@@ -16831,7 +16831,7 @@ (define_insn "*avx2_eq<mode>3"
[(set (match_operand:VI_256 0 "register_operand" "=x")
(eq:VI_256
(match_operand:VI_256 1 "nonimmediate_operand" "%x")
- (match_operand:VI_256 2 "nonimmediate_operand" "xm")))]
+ (match_operand:VI_256 2 "nonimmediate_operand" "jm")))]
"TARGET_AVX2 && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
"vpcmpeq<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "ssecmp")
@@ -16839,6 +16839,7 @@ (define_insn "*avx2_eq<mode>3"
(if_then_else (eq (const_string "<MODE>mode") (const_string "V4DImode"))
(const_string "1")
(const_string "*")))
+ (set_attr "gpr32" "0")
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
@@ -17021,7 +17022,7 @@ (define_insn "*sse4_1_eqv2di3"
[(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,x")
(eq:V2DI
(match_operand:V2DI 1 "vector_operand" "%0,0,x")
- (match_operand:V2DI 2 "vector_operand" "YrBm,*xBm,xm")))]
+ (match_operand:V2DI 2 "vector_operand" "Yrja,*xja,xjm")))]
"TARGET_SSE4_1 && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
"@
pcmpeqq\t{%2, %0|%0, %2}
@@ -17029,6 +17030,7 @@ (define_insn "*sse4_1_eqv2di3"
vpcmpeqq\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssecmp")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,orig,vex")
(set_attr "mode" "TI")])
@@ -17037,13 +17039,14 @@ (define_insn "*sse2_eq<mode>3"
[(set (match_operand:VI124_128 0 "register_operand" "=x,x")
(eq:VI124_128
(match_operand:VI124_128 1 "vector_operand" "%0,x")
- (match_operand:VI124_128 2 "vector_operand" "xBm,xm")))]
+ (match_operand:VI124_128 2 "vector_operand" "xBm,xjm")))]
"TARGET_SSE2
&& !(MEM_P (operands[1]) && MEM_P (operands[2]))"
"@
pcmpeq<ssemodesuffix>\t{%2, %0|%0, %2}
vpcmpeq<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
+ (set_attr "gpr32" "1,0")
(set_attr "type" "ssecmp")
(set_attr "prefix" "orig,vex")
(set_attr "mode" "TI")])
@@ -17052,7 +17055,7 @@ (define_insn "sse4_2_gtv2di3"
[(set (match_operand:V2DI 0 "register_operand" "=Yr,*x,x")
(gt:V2DI
(match_operand:V2DI 1 "register_operand" "0,0,x")
- (match_operand:V2DI 2 "vector_operand" "YrBm,*xBm,xm")))]
+ (match_operand:V2DI 2 "vector_operand" "Yrja,*xja,xjm")))]
"TARGET_SSE4_2"
"@
pcmpgtq\t{%2, %0|%0, %2}
@@ -17060,6 +17063,7 @@ (define_insn "sse4_2_gtv2di3"
vpcmpgtq\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssecmp")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,orig,vex")
(set_attr "mode" "TI")])
@@ -17068,7 +17072,7 @@ (define_insn "avx2_gt<mode>3"
[(set (match_operand:VI_256 0 "register_operand" "=x")
(gt:VI_256
(match_operand:VI_256 1 "register_operand" "x")
- (match_operand:VI_256 2 "nonimmediate_operand" "xm")))]
+ (match_operand:VI_256 2 "nonimmediate_operand" "xjm")))]
"TARGET_AVX2"
"vpcmpgt<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "ssecmp")
@@ -17076,6 +17080,7 @@ (define_insn "avx2_gt<mode>3"
(if_then_else (eq (const_string "<MODE>mode") (const_string "V4DImode"))
(const_string "1")
(const_string "*")))
+ (set_attr "gpr32" "0")
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
@@ -17099,7 +17104,7 @@ (define_insn "*sse2_gt<mode>3"
[(set (match_operand:VI124_128 0 "register_operand" "=x,x")
(gt:VI124_128
