
> +                          uint32_t maxsz, uint64_t x)
> +{
> +    check_size_align(oprsz, maxsz, dofs);
> +    do_dup(vece, dofs, oprsz, maxsz, NULL, NULL, x);
> +}
> +
>  void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs,
>                        uint32_t oprsz, uint32_t maxsz)
>  {
> 

Reviewed-by: David Hildenbrand <david@redhat.com>

-- 
Thanks,

David / dhildenb

Re: [PATCH 6/7] tcg: Remove tcg_gen_gvec_dup{8,16,32,64}i

[David Hildenbrand]

On 18.04.20 17:04, Richard Henderson wrote:
> These interfaces are now unused.
> 
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  include/tcg/tcg-op-gvec.h |  5 -----
>  tcg/tcg-op-gvec.c         | 28 ----------------------------
>  2 files changed, 33 deletions(-)
> 
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index eb0d47a42b..fa8a0c8d03 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,11 +320,6 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i64);
>  
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t s, uint32_t m, uint8_t x);
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t s, uint32_t m, uint16_t x);
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t s, uint32_t m, uint32_t x);
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t s, uint32_t m, uint64_t x);
> -
>  void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
>                         int64_t shift, uint32_t oprsz, uint32_t maxsz);
>  void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index de16c027b3..5a6cc19812 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1541,34 +1541,6 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>      }
>  }
>  
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint64_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_64, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint32_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_32, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint16_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_16, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint8_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
>  void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
>                            uint32_t maxsz, uint64_t x)
>  {
> 

Reviewed-by: David Hildenbrand <david@redhat.com>

-- 
Thanks,

David / dhildenb

Re: [PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[David Hildenbrand]

On 18.04.20 17:04, Richard Henderson wrote:
> For use when a target needs to pass a configure-specific
> target_ulong value to duplicate.
> 
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  include/tcg/tcg-op-gvec.h | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index fa8a0c8d03..d89f91f40e 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,6 +320,12 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i64);
>  
> +#if TARGET_LONG_BITS == 64
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
> +#else
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
> +#endif
> +

Any user in mind?


-- 
Thanks,

David / dhildenb

Re: [PATCH 1/7] tcg: Add tcg_gen_gvec_dup_imm

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> Add a version of tcg_gen_dup_* that takes both immediate and
> a vector element size operand.  This will replace the set of
> tcg_gen_gvec_dup{8,16,32,64}i functions that encode the element
> size within the function name.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  include/tcg/tcg-op-gvec.h | 2 ++
>  tcg/tcg-op-gvec.c         | 7 +++++++
>  2 files changed, 9 insertions(+)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index 74534e2480..eb0d47a42b 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -313,6 +313,8 @@ void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
>  
>  void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>                            uint32_t s, uint32_t m);
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t s,
> +                          uint32_t m, uint64_t imm);
>  void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i32);
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index 327d9588e0..593bb4542e 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1569,6 +1569,13 @@ void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
>      do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
>  }
>  
> +void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
> +                          uint32_t maxsz, uint64_t x)
> +{
> +    check_size_align(oprsz, maxsz, dofs);
> +    do_dup(vece, dofs, oprsz, maxsz, NULL, NULL, x);
> +}
> +
>  void tcg_gen_gvec_not(unsigned vece, uint32_t dofs, uint32_t aofs,
>                        uint32_t oprsz, uint32_t maxsz)
>  {


