diff options
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/config/i386/i386-expand.cc | 2 | ||||
| -rw-r--r-- | gcc/config/i386/sse.md | 36 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.target/i386/avx512f-copysign.c | 32 |
3 files changed, 59 insertions, 11 deletions
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index ad2cd07..7bb4d39 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -2278,7 +2278,7 @@ ix86_expand_copysign (rtx operands[]) else dest = NULL_RTX; op1 = lowpart_subreg (vmode, force_reg (mode, operands[2]), mode); - mask = ix86_build_signbit_mask (vmode, 0, 0); + mask = ix86_build_signbit_mask (vmode, TARGET_AVX512F && mode != HFmode, 0); if (CONST_DOUBLE_P (operands[1])) { diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index b99becb..f793258 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -12597,22 +12597,35 @@ (set_attr "mode" "<sseinsnmode>")]) (define_insn "*<avx512>_vternlog<mode>_all" - [(set (match_operand:V 0 "register_operand" "=v") + [(set (match_operand:V 0 "register_operand" "=v,v") (unspec:V - [(match_operand:V 1 "register_operand" "0") - (match_operand:V 2 "register_operand" "v") - (match_operand:V 3 "bcst_vector_operand" "vmBr") + [(match_operand:V 1 "register_operand" "0,0") + (match_operand:V 2 "register_operand" "v,v") + (match_operand:V 3 "bcst_vector_operand" "vBr,m") (match_operand:SI 4 "const_0_to_255_operand")] UNSPEC_VTERNLOG))] - "TARGET_AVX512F + "(<MODE_SIZE> == 64 || TARGET_AVX512VL + || (TARGET_AVX512F && !TARGET_PREFER_AVX256)) /* Disallow embeded broadcast for vector HFmode since it's not real AVX512FP16 instruction. */ && (GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) >= 4 || GET_CODE (operands[3]) != VEC_DUPLICATE)" - "vpternlog<ternlogsuffix>\t{%4, %3, %2, %0|%0, %2, %3, %4}" +{ + if (TARGET_AVX512VL) + return "vpternlog<ternlogsuffix>\t{%4, %3, %2, %0|%0, %2, %3, %4}"; + else + return "vpternlog<ternlogsuffix>\t{%4, %g3, %g2, %g0|%g0, %g2, %g3, %4}"; +} [(set_attr "type" "sselog") (set_attr "prefix" "evex") - (set_attr "mode" "<sseinsnmode>")]) + (set (attr "mode") + (if_then_else (match_test "TARGET_AVX512VL") + (const_string "<sseinsnmode>") + (const_string "XI"))) + (set (attr "enabled") + (if_then_else (eq_attr "alternative" "1") + (symbol_ref "<MODE_SIZE> == 64 || TARGET_AVX512VL") + (const_string "*")))]) ;; There must be lots of other combinations like ;; @@ -12641,7 +12654,8 @@ (any_logic2:V (match_operand:V 3 "regmem_or_bitnot_regmem_operand") (match_operand:V 4 "regmem_or_bitnot_regmem_operand"))))] - "(<MODE_SIZE> == 64 || TARGET_AVX512VL) + "(<MODE_SIZE> == 64 || TARGET_AVX512VL + || (TARGET_AVX512F && !TARGET_PREFER_AVX256)) && ix86_pre_reload_split () && (rtx_equal_p (STRIP_UNARY (operands[1]), STRIP_UNARY (operands[4])) @@ -12725,7 +12739,8 @@ (match_operand:V 2 "regmem_or_bitnot_regmem_operand")) (match_operand:V 3 "regmem_or_bitnot_regmem_operand")) (match_operand:V 4 "regmem_or_bitnot_regmem_operand")))] - "(<MODE_SIZE> == 64 || TARGET_AVX512VL) + "(<MODE_SIZE> == 64 || TARGET_AVX512VL + || (TARGET_AVX512F && !TARGET_PREFER_AVX256)) && ix86_pre_reload_split () && (rtx_equal_p (STRIP_UNARY (operands[1]), STRIP_UNARY (operands[4])) @@ -12808,7 +12823,8 @@ (match_operand:V 1 "regmem_or_bitnot_regmem_operand") (match_operand:V 2 "regmem_or_bitnot_regmem_operand")) (match_operand:V 3 "regmem_or_bitnot_regmem_operand")))] - "(<MODE_SIZE> == 64 || TARGET_AVX512VL) + "(<MODE_SIZE> == 64 || TARGET_AVX512VL + || (TARGET_AVX512F && !TARGET_PREFER_AVX256)) && ix86_pre_reload_split ()" "#" "&& 1" diff --git a/gcc/testsuite/gcc.target/i386/avx512f-copysign.c b/gcc/testsuite/gcc.target/i386/avx512f-copysign.c new file mode 100644 index 0000000..51ca028 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx512f-copysign.c @@ -0,0 +1,32 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512f -mno-avx512vl -mprefer-vector-width=512 -O2" } */ +/* { dg-final { scan-assembler-times "vpternlog\[dq\]\[ \\t\]+\\\$(?:216|228|0xd8|0xe4)," 5 } } */ + +double cs_df (double x, double y) +{ + return __builtin_copysign (x, y); +} + +float cs_sf (float x, float y) +{ + return __builtin_copysignf (x, y); +} + +typedef double __attribute__ ((vector_size (16))) v2df; +typedef double __attribute__ ((vector_size (32))) v4df; +typedef double __attribute__ ((vector_size (64))) v8df; + +v2df cs_v2df (v2df x, v2df y) +{ + return __builtin_ia32_copysignpd (x, y); +} + +v4df cs_v4df (v4df x, v4df y) +{ + return __builtin_ia32_copysignpd256 (x, y); +} + +v8df cs_v8df (v8df x, v8df y) +{ + return __builtin_ia32_copysignpd512 (x, y); +} |