(match_operand:VI124_128 1 "register_operand" "0,x")
- (match_operand:VI124_128 2 "vector_operand" "xBm,xm")))]
+ (match_operand:VI124_128 2 "vector_operand" "xBm,xjm")))]
"TARGET_SSE2"
"@
pcmpgt<ssemodesuffix>\t{%2, %0|%0, %2}
@@ -21222,7 +21227,7 @@ (define_insn "avx2_ph<plusminus_mnemonic>wv16hi3"
(vec_select:V16HI
(vec_concat:V32HI
(match_operand:V16HI 1 "register_operand" "x")
- (match_operand:V16HI 2 "nonimmediate_operand" "xm"))
+ (match_operand:V16HI 2 "nonimmediate_operand" "xjm"))
(parallel
[(const_int 0) (const_int 2) (const_int 4) (const_int 6)
(const_int 16) (const_int 18) (const_int 20) (const_int 22)
@@ -21238,6 +21243,7 @@ (define_insn "avx2_ph<plusminus_mnemonic>wv16hi3"
"TARGET_AVX2"
"vph<plusminus_mnemonic>w\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "sseiadd")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
@@ -21248,7 +21254,7 @@ (define_insn "ssse3_ph<plusminus_mnemonic>wv8hi3"
(vec_select:V8HI
(vec_concat:V16HI
(match_operand:V8HI 1 "register_operand" "0,x")
- (match_operand:V8HI 2 "vector_operand" "xBm,xm"))
+ (match_operand:V8HI 2 "vector_operand" "xja,xjm"))
(parallel
[(const_int 0) (const_int 2) (const_int 4) (const_int 6)
(const_int 8) (const_int 10) (const_int 12) (const_int 14)]))
@@ -21263,6 +21269,7 @@ (define_insn "ssse3_ph<plusminus_mnemonic>wv8hi3"
vph<plusminus_mnemonic>w\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sseiadd")
+ (set_attr "gpr32" "0")
(set_attr "atom_unit" "complex")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,vex")
@@ -21314,7 +21321,7 @@ (define_insn "avx2_ph<plusminus_mnemonic>dv8si3"
(vec_select:V8SI
(vec_concat:V16SI
(match_operand:V8SI 1 "register_operand" "x")
- (match_operand:V8SI 2 "nonimmediate_operand" "xm"))
+ (match_operand:V8SI 2 "nonimmediate_operand" "xjm"))
(parallel
[(const_int 0) (const_int 2) (const_int 8) (const_int 10)
(const_int 4) (const_int 6) (const_int 12) (const_int 14)]))
@@ -21326,6 +21333,7 @@ (define_insn "avx2_ph<plusminus_mnemonic>dv8si3"
"TARGET_AVX2"
"vph<plusminus_mnemonic>d\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "sseiadd")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
@@ -21336,7 +21344,7 @@ (define_insn "ssse3_ph<plusminus_mnemonic>dv4si3"
(vec_select:V4SI
(vec_concat:V8SI
(match_operand:V4SI 1 "register_operand" "0,x")
- (match_operand:V4SI 2 "vector_operand" "xBm,xm"))
+ (match_operand:V4SI 2 "vector_operand" "xja,xjm"))
(parallel
[(const_int 0) (const_int 2) (const_int 4) (const_int 6)]))
(vec_select:V4SI
@@ -21349,6 +21357,7 @@ (define_insn "ssse3_ph<plusminus_mnemonic>dv4si3"
vph<plusminus_mnemonic>d\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sseiadd")
+ (set_attr "gpr32" "0")
(set_attr "atom_unit" "complex")
(set_attr "prefix_data16" "1,*")
(set_attr "prefix_extra" "1")
@@ -21388,6 +21397,7 @@ (define_insn_and_split "ssse3_ph<plusminus_mnemonic>dv2si3"
}
[(set_attr "mmx_isa" "native,sse_noavx,avx")
(set_attr "type" "sseiadd")
+ (set_attr "gpr32" "0")
(set_attr "atom_unit" "complex")
(set_attr "prefix_extra" "1")
(set (attr "prefix_rex") (symbol_ref "x86_extended_reg_mentioned_p (insn)"))
@@ -21842,7 +21852,7 @@ (define_insn "<ssse3_avx2>_psign<mode>3"