-- 
Alex Bennée

Re: [PATCH 2/7] target/s390x: Use tcg_gen_gvec_dup_imm

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> The gen_gvec_dupi switch is unnecessarily with the new function.
> Replace it with a local gen_gvec_dup_imm that takes care of the
> register to offset conversion and length arguments.
>
> Drop zero_vec and use use gen_gvec_dup_imm with 0.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  target/s390x/translate_vx.inc.c | 41 +++++++--------------------------
>  1 file changed, 8 insertions(+), 33 deletions(-)
>
> diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
> index 24558cce80..12347f8a03 100644
> --- a/target/s390x/translate_vx.inc.c
> +++ b/target/s390x/translate_vx.inc.c
> @@ -231,8 +231,8 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
>  #define gen_gvec_mov(v1, v2) \
>      tcg_gen_gvec_mov(0, vec_full_reg_offset(v1), vec_full_reg_offset(v2), 16, \
>                       16)
> -#define gen_gvec_dup64i(v1, c) \
> -    tcg_gen_gvec_dup64i(vec_full_reg_offset(v1), 16, 16, c)
> +#define gen_gvec_dup_imm(es, v1, c) \
> +    tcg_gen_gvec_dup_imm(es, vec_full_reg_offset(v1), 16, 16, c);
>  #define gen_gvec_fn_2(fn, es, v1, v2) \
>      tcg_gen_gvec_##fn(es, vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
>                        16, 16)
> @@ -316,31 +316,6 @@ static void gen_gvec128_4_i64(gen_gvec128_4_i64_fn fn, uint8_t d, uint8_t a,
>          tcg_temp_free_i64(cl);
>  }
>  
> -static void gen_gvec_dupi(uint8_t es, uint8_t reg, uint64_t c)
> -{
> -    switch (es) {
> -    case ES_8:
> -        tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_16:
> -        tcg_gen_gvec_dup16i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_32:
> -        tcg_gen_gvec_dup32i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_64:
> -        gen_gvec_dup64i(reg, c);
> -        break;
> -    default:
> -        g_assert_not_reached();
> -    }
> -}
> -
> -static void zero_vec(uint8_t reg)
> -{
> -    tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, 0);
> -}
> -
>  static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah,
>                            uint64_t b)
>  {
> @@ -396,8 +371,8 @@ static DisasJumpType op_vgbm(DisasContext *s, DisasOps *o)
>           * Masks for both 64 bit elements of the vector are the same.
>           * Trust tcg to produce a good constant loading.
>           */
> -        gen_gvec_dup64i(get_field(s, v1),
> -                        generate_byte_mask(i2 & 0xff));
> +        gen_gvec_dup_imm(ES_64, get_field(s, v1),
> +                         generate_byte_mask(i2 & 0xff));
>      } else {
>          TCGv_i64 t = tcg_temp_new_i64();
>  
> @@ -432,7 +407,7 @@ static DisasJumpType op_vgm(DisasContext *s, DisasOps *o)
>          }
>      }
>  
> -    gen_gvec_dupi(es, get_field(s, v1), mask);
> +    gen_gvec_dup_imm(es, get_field(s, v1), mask);
>      return DISAS_NEXT;
>  }
>  
> @@ -585,7 +560,7 @@ static DisasJumpType op_vllez(DisasContext *s, DisasOps *o)
>  
>      t = tcg_temp_new_i64();
>      tcg_gen_qemu_ld_i64(t, o->addr1, get_mem_index(s), MO_TE | es);
> -    zero_vec(get_field(s, v1));
> +    gen_gvec_dup_imm(es, get_field(s, v1), 0);
>      write_vec_element_i64(t, get_field(s, v1), enr, es);
>      tcg_temp_free_i64(t);
>      return DISAS_NEXT;
> @@ -892,7 +867,7 @@ static DisasJumpType op_vrepi(DisasContext *s, DisasOps *o)
>          return DISAS_NORETURN;
>      }
>  
> -    gen_gvec_dupi(es, get_field(s, v1), data);
> +    gen_gvec_dup_imm(es, get_field(s, v1), data);
>      return DISAS_NEXT;
>  }
>  
> @@ -1372,7 +1347,7 @@ static DisasJumpType op_vcksm(DisasContext *s, DisasOps *o)
>          read_vec_element_i32(tmp, get_field(s, v2), i, ES_32);
>          tcg_gen_add2_i32(tmp, sum, sum, sum, tmp, tmp);
>      }
> -    zero_vec(get_field(s, v1));
> +    gen_gvec_dup_imm(ES_32, get_field(s, v1), 0);
>      write_vec_element_i32(sum, get_field(s, v1), 1, ES_32);
>  
>      tcg_temp_free_i32(tmp);


