Hi! This pattern is used to improve __builtin_shuffle in some cases; VPALIGNR is AVX512BW & AVX512VL.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk? 2016-05-23 Jakub Jelinek <ja...@redhat.com> * config/i386/sse.md (*ssse3_palignr<mode>_perm): Add avx512bw alternative. Formatting fix. * gcc.target/i386/avx512bw-vpalignr-4.c: New test. * gcc.target/i386/avx512vl-vpalignr-4.c: New test. --- gcc/config/i386/sse.md.jj 2016-05-23 14:53:36.000000000 +0200 +++ gcc/config/i386/sse.md 2016-05-23 15:07:41.518548599 +0200 @@ -17747,33 +17747,34 @@ (define_insn "*avx_vperm2f128<mode>_noze (set_attr "mode" "<sseinsnmode>")]) (define_insn "*ssse3_palignr<mode>_perm" - [(set (match_operand:V_128 0 "register_operand" "=x,x") + [(set (match_operand:V_128 0 "register_operand" "=x,x,v") (vec_select:V_128 - (match_operand:V_128 1 "register_operand" "0,x") + (match_operand:V_128 1 "register_operand" "0,x,v") (match_parallel 2 "palignr_operand" - [(match_operand 3 "const_int_operand" "n, n")])))] + [(match_operand 3 "const_int_operand" "n,n,n")])))] "TARGET_SSSE3" { - operands[2] = - GEN_INT (INTVAL (operands[3]) * GET_MODE_UNIT_SIZE (GET_MODE (operands[0]))); + operands[2] = (GEN_INT (INTVAL (operands[3]) + * GET_MODE_UNIT_SIZE (GET_MODE (operands[0])))); switch (which_alternative) { case 0: return "palignr\t{%2, %1, %0|%0, %1, %2}"; case 1: + case 2: return "vpalignr\t{%2, %1, %1, %0|%0, %1, %1, %2}"; default: gcc_unreachable (); } } - [(set_attr "isa" "noavx,avx") + [(set_attr "isa" "noavx,avx,avx512bw") (set_attr "type" "sseishft") (set_attr "atom_unit" "sishuf") - (set_attr "prefix_data16" "1,*") + (set_attr "prefix_data16" "1,*,*") (set_attr "prefix_extra" "1") (set_attr "length_immediate" "1") - (set_attr "prefix" "orig,vex")]) + (set_attr "prefix" "orig,vex,evex")]) (define_expand "avx512vl_vinsert<mode>" [(match_operand:VI48F_256 0 "register_operand") --- gcc/testsuite/gcc.target/i386/avx512bw-vpalignr-4.c.jj 2016-05-23 15:18:57.787640379 +0200 +++ gcc/testsuite/gcc.target/i386/avx512bw-vpalignr-4.c 2016-05-23 15:18:26.000000000 +0200 @@ -0,0 +1,86 @@ +/* { dg-do compile { target { ! ia32 } } } */ +/* { dg-options "-O2 -mavx512vl -mavx512bw -masm=att" } */ + +typedef char V1 __attribute__((vector_size (16))); + +void +f1 (V1 x) +{ + register V1 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V1) { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 0, 1, 2, 3, 4, 5 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$6\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef short V2 __attribute__((vector_size (16))); + +void +f2 (V2 x) +{ + register V2 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V2) { 5, 6, 7, 0, 1, 2, 3, 4 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$10\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef int V3 __attribute__((vector_size (16))); + +void +f3 (V3 x) +{ + register V3 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpshufd\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef long long V4 __attribute__((vector_size (16))); + +void +f4 (V4 x) +{ + register V4 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V4) { 1, 0 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpalignr\[^\n\r]*\\\$8\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef float V5 __attribute__((vector_size (16))); + +void +f5 (V5 x) +{ + register V5 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef double V6 __attribute__((vector_size (16))); + +void +f6 (V6 x) +{ + register V6 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V4) { 1, 0 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpermilpd\[^\n\r]*\\\$1\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ --- gcc/testsuite/gcc.target/i386/avx512vl-vpalignr-4.c.jj 2016-05-23 15:19:34.352162361 +0200 +++ gcc/testsuite/gcc.target/i386/avx512vl-vpalignr-4.c 2016-05-23 15:20:02.570793519 +0200 @@ -0,0 +1,86 @@ +/* { dg-do compile { target { ! ia32 } } } */ +/* { dg-options "-O2 -mavx512vl -mno-avx512bw -masm=att" } */ + +typedef char V1 __attribute__((vector_size (16))); + +void +f1 (V1 x) +{ + register V1 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V1) { 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 0, 1, 2, 3, 4, 5 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$6\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */ + +typedef short V2 __attribute__((vector_size (16))); + +void +f2 (V2 x) +{ + register V2 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V2) { 5, 6, 7, 0, 1, 2, 3, 4 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$10\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */ + +typedef int V3 __attribute__((vector_size (16))); + +void +f3 (V3 x) +{ + register V3 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpshufd\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef long long V4 __attribute__((vector_size (16))); + +void +f4 (V4 x) +{ + register V4 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V4) { 1, 0 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-not "vpalignr\[^\n\r]*\\\$8\[^\n\r]*%xmm16\[^\n\r]*%xmm16\[^\n\r]*%xmm16" } } */ + +typedef float V5 __attribute__((vector_size (16))); + +void +f5 (V5 x) +{ + register V5 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V3) { 3, 0, 1, 2 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$147\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ + +typedef double V6 __attribute__((vector_size (16))); + +void +f6 (V6 x) +{ + register V6 a __asm ("xmm16"); + a = x; + asm volatile ("" : "+v" (a)); + a = __builtin_shuffle (a, (V4) { 1, 0 }); + asm volatile ("" : "+v" (a)); +} + +/* { dg-final { scan-assembler-times "vpermilpd\[^\n\r]*\\\$1\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */ Jakub