[(set (match_operand:VI124_AVX2 0 "register_operand" "=x,x")
(unspec:VI124_AVX2
[(match_operand:VI124_AVX2 1 "register_operand" "0,x")
- (match_operand:VI124_AVX2 2 "vector_operand" "xBm,xm")]
+ (match_operand:VI124_AVX2 2 "vector_operand" "xja,xjm")]
UNSPEC_PSIGN))]
"TARGET_SSSE3"
"@
@@ -21850,6 +21860,7 @@ (define_insn "<ssse3_avx2>_psign<mode>3"
vpsign<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sselog1")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,vex")
(set_attr "mode" "<sseinsnmode>")])
@@ -22147,7 +22158,7 @@ (define_mode_attr blendbits
(define_insn "<sse4_1>_blend<ssemodesuffix><avxsizesuffix>"
[(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x")
(vec_merge:VF_128_256
- (match_operand:VF_128_256 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VF_128_256 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:VF_128_256 1 "register_operand" "0,0,x")
(match_operand:SI 3 "const_0_to_<blendbits>_operand")))]
"TARGET_SSE4_1"
@@ -22157,6 +22168,7 @@ (define_insn "<sse4_1>_blend<ssemodesuffix><avxsizesuffix>"
vblend<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_data16" "1,1,*")
(set_attr "prefix_extra" "1")
@@ -22167,7 +22179,7 @@ (define_insn "<sse4_1>_blendv<ssemodesuffix><avxsizesuffix>"
[(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x")
(unspec:VF_128_256
[(match_operand:VF_128_256 1 "register_operand" "0,0,x")
- (match_operand:VF_128_256 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VF_128_256 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:VF_128_256 3 "register_operand" "Yz,Yz,x")]
UNSPEC_BLENDV))]
"TARGET_SSE4_1"
@@ -22177,6 +22189,7 @@ (define_insn "<sse4_1>_blendv<ssemodesuffix><avxsizesuffix>"
vblendv<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_data16" "1,1,*")
(set_attr "prefix_extra" "1")
@@ -22228,7 +22241,7 @@ (define_insn_and_split "*<sse4_1>_blendv<ssemodesuffix><avxsizesuffix>_lt"
[(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x")
(unspec:VF_128_256
[(match_operand:VF_128_256 1 "register_operand" "0,0,x")
- (match_operand:VF_128_256 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VF_128_256 2 "vector_operand" "Yrja,*xja,xjm")
(lt:VF_128_256
(match_operand:<sseintvecmode> 3 "register_operand" "Yz,Yz,x")
(match_operand:<sseintvecmode> 4 "const0_operand"))]
@@ -22242,6 +22255,7 @@ (define_insn_and_split "*<sse4_1>_blendv<ssemodesuffix><avxsizesuffix>_lt"
"operands[3] = gen_lowpart (<MODE>mode, operands[3]);"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_data16" "1,1,*")
(set_attr "prefix_extra" "1")
@@ -22260,7 +22274,7 @@ (define_insn_and_split "*<sse4_1>_blendv<ssefltmodesuffix><avxsizesuffix>_ltint"
[(set (match_operand:<ssebytemode> 0 "register_operand" "=Yr,*x,x")
(unspec:<ssebytemode>
[(match_operand:<ssebytemode> 1 "register_operand" "0,0,x")
- (match_operand:<ssebytemode> 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:<ssebytemode> 2 "vector_operand" "Yrja,*xja,xjm")
(subreg:<ssebytemode>
(lt:VI48_AVX
(match_operand:VI48_AVX 3 "register_operand" "Yz,Yz,x")
@@ -22280,6 +22294,7 @@ (define_insn_and_split "*<sse4_1>_blendv<ssefltmodesuffix><avxsizesuffix>_ltint"
}