-- 
Alex Bennée

Re: [PATCH 2/7] target/s390x: Use tcg_gen_gvec_dup_imm

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> The gen_gvec_dupi switch is unnecessarily with the new function.
> Replace it with a local gen_gvec_dup_imm that takes care of the
> register to offset conversion and length arguments.
>
> Drop zero_vec and use use gen_gvec_dup_imm with 0.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  target/s390x/translate_vx.inc.c | 41 +++++++--------------------------
>  1 file changed, 8 insertions(+), 33 deletions(-)
>
> diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
> index 24558cce80..12347f8a03 100644
> --- a/target/s390x/translate_vx.inc.c
> +++ b/target/s390x/translate_vx.inc.c
> @@ -231,8 +231,8 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
>  #define gen_gvec_mov(v1, v2) \
>      tcg_gen_gvec_mov(0, vec_full_reg_offset(v1), vec_full_reg_offset(v2), 16, \
>                       16)
> -#define gen_gvec_dup64i(v1, c) \
> -    tcg_gen_gvec_dup64i(vec_full_reg_offset(v1), 16, 16, c)
> +#define gen_gvec_dup_imm(es, v1, c) \
> +    tcg_gen_gvec_dup_imm(es, vec_full_reg_offset(v1), 16, 16, c);
>  #define gen_gvec_fn_2(fn, es, v1, v2) \
>      tcg_gen_gvec_##fn(es, vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
>                        16, 16)
> @@ -316,31 +316,6 @@ static void gen_gvec128_4_i64(gen_gvec128_4_i64_fn fn, uint8_t d, uint8_t a,
>          tcg_temp_free_i64(cl);
>  }
>  
> -static void gen_gvec_dupi(uint8_t es, uint8_t reg, uint64_t c)
> -{
> -    switch (es) {
> -    case ES_8:
> -        tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_16:
> -        tcg_gen_gvec_dup16i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_32:
> -        tcg_gen_gvec_dup32i(vec_full_reg_offset(reg), 16, 16, c);
> -        break;
> -    case ES_64:
> -        gen_gvec_dup64i(reg, c);
> -        break;
> -    default:
> -        g_assert_not_reached();
> -    }
> -}
> -
> -static void zero_vec(uint8_t reg)
> -{
> -    tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, 0);
> -}
> -
>  static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah,
>                            uint64_t b)
>  {
> @@ -396,8 +371,8 @@ static DisasJumpType op_vgbm(DisasContext *s, DisasOps *o)
>           * Masks for both 64 bit elements of the vector are the same.
>           * Trust tcg to produce a good constant loading.
>           */
> -        gen_gvec_dup64i(get_field(s, v1),
> -                        generate_byte_mask(i2 & 0xff));
> +        gen_gvec_dup_imm(ES_64, get_field(s, v1),
> +                         generate_byte_mask(i2 & 0xff));
>      } else {
>          TCGv_i64 t = tcg_temp_new_i64();
>  
> @@ -432,7 +407,7 @@ static DisasJumpType op_vgm(DisasContext *s, DisasOps *o)
>          }
>      }
>  
> -    gen_gvec_dupi(es, get_field(s, v1), mask);
> +    gen_gvec_dup_imm(es, get_field(s, v1), mask);
>      return DISAS_NEXT;
>  }
>  
> @@ -585,7 +560,7 @@ static DisasJumpType op_vllez(DisasContext *s, DisasOps *o)
>  
>      t = tcg_temp_new_i64();
>      tcg_gen_qemu_ld_i64(t, o->addr1, get_mem_index(s), MO_TE | es);
> -    zero_vec(get_field(s, v1));
> +    gen_gvec_dup_imm(es, get_field(s, v1), 0);
>      write_vec_element_i64(t, get_field(s, v1), enr, es);
>      tcg_temp_free_i64(t);
>      return DISAS_NEXT;
> @@ -892,7 +867,7 @@ static DisasJumpType op_vrepi(DisasContext *s, DisasOps *o)
>          return DISAS_NORETURN;
>      }
>  
> -    gen_gvec_dupi(es, get_field(s, v1), data);
> +    gen_gvec_dup_imm(es, get_field(s, v1), data);
>      return DISAS_NEXT;
>  }
>  
> @@ -1372,7 +1347,7 @@ static DisasJumpType op_vcksm(DisasContext *s, DisasOps *o)
>          read_vec_element_i32(tmp, get_field(s, v2), i, ES_32);
>          tcg_gen_add2_i32(tmp, sum, sum, sum, tmp, tmp);
>      }
> -    zero_vec(get_field(s, v1));
> +    gen_gvec_dup_imm(ES_32, get_field(s, v1), 0);
>      write_vec_element_i32(sum, get_field(s, v1), 1, ES_32);
>  
>      tcg_temp_free_i32(tmp);


