i386: Fix wrong optimization for consecutive masked scatters [PR 101472]

gcc/ChangeLog:

	PR target/101472
	* config/i386/sse.md: (<avx512>scattersi<mode>): Add mask operand to
	UNSPEC_VSIBADDR.
	(<avx512>scattersi<mode>): Likewise.
	(*avx512f_scattersi<VI48F:mode>): Merge mask operand to set_dest.
	(*avx512f_scatterdi<VI48F:mode>): Likewise

gcc/testsuite/ChangeLog:

	PR target/101472
	* gcc.target/i386/avx512f-pr101472.c: New test.
	* gcc.target/i386/avx512vl-pr101472.c: New test.

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 0ca322996ce790bf9483479e07f6fa38e8f4a417..ac0c46328f20736ceacb444cf76ecb2f92c0a151 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -24205,8 +24205,9 @@
   "TARGET_AVX512F"
 {
   operands[5]
-    = gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[0], operands[2],
-                                       operands[4]), UNSPEC_VSIBADDR);
+    = gen_rtx_UNSPEC (Pmode, gen_rtvec (4, operands[0], operands[2],
+                                       operands[4], operands[1]),
+                                       UNSPEC_VSIBADDR);
 })
 
 (define_insn "*avx512f_scattersi<VI48F:mode>"
@@ -24214,10 +24215,11 @@
          [(unspec:P
             [(match_operand:P 0 "vsib_address_operand" "Tv")
              (match_operand:<VEC_GATHER_IDXSI> 2 "register_operand" "v")
-             (match_operand:SI 4 "const1248_operand" "n")]
+             (match_operand:SI 4 "const1248_operand" "n")
+             (match_operand:<avx512fmaskmode> 6 "register_operand" "1")]
             UNSPEC_VSIBADDR)])
        (unspec:VI48F
-         [(match_operand:<avx512fmaskmode> 6 "register_operand" "1")
+         [(match_dup 6)
           (match_operand:VI48F 3 "register_operand" "v")]
          UNSPEC_SCATTER))
    (clobber (match_scratch:<avx512fmaskmode> 1 "=&Yk"))]
@@ -24243,8 +24245,9 @@
   "TARGET_AVX512F"
 {
   operands[5]
-    = gen_rtx_UNSPEC (Pmode, gen_rtvec (3, operands[0], operands[2],
-                                       operands[4]), UNSPEC_VSIBADDR);
+    = gen_rtx_UNSPEC (Pmode, gen_rtvec (4, operands[0], operands[2],
+                                       operands[4], operands[1]),
+                                       UNSPEC_VSIBADDR);
 })
 
 (define_insn "*avx512f_scatterdi<VI48F:mode>"
@@ -24252,10 +24255,11 @@
          [(unspec:P
             [(match_operand:P 0 "vsib_address_operand" "Tv")
              (match_operand:<VEC_GATHER_IDXDI> 2 "register_operand" "v")
-             (match_operand:SI 4 "const1248_operand" "n")]
+             (match_operand:SI 4 "const1248_operand" "n")
+             (match_operand:QI 6 "register_operand" "1")]
             UNSPEC_VSIBADDR)])
        (unspec:VI48F
-         [(match_operand:QI 6 "register_operand" "1")
+         [(match_dup 6)
           (match_operand:<VEC_GATHER_SRCDI> 3 "register_operand" "v")]
          UNSPEC_SCATTER))
    (clobber (match_scratch:QI 1 "=&Yk"))]

diff --git a/gcc/testsuite/gcc.target/i386/avx512f-pr101472.c b/gcc/testsuite/gcc.target/i386/avx512f-pr101472.c
new file mode 100644 (file)
index 0000000..89c6603
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-pr101472.c
@@ -0,0 +1,49 @@
+/* PR target/101472 */
+/* { dg-do compile } */
+/* { dg-options "-mavx512f -O2" } */
+/* { dg-final { scan-assembler-times "vpscatterqd\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdd\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterqq\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdq\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqps\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdps\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqpd\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*zmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdpd\[ \\t\]+\[^\{\n\]*zmm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+
+#include <immintrin.h>
+
+void two_scatters_epi32(void* addr, __mmask8 k1, __mmask8 k2, __m512i vindex, 
+                        __m256i a, __m512i b)
+{
+    _mm512_mask_i64scatter_epi32(addr, k1, vindex, a, 1);
+    _mm512_mask_i64scatter_epi32(addr, k2, vindex, a, 1);
+    _mm512_mask_i32scatter_epi32(addr, k1, vindex, b, 1);
+    _mm512_mask_i32scatter_epi32(addr, k2, vindex, b, 1);
+}
+
+void two_scatters_epi64(void* addr, __mmask8 k1, __mmask8 k2, __m512i vindex, 
+                        __m256i idx, __m512i a)
+{
+    _mm512_mask_i64scatter_epi64(addr, k1, vindex, a, 1);
+    _mm512_mask_i64scatter_epi64(addr, k2, vindex, a, 1);
+    _mm512_mask_i32scatter_epi64(addr, k1, idx, a, 1);
+    _mm512_mask_i32scatter_epi64(addr, k2, idx, a, 1);
+}
+
+void two_scatters_ps(void* addr, __mmask8 k1, __mmask8 k2, __m512i vindex, 
+                     __m256 a, __m512 b)
+{
+    _mm512_mask_i64scatter_ps(addr, k1, vindex, a, 1);
+    _mm512_mask_i64scatter_ps(addr, k2, vindex, a, 1);
+    _mm512_mask_i32scatter_ps(addr, k1, vindex, b, 1);
+    _mm512_mask_i32scatter_ps(addr, k2, vindex, b, 1);
+}
+
+void two_scatters_pd(void* addr, __mmask8 k1, __mmask8 k2, __m512i vindex, 
+                     __m256i idx, __m512d a)
+{
+    _mm512_mask_i64scatter_pd(addr, k1, vindex, a, 1);
+    _mm512_mask_i64scatter_pd(addr, k2, vindex, a, 1);
+    _mm512_mask_i32scatter_pd(addr, k1, idx, a, 1);
+    _mm512_mask_i32scatter_pd(addr, k2, idx, a, 1);
+}

diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr101472.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr101472.c
new file mode 100644 (file)
index 0000000..6df59a2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr101472.c
@@ -0,0 +1,79 @@
+/* PR target/101472 */
+/* { dg-do compile } */
+/* { dg-options "-mavx512vl -O2" } */
+/* { dg-final { scan-assembler-times "vpscatterqd\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterqd\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdd\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdd\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterqq\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterqq\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdq\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpscatterdq\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqps\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqps\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdps\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdps\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqpd\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterqpd\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*ymm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdpd\[ \\t\]+\[^\{\n\]*xmm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vscatterdpd\[ \\t\]+\[^\{\n\]*ymm\[0-9\]\[^\n\]*xmm\[0-9\]\[^\n\]*{%k\[1-7\]}(?:\n|\[ \\t\]+#)" 2 } } */
+
+
+#include <immintrin.h>
+
+void two_scatters_epi32(void* addr, __mmask8 k1, __mmask8 k2, __m128i vindex1, 
+                        __m256i vindex2, __m128i src_epi32, 
+                        __m256i src_i32_epi32)
+{
+    _mm_mask_i64scatter_epi32(addr, k1, vindex1, src_epi32, 1);
+    _mm_mask_i64scatter_epi32(addr, k2, vindex1, src_epi32, 1);
+    _mm256_mask_i64scatter_epi32(addr, k1, vindex2, src_epi32, 1);
+    _mm256_mask_i64scatter_epi32(addr, k2, vindex2, src_epi32, 1);
+
+    _mm_mask_i32scatter_epi32(addr, k1, vindex1, src_epi32, 1);
+    _mm_mask_i32scatter_epi32(addr, k2, vindex1, src_epi32, 1);
+    _mm256_mask_i32scatter_epi32(addr, k1, vindex2, src_i32_epi32, 1);
+    _mm256_mask_i32scatter_epi32(addr, k2, vindex2, src_i32_epi32, 1);
+}
+
+void two_scatters_epi64(void* addr, __mmask8 k1, __mmask8 k2, __m128i vindex1, 
+                        __m256i vindex2, __m128i src_epi64_mm, 
+                        __m256i src_epi64)
+{
+    _mm_mask_i64scatter_epi64(addr, k1, vindex1, src_epi64_mm, 1);
+    _mm_mask_i64scatter_epi64(addr, k2, vindex1, src_epi64_mm, 1);
+    _mm256_mask_i64scatter_epi64(addr, k1, vindex2, src_epi64, 1);
+    _mm256_mask_i64scatter_epi64(addr, k2, vindex2, src_epi64, 1);
+
+    _mm_mask_i32scatter_epi64(addr, k1, vindex1, src_epi64_mm, 8);
+    _mm_mask_i32scatter_epi64(addr, k2, vindex1, src_epi64_mm, 8);
+    _mm256_mask_i32scatter_epi64(addr, k1, vindex1, src_epi64, 1);
+    _mm256_mask_i32scatter_epi64(addr, k2, vindex1, src_epi64, 1);
+}
+void two_scatters_ps(void* addr, __mmask8 k1, __mmask8 k2, __m128i vindex1, 
+                     __m256i vindex2, __m128 src_ps, __m256 src_i32_ps)
+{
+    _mm_mask_i64scatter_ps(addr, k1, vindex1, src_ps, 1);
+    _mm_mask_i64scatter_ps(addr, k2, vindex1, src_ps, 1);
+    _mm256_mask_i64scatter_ps(addr, k1, vindex2, src_ps, 1);
+    _mm256_mask_i64scatter_ps(addr, k2, vindex2, src_ps, 1);
+
+    _mm_mask_i32scatter_ps(addr, k1, vindex1, src_ps, 8);
+    _mm_mask_i32scatter_ps(addr, k2, vindex1, src_ps, 8);
+    _mm256_mask_i32scatter_ps(addr, k1, vindex2, src_i32_ps, 1);
+    _mm256_mask_i32scatter_ps(addr, k2, vindex2, src_i32_ps, 1);
+}
+
+void two_scatters_pd(void* addr, __mmask8 k1, __mmask8 k2,  __m128i vindex1,
+                     __m256i vindex2, __m128d src_pd_mm, __m256d src_pd)
+{
+    _mm_mask_i64scatter_pd(addr, k1, vindex1, src_pd_mm, 1);
+    _mm_mask_i64scatter_pd(addr, k2, vindex1, src_pd_mm, 1);
+    _mm256_mask_i64scatter_pd(addr, k1, vindex2, src_pd, 1);
+    _mm256_mask_i64scatter_pd(addr, k2, vindex2, src_pd, 1);
+
+    _mm_mask_i32scatter_pd(addr, k1, vindex1, src_pd_mm, 8);
+    _mm_mask_i32scatter_pd(addr, k2, vindex1, src_pd_mm, 8);
+    _mm256_mask_i32scatter_pd(addr, k1, vindex1, src_pd, 1);
+    _mm256_mask_i32scatter_pd(addr, k2, vindex1, src_pd, 1);
+}