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_data16" "1,1,*")
(set_attr "prefix_extra" "1")
@@ -22318,7 +22333,7 @@ (define_insn "<sse4_1>_dp<ssemodesuffix><avxsizesuffix>"
[(set (match_operand:VF_128_256 0 "register_operand" "=Yr,*x,x")
(unspec:VF_128_256
[(match_operand:VF_128_256 1 "vector_operand" "%0,0,x")
- (match_operand:VF_128_256 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VF_128_256 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:SI 3 "const_0_to_255_operand")]
UNSPEC_DP))]
"TARGET_SSE4_1"
@@ -22328,6 +22343,7 @@ (define_insn "<sse4_1>_dp<ssemodesuffix><avxsizesuffix>"
vdp<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemul")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_data16" "1,1,*")
(set_attr "prefix_extra" "1")
@@ -22356,7 +22372,7 @@ (define_insn "<sse4_1_avx2>_mpsadbw"
[(set (match_operand:VI1_AVX2 0 "register_operand" "=Yr,*x,x")
(unspec:VI1_AVX2
[(match_operand:VI1_AVX2 1 "register_operand" "0,0,x")
- (match_operand:VI1_AVX2 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VI1_AVX2 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:SI 3 "const_0_to_255_operand")]
UNSPEC_MPSADBW))]
"TARGET_SSE4_1"
@@ -22366,6 +22382,7 @@ (define_insn "<sse4_1_avx2>_mpsadbw"
vmpsadbw\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "sselog1")
+ (set_attr "gpr32" "0")
(set_attr "length_immediate" "1")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "orig,orig,vex")
@@ -22394,7 +22411,7 @@ (define_insn "<sse4_1_avx2>_pblendvb"
[(set (match_operand:VI1_AVX2 0 "register_operand" "=Yr,*x,x")
(unspec:VI1_AVX2
[(match_operand:VI1_AVX2 1 "register_operand" "0,0,x")
- (match_operand:VI1_AVX2 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VI1_AVX2 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:VI1_AVX2 3 "register_operand" "Yz,Yz,x")]
UNSPEC_BLENDV))]
"TARGET_SSE4_1"
@@ -22404,6 +22421,7 @@ (define_insn "<sse4_1_avx2>_pblendvb"
vpblendvb\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "length_immediate" "*,*,1")
(set_attr "prefix" "orig,orig,vex")
@@ -22443,7 +22461,7 @@ (define_insn_and_split "*<sse4_1_avx2>_pblendvb_lt"
[(set (match_operand:VI1_AVX2 0 "register_operand" "=Yr,*x,x")
(unspec:VI1_AVX2
[(match_operand:VI1_AVX2 1 "register_operand" "0,0,x")
- (match_operand:VI1_AVX2 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:VI1_AVX2 2 "vector_operand" "Yrja,*xja,xjm")
(lt:VI1_AVX2 (match_operand:VI1_AVX2 3 "register_operand" "Yz,Yz,x")
(match_operand:VI1_AVX2 4 "const0_operand"))]
UNSPEC_BLENDV))]
@@ -22456,6 +22474,7 @@ (define_insn_and_split "*<sse4_1_avx2>_pblendvb_lt"
""
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "length_immediate" "*,*,1")
(set_attr "prefix" "orig,orig,vex")
@@ -22487,7 +22506,7 @@ (define_insn_and_split "*<sse4_1_avx2>_pblendvb_lt_subreg_not"
(define_insn "sse4_1_pblend<ssemodesuffix>"
[(set (match_operand:V8_128 0 "register_operand" "=Yr,*x,x")
(vec_merge:V8_128
- (match_operand:V8_128 2 "vector_operand" "YrBm,*xBm,xm")
+ (match_operand:V8_128 2 "vector_operand" "Yrja,*xja,xjm")
(match_operand:V8_128 1 "register_operand" "0,0,x")
(match_operand:SI 3 "const_0_to_255_operand")))]
"TARGET_SSE4_1"