-- 
Alex Bennée

Re: [PATCH 3/7] target/ppc: Use tcg_gen_gvec_dup_imm

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> We can now unify the implementation of the 3 VSPLTI instructions.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/ppc/translate/vmx-impl.inc.c | 32 ++++++++++++++++-------------
>  target/ppc/translate/vsx-impl.inc.c |  2 +-
>  2 files changed, 19 insertions(+), 15 deletions(-)
>
> diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c
> index 81d5a7a341..403ed3a01c 100644
> --- a/target/ppc/translate/vmx-impl.inc.c
> +++ b/target/ppc/translate/vmx-impl.inc.c
> @@ -1035,21 +1035,25 @@ GEN_VXRFORM_DUAL(vcmpbfp, PPC_ALTIVEC, PPC_NONE, \
>  GEN_VXRFORM_DUAL(vcmpgtfp, PPC_ALTIVEC, PPC_NONE, \
>                   vcmpgtud, PPC_NONE, PPC2_ALTIVEC_207)
>  
> -#define GEN_VXFORM_DUPI(name, tcg_op, opc2, opc3)                       \
> -static void glue(gen_, name)(DisasContext *ctx)                         \
> -    {                                                                   \
> -        int simm;                                                       \
> -        if (unlikely(!ctx->altivec_enabled)) {                          \
> -            gen_exception(ctx, POWERPC_EXCP_VPU);                       \
> -            return;                                                     \
> -        }                                                               \
> -        simm = SIMM5(ctx->opcode);                                      \
> -        tcg_op(avr_full_offset(rD(ctx->opcode)), 16, 16, simm);         \
> +static void gen_vsplti(DisasContext *ctx, int vece)
> +{
> +    int simm;
> +
> +    if (unlikely(!ctx->altivec_enabled)) {
> +        gen_exception(ctx, POWERPC_EXCP_VPU);
> +        return;
>      }
>  
> -GEN_VXFORM_DUPI(vspltisb, tcg_gen_gvec_dup8i, 6, 12);
> -GEN_VXFORM_DUPI(vspltish, tcg_gen_gvec_dup16i, 6, 13);
> -GEN_VXFORM_DUPI(vspltisw, tcg_gen_gvec_dup32i, 6, 14);
> +    simm = SIMM5(ctx->opcode);
> +    tcg_gen_gvec_dup_imm(vece, avr_full_offset(rD(ctx->opcode)), 16, 16, simm);
> +}
> +
> +#define GEN_VXFORM_VSPLTI(name, vece, opc2, opc3) \
> +static void glue(gen_, name)(DisasContext *ctx) { gen_vsplti(ctx, vece); }
> +
> +GEN_VXFORM_VSPLTI(vspltisb, MO_8, 6, 12);
> +GEN_VXFORM_VSPLTI(vspltish, MO_16, 6, 13);
> +GEN_VXFORM_VSPLTI(vspltisw, MO_32, 6, 14);

There are unused parameters opc2/opc3 parameters here. Given that is it
really worth the glue obfuscation:

  static void gen_vspltisb(DisasContext *ctx)
  {
      gen_vsplti(ctx, MO_8);
  }

  static void gen_vspltish(DisasContext *ctx)
  {
      gen_vsplti(ctx, MO_8);
  }

  static void gen_vspltisw(DisasContext *ctx)
  {
      gen_vsplti(ctx, MO_8);
  }

Of course I tried grepping for their use and couldn't find them until I
realised the call to them was hidden inside another glue operation.

With the removed extra unused macro params:

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>


>  
>  #define GEN_VXFORM_NOA(name, opc2, opc3)                                \
>  static void glue(gen_, name)(DisasContext *ctx)                         \
> @@ -1559,7 +1563,7 @@ GEN_VXFORM_DUAL(vsldoi, PPC_ALTIVEC, PPC_NONE,
>  #undef GEN_VXRFORM_DUAL
>  #undef GEN_VXRFORM1
>  #undef GEN_VXRFORM
> -#undef GEN_VXFORM_DUPI
> +#undef GEN_VXFORM_VSPLTI
>  #undef GEN_VXFORM_NOA
>  #undef GEN_VXFORM_UIMM
>  #undef GEN_VAFORM_PAIRED
> diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c
> index 8287e272f5..b518de46db 100644
> --- a/target/ppc/translate/vsx-impl.inc.c
> +++ b/target/ppc/translate/vsx-impl.inc.c
> @@ -1579,7 +1579,7 @@ static void gen_xxspltib(DisasContext *ctx)
>              return;
>          }
>      }
> -    tcg_gen_gvec_dup8i(vsr_full_offset(rt), 16, 16, uim8);
> +    tcg_gen_gvec_dup_imm(MO_8, vsr_full_offset(rt), 16, 16, uim8);
>  }
>  
>  static void gen_xxsldwi(DisasContext *ctx)


