Hi!
The vinsert[if]64x2 instructions are AVX512VL & AVX512DQ, so
if only AVX512VL is on, we should emit the other insns - 32x4,
which without masking do the same thing.
With masking, we have to require TARGET_AVX512DQ.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2016-05-18 Jakub Jelinek <ja...@redhat.com>
* config/i386/sse.md (vec_set_lo_<mode><mask_name>,
vec_set_hi_<mode><mask_name>): Add && <mask_avx512dq_condition>
condition. For !TARGET_AVX512DQ, emit 32x4 instruction instead
of 64x2.
* gcc.target/i386/avx512dq-vinsert-1.c: New test.
* gcc.target/i386/avx512vl-vinsert-1.c: New test.
--- gcc/config/i386/sse.md.jj 2016-05-18 15:02:54.000000000 +0200
+++ gcc/config/i386/sse.md 2016-05-18 15:54:20.944236472 +0200
@@ -17823,10 +17823,12 @@ (define_insn "vec_set_lo_<mode><mask_nam
(vec_select:<ssehalfvecmode>
(match_operand:VI8F_256 1 "register_operand" "v")
(parallel [(const_int 2) (const_int 3)]))))]
- "TARGET_AVX"
+ "TARGET_AVX && <mask_avx512dq_condition>"
{
- if (TARGET_AVX512VL)
+ if (TARGET_AVX512DQ)
return "vinsert<shuffletype>64x2\t{$0x0, %2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2, 0x0}";
+ else if (TARGET_AVX512VL)
+ return "vinsert<shuffletype>32x4\t{$0x0, %2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2, 0x0}";
else
return "vinsert<i128>\t{$0x0, %2, %1, %0|%0, %1, %2, 0x0}";
}
@@ -17843,10 +17845,12 @@ (define_insn "vec_set_hi_<mode><mask_nam
(match_operand:VI8F_256 1 "register_operand" "v")
(parallel [(const_int 0) (const_int 1)]))
(match_operand:<ssehalfvecmode> 2 "nonimmediate_operand" "vm")))]
- "TARGET_AVX"
+ "TARGET_AVX && <mask_avx512dq_condition>"
{
- if (TARGET_AVX512VL)
+ if (TARGET_AVX512DQ)
return "vinsert<shuffletype>64x2\t{$0x1, %2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2, 0x1}";
+ else if (TARGET_AVX512VL)
+ return "vinsert<shuffletype>32x4\t{$0x1, %2, %1,
%0<mask_operand3>|%0<mask_operand3>, %1, %2, 0x1}";
else
return "vinsert<i128>\t{$0x1, %2, %1, %0|%0, %1, %2, 0x1}";
}
--- gcc/testsuite/gcc.target/i386/avx512dq-vinsert-1.c.jj 2016-05-18
16:08:48.572351388 +0200
+++ gcc/testsuite/gcc.target/i386/avx512dq-vinsert-1.c 2016-05-18
16:09:18.114947627 +0200
@@ -0,0 +1,100 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512vl -mavx512dq -masm=att" } */
+
+typedef int V1 __attribute__((vector_size (32)));
+typedef long long V2 __attribute__((vector_size (32)));
+typedef float V3 __attribute__((vector_size (32)));
+typedef double V4 __attribute__((vector_size (32)));
+
+void
+f1 (V1 x, int y)
+{
+ register V1 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f2 (V1 x, int y)
+{
+ register V1 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[6] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f3 (V2 x, long long y)
+{
+ register V2 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[1] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f4 (V2 x, long long y)
+{
+ register V2 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f5 (V3 x, float y)
+{
+ register V3 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f6 (V3 x, float y)
+{
+ register V3 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[6] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f7 (V4 x, double y)
+{
+ register V4 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[1] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f8 (V4 x, double y)
+{
+ register V4 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vinserti32x4\[^\n\r]*0x0\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinserti32x4\[^\n\r]*0x1\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinsertf32x4\[^\n\r]*0x0\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinsertf32x4\[^\n\r]*0x1\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times
"vextracti32x4\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 1 } } */
+/* { dg-final { scan-assembler-times
"vextractf32x4\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 1 } } */
+/* { dg-final { scan-assembler-times "vinserti64x2\[^\n\r]*0x0\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinserti64x2\[^\n\r]*0x1\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinsertf64x2\[^\n\r]*0x0\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times "vinsertf64x2\[^\n\r]*0x1\[^\n\r]*%ymm16"
1 } } */
+/* { dg-final { scan-assembler-times
"vextracti64x2\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 1 } } */
+/* { dg-final { scan-assembler-times
"vextractf64x2\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 1 } } */
--- gcc/testsuite/gcc.target/i386/avx512vl-vinsert-1.c.jj 2016-05-18
16:07:03.928781560 +0200
+++ gcc/testsuite/gcc.target/i386/avx512vl-vinsert-1.c 2016-05-18
16:08:29.500612043 +0200
@@ -0,0 +1,98 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx512vl -mno-avx512dq -masm=att" } */
+
+typedef int V1 __attribute__((vector_size (32)));
+typedef long long V2 __attribute__((vector_size (32)));
+typedef float V3 __attribute__((vector_size (32)));
+typedef double V4 __attribute__((vector_size (32)));
+
+void
+f1 (V1 x, int y)
+{
+ register V1 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f2 (V1 x, int y)
+{
+ register V1 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[6] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f3 (V2 x, long long y)
+{
+ register V2 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[1] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f4 (V2 x, long long y)
+{
+ register V2 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f5 (V3 x, float y)
+{
+ register V3 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f6 (V3 x, float y)
+{
+ register V3 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[6] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f7 (V4 x, double y)
+{
+ register V4 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[1] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+void
+f8 (V4 x, double y)
+{
+ register V4 a __asm ("xmm16");
+ a = x;
+ asm volatile ("" : "+v" (a));
+ a[3] = y;
+ asm volatile ("" : "+v" (a));
+}
+
+/* { dg-final { scan-assembler-times "vinserti32x4\[^\n\r]*0x0\[^\n\r]*%ymm16"
2 } } */
+/* { dg-final { scan-assembler-times "vinserti32x4\[^\n\r]*0x1\[^\n\r]*%ymm16"
2 } } */
+/* { dg-final { scan-assembler-times "vinsertf32x4\[^\n\r]*0x0\[^\n\r]*%ymm16"
2 } } */
+/* { dg-final { scan-assembler-times "vinsertf32x4\[^\n\r]*0x1\[^\n\r]*%ymm16"
2 } } */
+/* { dg-final { scan-assembler-times
"vextracti32x4\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 2 } } */
+/* { dg-final { scan-assembler-times
"vextractf32x4\[^\n\r]*0x1\[^\n\r]*%\[yz]mm16" 2 } } */
+/* { dg-final { scan-assembler-not "vinserti64x2" } } */
+/* { dg-final { scan-assembler-not "vinsertf64x2" } } */
+/* { dg-final { scan-assembler-not "vextracti64x2" } } */
+/* { dg-final { scan-assembler-not "vextracti64x2" } } */
Jakub