@@ -22497,6 +22516,7 @@ (define_insn "sse4_1_pblend<ssemodesuffix>"
vpblendw\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "length_immediate" "1")
(set_attr "prefix" "orig,orig,vex")
@@ -22559,7 +22579,7 @@ (define_expand "avx2_pblend<ssemodesuffix>_1"
(define_insn "*avx2_pblend<ssemodesuffix>"
[(set (match_operand:V16_256 0 "register_operand" "=x")
(vec_merge:V16_256
- (match_operand:V16_256 2 "nonimmediate_operand" "xm")
+ (match_operand:V16_256 2 "nonimmediate_operand" "xjm")
(match_operand:V16_256 1 "register_operand" "x")
(match_operand:SI 3 "avx2_pblendw_operand")))]
"TARGET_AVX2"
@@ -22568,6 +22588,7 @@ (define_insn "*avx2_pblend<ssemodesuffix>"
return "vpblendw\t{%3, %2, %1, %0|%0, %1, %2, %3}";
}
[(set_attr "type" "ssemov")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "length_immediate" "1")
(set_attr "prefix" "vex")
@@ -22576,7 +22597,7 @@ (define_insn "*avx2_pblend<ssemodesuffix>"
(define_insn "avx2_pblendd<mode>"
[(set (match_operand:VI4_AVX2 0 "register_operand" "=x")
(vec_merge:VI4_AVX2
- (match_operand:VI4_AVX2 2 "nonimmediate_operand" "xm")
+ (match_operand:VI4_AVX2 2 "nonimmediate_operand" "xjm")
(match_operand:VI4_AVX2 1 "register_operand" "x")
(match_operand:SI 3 "const_0_to_255_operand")))]
"TARGET_AVX2"
@@ -26437,11 +26458,13 @@ (define_insn "avx512f_perm<mode>_1<mask_name>"
(set_attr "prefix" "<mask_prefix2>")
(set_attr "mode" "<sseinsnmode>")])
+;; TODO (APX): vmovaps supports EGPR but not others, could split
+;; pattern to enable gpr32 for this one.
(define_insn "avx2_permv2ti"
[(set (match_operand:V4DI 0 "register_operand" "=x")
(unspec:V4DI
[(match_operand:V4DI 1 "register_operand" "x")
- (match_operand:V4DI 2 "nonimmediate_operand" "xm")
+ (match_operand:V4DI 2 "nonimmediate_operand" "xjm")
(match_operand:SI 3 "const_0_to_255_operand")]
UNSPEC_VPERMTI))]
"TARGET_AVX2"
@@ -26468,6 +26491,7 @@ (define_insn "avx2_permv2ti"
return "vperm2i128\t{%3, %2, %1, %0|%0, %1, %2, %3}";
}
[(set_attr "type" "sselog")
+ (set_attr "gpr32" "0")
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
@@ -27098,7 +27122,7 @@ (define_insn "*avx_vperm2f128<mode>_nozero"
(vec_select:AVX256MODE2P
(vec_concat:<ssedoublevecmode>
(match_operand:AVX256MODE2P 1 "register_operand" "x")
- (match_operand:AVX256MODE2P 2 "nonimmediate_operand" "xm"))
+ (match_operand:AVX256MODE2P 2 "nonimmediate_operand" "xjm"))
(match_parallel 3 ""
[(match_operand 4 "const_int_operand")])))]
"TARGET_AVX
@@ -27115,6 +27139,7 @@ (define_insn "*avx_vperm2f128<mode>_nozero"
return "vperm2<i128>\t{%3, %2, %1, %0|%0, %1, %2, %3}";
}
[(set_attr "type" "sselog")
+ (set_attr "gpr32" "0")
(set_attr "prefix_extra" "1")
(set_attr "length_immediate" "1")
(set_attr "prefix" "vex")
@@ -28,3 +28,109 @@ void legacy_test ()
/* { dg-final { scan-assembler-not "xrstor64\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
/* { dg-final { scan-assembler-not "fxsave64\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
/* { dg-final { scan-assembler-not "fxrstor64\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+
+#ifdef DTYPE
+#undef DTYPE
+#define DTYPE u64
+#endif
+
+typedef union
+{
+ __m128i xi[8];
+ __m128 xf[8];
+ __m128d xd[8];
+ __m256i yi[4];