-- 
Alex Bennée

Re: [PATCH 4/7] target/arm: Use tcg_gen_gvec_dup_imm

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> In a few cases, we're able to remove some manual replication.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  target/arm/translate-a64.c | 10 +++++-----
>  target/arm/translate-sve.c | 12 +++++-------
>  target/arm/translate.c     |  9 ++++++---
>  3 files changed, 16 insertions(+), 15 deletions(-)
>
> diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
> index 7580e46367..095638e09a 100644
> --- a/target/arm/translate-a64.c
> +++ b/target/arm/translate-a64.c
> @@ -519,7 +519,7 @@ static void clear_vec_high(DisasContext *s, bool is_q, int rd)
>          tcg_temp_free_i64(tcg_zero);
>      }
>      if (vsz > 16) {
> -        tcg_gen_gvec_dup8i(ofs + 16, vsz - 16, vsz - 16, 0);
> +        tcg_gen_gvec_dup_imm(MO_64, ofs + 16, vsz - 16, vsz - 16, 0);
>      }
>  }
>  
> @@ -7794,8 +7794,8 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
>  
>      if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) {
>          /* MOVI or MVNI, with MVNI negation handled above.  */
> -        tcg_gen_gvec_dup64i(vec_full_reg_offset(s, rd), is_q ? 16 : 8,
> -                            vec_full_reg_size(s), imm);
> +        tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), is_q ? 16 : 8,
> +                             vec_full_reg_size(s), imm);
>      } else {
>          /* ORR or BIC, with BIC negation to AND handled above.  */
>          if (is_neg) {
> @@ -10223,8 +10223,8 @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
>          if (is_u) {
>              if (shift == 8 << size) {
>                  /* Shift count the same size as element size produces zero.  */
> -                tcg_gen_gvec_dup8i(vec_full_reg_offset(s, rd),
> -                                   is_q ? 16 : 8, vec_full_reg_size(s), 0);
> +                tcg_gen_gvec_dup_imm(size, vec_full_reg_offset(s, rd),
> +                                     is_q ? 16 : 8, vec_full_reg_size(s), 0);
>              } else {
>                  gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shri, size);
>              }
> diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
> index b35bad245e..6c8bda4e4c 100644
> --- a/target/arm/translate-sve.c
> +++ b/target/arm/translate-sve.c
> @@ -177,7 +177,7 @@ static bool do_mov_z(DisasContext *s, int rd, int rn)
>  static void do_dupi_z(DisasContext *s, int rd, uint64_t word)
>  {
>      unsigned vsz = vec_full_reg_size(s);
> -    tcg_gen_gvec_dup64i(vec_full_reg_offset(s, rd), vsz, vsz, word);
> +    tcg_gen_gvec_dup_imm(MO_64, vec_full_reg_offset(s, rd), vsz, vsz, word);
>  }
>  
>  /* Invoke a vector expander on two Pregs.  */
> @@ -1453,7 +1453,7 @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag)
>          unsigned oprsz = size_for_gvec(setsz / 8);
>  
>          if (oprsz * 8 == setsz) {
> -            tcg_gen_gvec_dup64i(ofs, oprsz, maxsz, word);
> +            tcg_gen_gvec_dup_imm(MO_64, ofs, oprsz, maxsz, word);
>              goto done;
>          }
>      }
> @@ -2044,7 +2044,7 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
>              unsigned nofs = vec_reg_offset(s, a->rn, index, esz);
>              tcg_gen_gvec_dup_mem(esz, dofs, nofs, vsz, vsz);
>          } else {
> -            tcg_gen_gvec_dup64i(dofs, vsz, vsz, 0);
> +            tcg_gen_gvec_dup_imm(esz, dofs, vsz, vsz, 0);
>          }
>      }
>      return true;
> @@ -3260,9 +3260,7 @@ static bool trans_FDUP(DisasContext *s, arg_FDUP *a)
>  
>          /* Decode the VFP immediate.  */
>          imm = vfp_expand_imm(a->esz, a->imm);
> -        imm = dup_const(a->esz, imm);
> -
> -        tcg_gen_gvec_dup64i(dofs, vsz, vsz, imm);
> +        tcg_gen_gvec_dup_imm(a->esz, dofs, vsz, vsz, imm);
>      }
>      return true;
>  }
> @@ -3276,7 +3274,7 @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a)
>          unsigned vsz = vec_full_reg_size(s);
>          int dofs = vec_full_reg_offset(s, a->rd);
>  
> -        tcg_gen_gvec_dup64i(dofs, vsz, vsz, dup_const(a->esz, a->imm));
> +        tcg_gen_gvec_dup_imm(a->esz, dofs, vsz, vsz, a->imm);
>      }
>      return true;
>  }
> diff --git a/target/arm/translate.c b/target/arm/translate.c
> index 9f9f4e19e0..af4d3ff4c9 100644
> --- a/target/arm/translate.c
> +++ b/target/arm/translate.c
> @@ -5386,7 +5386,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
>                                            MIN(shift, (8 << size) - 1),
>                                            vec_size, vec_size);
>                      } else if (shift >= 8 << size) {
> -                        tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0);
> +                        tcg_gen_gvec_dup_imm(MO_8, rd_ofs, vec_size,
> +                                             vec_size, 0);
>                      } else {
>                          tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift,
>                                            vec_size, vec_size);
> @@ -5437,7 +5438,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
>                           * architecturally valid and results in zero.
>                           */
>                          if (shift >= 8 << size) {
> -                            tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0);
> +                            tcg_gen_gvec_dup_imm(size, rd_ofs,
> +                                                 vec_size, vec_size, 0);
>                          } else {
>                              tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift,
>                                                vec_size, vec_size);
> @@ -5783,7 +5785,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
>                      }
>                      tcg_temp_free_i64(t64);
>                  } else {
> -                    tcg_gen_gvec_dup32i(reg_ofs, vec_size, vec_size, imm);
> +                    tcg_gen_gvec_dup_imm(MO_32, reg_ofs, vec_size,
> +                                         vec_size, imm);
>                  }
>              }
>          }