+ __m256 yf[4];
+ __m256d yd[4];
+ DTYPE a[16];
+} tmp_u;
+
+__attribute__((target("sse4.2")))
+void sse_test ()
+{
+ register tmp_u *tdst __asm__("%r16");
+ register tmp_u *src1 __asm__("%r17");
+ register tmp_u *src2 __asm__("%r18");
+
+ src1->xi[0] = _mm_hadd_epi16 (tdst->xi[2], src2->xi[3]);
+ src1->xi[1] = _mm_hadd_epi32 (tdst->xi[0], src2->xi[1]);
+ tdst->xi[2] = _mm_hadds_epi16 (src1->xi[4], src2->xi[5]);
+ tdst->xi[3] = _mm_hsub_epi16 (src1->xi[6], src2->xi[7]);
+ tdst->xi[4] = _mm_hsub_epi32 (src1->xi[0], src2->xi[1]);
+ tdst->xi[5] = _mm_hsubs_epi16 (src1->xi[2], src2->xi[3]);
+
+ src1->xi[6] = _mm_cmpeq_epi64 (tdst->xi[4], src2->xi[5]);
+ src1->xi[7] = _mm_cmpgt_epi64 (tdst->xi[6], src2->xi[7]);
+
+ tdst->xf[0] = _mm_dp_ps (src1->xf[0], src2->xf[1], 0xbf);
+ tdst->xd[1] = _mm_dp_pd (src1->xd[2], src2->xd[3], 0xae);
+
+ tdst->xi[2] = _mm_mpsadbw_epu8 (src1->xi[4], src2->xi[5], 0xc1);
+
+ tdst->xi[3] = _mm_blend_epi16 (src1->xi[6], src2->xi[7], 0xc);
+ tdst->xi[4] = _mm_blendv_epi8 (src1->xi[0], src2->xi[1], tdst->xi[2]);
+ tdst->xf[5] = _mm_blend_ps (src1->xf[3], src2->xf[4], 0x4);
+ tdst->xf[6] = _mm_blendv_ps (src1->xf[5], src2->xf[6], tdst->xf[7]);
+ tdst->xd[7] = _mm_blend_pd (tdst->xd[0], src1->xd[1], 0x1);
+ tdst->xd[0] = _mm_blendv_pd (src1->xd[2], src2->xd[3], tdst->xd[4]);
+
+ tdst->xi[1] = _mm_sign_epi8 (src1->xi[5], src2->xi[6]);
+ tdst->xi[2] = _mm_sign_epi16 (src1->xi[7], src2->xi[0]);
+ tdst->xi[3] = _mm_sign_epi32 (src1->xi[1], src2->xi[2]);
+}
+
+__attribute__((target("avx2")))
+void vex_test ()
+{
+
+ register tmp_u *tdst __asm__("%r16");
+ register tmp_u *src1 __asm__("%r17");
+ register tmp_u *src2 __asm__("%r18");
+
+ src1->yi[1] = _mm256_hadd_epi16 (tdst->yi[2], src2->yi[3]);
+ src1->yi[2] = _mm256_hadd_epi32 (tdst->yi[0], src2->yi[1]);
+ tdst->yi[3] = _mm256_hadds_epi16 (src1->yi[1], src2->yi[2]);
+ tdst->yi[0] = _mm256_hsub_epi16 (src1->yi[3], src2->yi[0]);
+ tdst->yi[1] = _mm256_hsub_epi32 (src1->yi[0], src2->yi[1]);
+ tdst->yi[2] = _mm256_hsubs_epi16 (src1->yi[2], src2->yi[3]);
+
+ src1->yi[2] = _mm256_cmpeq_epi64 (tdst->yi[1], src2->yi[2]);
+ src1->yi[1] = _mm256_cmpgt_epi64 (tdst->yi[3], src2->yi[0]);
+
+ tdst->yf[2] = _mm256_dp_ps (src1->yf[0], src2->yf[1], 0xbf);
+ tdst->xd[3] = _mm_dp_pd (src1->xd[0], src2->xd[1], 0xbf);
+
+ tdst->yi[3] = _mm256_mpsadbw_epu8 (src1->yi[1], src2->yi[1], 0xc1);
+
+ tdst->yi[0] = _mm256_blend_epi16 (src1->yi[1], src2->yi[2], 0xc);
+ tdst->yi[1] = _mm256_blendv_epi8 (src1->yi[1], src2->yi[2], tdst->yi[0]);
+ tdst->yf[2] = _mm256_blend_ps (src1->yf[0], src2->yf[1], 0x4);
+ tdst->yf[3] = _mm256_blendv_ps (src1->yf[2], src2->yf[3], tdst->yf[1]);
+ tdst->yd[3] = _mm256_blend_pd (tdst->yd[1], src1->yd[0], 0x1);
+ tdst->yd[1] = _mm256_blendv_pd (src1->yd[2], src2->yd[3], tdst->yd[2]);
+
+ tdst->yi[2] = _mm256_sign_epi8 (src1->yi[0], src2->yi[1]);
+ tdst->yi[3] = _mm256_sign_epi16 (src1->yi[2], src2->yi[3]);
+ tdst->yi[0] = _mm256_sign_epi32 (src1->yi[0], src2->yi[1]);
+}
+