-- 
Alex Bennée

Re: [PATCH 5/7] tcg: Use tcg_gen_gvec_dup_imm in logical simplifications

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> Replace the outgoing interface.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  tcg/tcg-op-gvec.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index 593bb4542e..de16c027b3 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -2326,7 +2326,7 @@ void tcg_gen_gvec_xor(unsigned vece, uint32_t dofs, uint32_t aofs,
>      };
>  
>      if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
>      } else {
>          tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>      }
> @@ -2343,7 +2343,7 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs,
>      };
>  
>      if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, 0);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, 0);
>      } else {
>          tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>      }
> @@ -2360,7 +2360,7 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs,
>      };
>  
>      if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
>      } else {
>          tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>      }
> @@ -2411,7 +2411,7 @@ void tcg_gen_gvec_eqv(unsigned vece, uint32_t dofs, uint32_t aofs,
>      };
>  
>      if (aofs == bofs) {
> -        tcg_gen_gvec_dup8i(dofs, oprsz, maxsz, -1);
> +        tcg_gen_gvec_dup_imm(MO_64, dofs, oprsz, maxsz, -1);
>      } else {
>          tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g);
>      }


-- 
Alex Bennée

Re: [PATCH 6/7] tcg: Remove tcg_gen_gvec_dup{8,16,32,64}i

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> These interfaces are now unused.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  include/tcg/tcg-op-gvec.h |  5 -----
>  tcg/tcg-op-gvec.c         | 28 ----------------------------
>  2 files changed, 33 deletions(-)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index eb0d47a42b..fa8a0c8d03 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,11 +320,6 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i64);
>  
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t s, uint32_t m, uint8_t x);
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t s, uint32_t m, uint16_t x);
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t s, uint32_t m, uint32_t x);
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t s, uint32_t m, uint64_t x);
> -
>  void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
>                         int64_t shift, uint32_t oprsz, uint32_t maxsz);
>  void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
> diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
> index de16c027b3..5a6cc19812 100644
> --- a/tcg/tcg-op-gvec.c
> +++ b/tcg/tcg-op-gvec.c
> @@ -1541,34 +1541,6 @@ void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs,
>      }
>  }
>  
> -void tcg_gen_gvec_dup64i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint64_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_64, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup32i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint32_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_32, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup16i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint16_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_16, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
> -void tcg_gen_gvec_dup8i(uint32_t dofs, uint32_t oprsz,
> -                         uint32_t maxsz, uint8_t x)
> -{
> -    check_size_align(oprsz, maxsz, dofs);
> -    do_dup(MO_8, dofs, oprsz, maxsz, NULL, NULL, x);
> -}
> -
>  void tcg_gen_gvec_dup_imm(unsigned vece, uint32_t dofs, uint32_t oprsz,
>                            uint32_t maxsz, uint64_t x)
>  {