+/* { dg-final { scan-assembler-not "v?pcmpeqq\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?pcmpgtq\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phaddw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phaddd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phaddsw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phsubw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phsubd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?phsubsw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?dpps\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?dppd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?psadbw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?pblendw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?pblendvb\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?blendps\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?blendvps\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?blendpd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?blendvpd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?psignb\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?psignw\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
+/* { dg-final { scan-assembler-not "v?psignd\[ \\t]+\\\.\\\*r\(1\[6-9\]\|2\[0-9\]|30\|31\)" } } */
From: Kong Lingling <lingling.kong@intel.com> These legacy insns in opcode map2/3 have vex but no evex counterpart, disable EGPR for them by adjusting alternatives and attr_gpr32. insn list: 1. phaddw/vphaddw, phaddd/vphaddd, phaddsw/vphaddsw 2. phsubw/vphsubw, phsubd/vphsubd, phsubsw/vphsubsw 3. psignb/vpsginb, psignw/vpsignw, psignd/vpsignd 4. blendps/vblendps, blendpd/vblendpd 5. blendvps/vblendvps, blendvpd/vblendvpd 6. pblendvb/vpblendvb, pblendw/vpblendw 7. mpsadbw/vmpsadbw 8. dpps/vddps, dppd/vdppd 9. pcmpeqq/vpcmpeqq, pcmpgtq/vpcmpgtq gcc/ChangeLog: * config/i386/sse.md (avx2_ph<plusminus_mnemonic>wv16hi3): Set attr gpr32 0 and constraint jm/ja to all mem alternatives. (ssse3_ph<plusminus_mnemonic>wv8hi3): Likewise. (ssse3_ph<plusminus_mnemonic>wv4hi3): Likewise. (avx2_ph<plusminus_mnemonic>dv8si3): Likewise. (ssse3_ph<plusminus_mnemonic>dv4si3): Likewise. (ssse3_ph<plusminus_mnemonic>dv2si3): Likewise. (<ssse3_avx2>_psign<mode>3): Likewise. (ssse3_psign<mode>3): Likewise. (<sse4_1>_blend<ssemodesuffix><avxsizesuffix): Likewise. (<sse4_1>_blendv<ssemodesuffix><avxsizesuffix): Likewise. (*<sse4_1>_blendv<ssemodesuffix><avxsizesuffix>_lt): Likewise. (*<sse4_1>_blendv<ssefltmodesuff)ix><avxsizesuffix>_not_ltint: Likewise. (<sse4_1>_dp<ssemodesuffix><avxsizesuffix>): Likewise. (<sse4_1_avx2>_mpsadbw): Likewise. (<sse4_1_avx2>_pblendvb): Likewise. (*<sse4_1_avx2>_pblendvb_lt): Likewise. (sse4_1_pblend<ssemodesuffix>): Likewise. (*avx2_pblend<ssemodesuffix>): Likewise. (avx2_permv2ti): Likewise. (*avx_vperm2f128<mode>_nozero): Likewise. (*avx2_eq<mode>3): Likewise. (*sse4_1_eqv2di3): Likewise. (sse4_2_gtv2di3): Likewise. (avx2_gt<mode>3): Likewise. gcc/testsuite/ChangeLog: * gcc.target/i386/apx-legacy-insn-check-norex2.c: Add sse/vex intrinsic tests. Co-authored-by: Hongyu Wang <hongyu.wang@intel.com> Co-authored-by: Hongtao Liu <hongtao.liu@intel.com> --- gcc/config/i386/sse.md | 73 ++++++++---- .../i386/apx-legacy-insn-check-norex2.c | 106 ++++++++++++++++++ 2 files changed, 155 insertions(+), 24 deletions(-)