-- 
Alex Bennée

Re: [PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[Alex Bennée]

Richard Henderson <richard.henderson@linaro.org> writes:

> For use when a target needs to pass a configure-specific
> target_ulong value to duplicate.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

> ---
>  include/tcg/tcg-op-gvec.h | 6 ++++++
>  1 file changed, 6 insertions(+)
>
> diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
> index fa8a0c8d03..d89f91f40e 100644
> --- a/include/tcg/tcg-op-gvec.h
> +++ b/include/tcg/tcg-op-gvec.h
> @@ -320,6 +320,12 @@ void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s,
>  void tcg_gen_gvec_dup_i64(unsigned vece, uint32_t dofs, uint32_t s,
>                            uint32_t m, TCGv_i64);
>  
> +#if TARGET_LONG_BITS == 64
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
> +#else
> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
> +#endif
> +
>  void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
>                         int64_t shift, uint32_t oprsz, uint32_t maxsz);
>  void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,


-- 
Alex Bennée

Re: [PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[Richard Henderson]

On 4/20/20 12:30 AM, David Hildenbrand wrote:
>> +#if TARGET_LONG_BITS == 64
>> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
>> +#else
>> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
>> +#endif
>> +
> 
> Any user in mind?

riscv -- the in-progress patches have some ifdefs that could be avoided.


r~

Re: [PATCH 7/7] tcg: Add tcg_gen_gvec_dup_tl

[David Hildenbrand]

On 20.04.20 16:52, Richard Henderson wrote:
> On 4/20/20 12:30 AM, David Hildenbrand wrote:
>>> +#if TARGET_LONG_BITS == 64
>>> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i64
>>> +#else
>>> +# define tcg_gen_gvec_dup_tl  tcg_gen_gvec_dup_i32
>>> +#endif
>>> +
>>
>> Any user in mind?
> 
> riscv -- the in-progress patches have some ifdefs that could be avoided.
> 

Perfect

Reviewed-by: David Hildenbrand <david@redhat.com>


-- 
Thanks,

David / dhildenb

Re: [PATCH 3/7] target/ppc: Use tcg_gen_gvec_dup_imm

[Richard Henderson]

On 4/20/20 3:34 AM, Alex Bennée wrote:
>> +GEN_VXFORM_VSPLTI(vspltisb, MO_8, 6, 12);
>> +GEN_VXFORM_VSPLTI(vspltish, MO_16, 6, 13);
>> +GEN_VXFORM_VSPLTI(vspltisw, MO_32, 6, 14);
> 
> There are unused parameters opc2/opc3 parameters here.

Yes, but all of the other GEN_* macros retain them as well.
Without looking at the actual history, I'd say once upon a time they were
actually used, but we've now split opcode from implementation.

> With the removed extra unused macro params:
> 
> Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

I wouldn't do that without David's approval.  And possibly stripping out the
opcodes everywhere else.


r~

Re: [PATCH 3/7] target/ppc: Use tcg_gen_gvec_dup_imm

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 1093 bytes --]

On Tue, Apr 21, 2020 at 10:50:25AM -0700, Richard Henderson wrote:
> On 4/20/20 3:34 AM, Alex Bennée wrote:
> >> +GEN_VXFORM_VSPLTI(vspltisb, MO_8, 6, 12);
> >> +GEN_VXFORM_VSPLTI(vspltish, MO_16, 6, 13);
> >> +GEN_VXFORM_VSPLTI(vspltisw, MO_32, 6, 14);
> > 
> > There are unused parameters opc2/opc3 parameters here.
> 
> Yes, but all of the other GEN_* macros retain them as well.
> Without looking at the actual history, I'd say once upon a time they were
> actually used, but we've now split opcode from implementation.
> 
> > With the removed extra unused macro params:
> > 
> > Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
> 
> I wouldn't do that without David's approval.  And possibly stripping out the
> opcodes everywhere else.

Yeah.  Sounds like one of a nearly infinite number of global cleanups
that the target-ppc tcg code could do with.  Patches welcome.

-- 
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 --]