maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/psubus.ll

2367 lines
98 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
define <8 x i16> @test1(<8 x i16> %x) nounwind {
; SSE-LABEL: test1:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: test1:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusw {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%0 = icmp slt <8 x i16> %x, zeroinitializer
%1 = xor <8 x i16> %x, <i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768>
%res = select <8 x i1> %0, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %res
}
define <8 x i16> @test2(<8 x i16> %x) nounwind {
; SSE-LABEL: test2:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: test2:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusw {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%0 = icmp ugt <8 x i16> %x, <i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766>
%1 = add <8 x i16> %x, <i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767>
%res = select <8 x i1> %0, <8 x i16> %1, <8 x i16> zeroinitializer
ret <8 x i16> %res
}
define <8 x i16> @test3(<8 x i16> %x, i16 zeroext %w) nounwind {
; SSE-LABEL: test3:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movd %edi, %xmm1
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; SSE-NEXT: psubusw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: test3:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vmovd %edi, %xmm1
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test3:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vmovd %edi, %xmm1
; AVX2-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX2-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test3:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpbroadcastw %edi, %xmm1
; AVX512-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
vector.ph:
%0 = insertelement <8 x i16> undef, i16 %w, i32 0
%broadcast15 = shufflevector <8 x i16> %0, <8 x i16> undef, <8 x i32> zeroinitializer
%1 = icmp ult <8 x i16> %x, %broadcast15
%2 = sub <8 x i16> %x, %broadcast15
%res = select <8 x i1> %1, <8 x i16> zeroinitializer, <8 x i16> %2
ret <8 x i16> %res
}
define <16 x i8> @test4(<16 x i8> %x) nounwind {
; SSE-LABEL: test4:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: test4:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusb {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%0 = icmp slt <16 x i8> %x, zeroinitializer
%1 = xor <16 x i8> %x, <i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128>
%res = select <16 x i1> %0, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %res
}
define <16 x i8> @test5(<16 x i8> %x) nounwind {
; SSE-LABEL: test5:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: test5:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusb {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%0 = icmp ugt <16 x i8> %x, <i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126>
%1 = add <16 x i8> %x, <i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127>
%res = select <16 x i1> %0, <16 x i8> %1, <16 x i8> zeroinitializer
ret <16 x i8> %res
}
define <16 x i8> @test6(<16 x i8> %x, i8 zeroext %w) nounwind {
; SSE2-LABEL: test6:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movd %edi, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; SSE2-NEXT: psubusb %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test6:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movd %edi, %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm2
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: psubusb %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test6:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movd %edi, %xmm1
; SSE41-NEXT: pxor %xmm2, %xmm2
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: psubusb %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: test6:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vmovd %edi, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsubusb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test6:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vmovd %edi, %xmm1
; AVX2-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX2-NEXT: vpsubusb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test6:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpbroadcastb %edi, %xmm1
; AVX512-NEXT: vpsubusb %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
vector.ph:
%0 = insertelement <16 x i8> undef, i8 %w, i32 0
%broadcast15 = shufflevector <16 x i8> %0, <16 x i8> undef, <16 x i32> zeroinitializer
%1 = icmp ult <16 x i8> %x, %broadcast15
%2 = sub <16 x i8> %x, %broadcast15
%res = select <16 x i1> %1, <16 x i8> zeroinitializer, <16 x i8> %2
ret <16 x i8> %res
}
define <16 x i16> @test7(<16 x i16> %x) nounwind {
; SSE-LABEL: test7:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSE-NEXT: psubusw %xmm2, %xmm0
; SSE-NEXT: psubusw %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: test7:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpgtw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpcmpgtw %xmm0, %xmm2, %xmm2
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT: vxorps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test7:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusw {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test7:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusw {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = icmp slt <16 x i16> %x, zeroinitializer
%1 = xor <16 x i16> %x, <i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768, i16 -32768>
%res = select <16 x i1> %0, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %res
}
define <16 x i16> @test8(<16 x i16> %x) nounwind {
; SSE-LABEL: test8:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [32767,32767,32767,32767,32767,32767,32767,32767]
; SSE-NEXT: psubusw %xmm2, %xmm0
; SSE-NEXT: psubusw %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: test8:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
; AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm3
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [65534,65534,65534,65534,65534,65534,65534,65534]
; AVX1-NEXT: vpcmpgtw %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm2
; AVX1-NEXT: vpcmpgtw %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [32769,32769,32769,32769,32769,32769,32769,32769]
; AVX1-NEXT: vpaddw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpaddw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm0, %ymm2, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test8:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusw {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test8:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusw {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = icmp ugt <16 x i16> %x, <i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766, i16 32766>
%1 = add <16 x i16> %x, <i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767, i16 -32767>
%res = select <16 x i1> %0, <16 x i16> %1, <16 x i16> zeroinitializer
ret <16 x i16> %res
}
define <16 x i16> @test9(<16 x i16> %x, i16 zeroext %w) nounwind {
; SSE-LABEL: test9:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movd %edi, %xmm2
; SSE-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,0,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; SSE-NEXT: psubusw %xmm2, %xmm0
; SSE-NEXT: psubusw %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: test9:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovd %edi, %xmm2
; AVX1-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,0,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; AVX1-NEXT: vpsubw %xmm2, %xmm1, %xmm3
; AVX1-NEXT: vpsubw %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm4, %ymm3
; AVX1-NEXT: vpmaxuw %xmm2, %xmm1, %xmm4
; AVX1-NEXT: vpcmpeqw %xmm4, %xmm1, %xmm1
; AVX1-NEXT: vpmaxuw %xmm2, %xmm0, %xmm2
; AVX1-NEXT: vpcmpeqw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test9:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vmovd %edi, %xmm1
; AVX2-NEXT: vpbroadcastw %xmm1, %ymm1
; AVX2-NEXT: vpsubusw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test9:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpbroadcastw %edi, %ymm1
; AVX512-NEXT: vpsubusw %ymm1, %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = insertelement <16 x i16> undef, i16 %w, i32 0
%broadcast15 = shufflevector <16 x i16> %0, <16 x i16> undef, <16 x i32> zeroinitializer
%1 = icmp ult <16 x i16> %x, %broadcast15
%2 = sub <16 x i16> %x, %broadcast15
%res = select <16 x i1> %1, <16 x i16> zeroinitializer, <16 x i16> %2
ret <16 x i16> %res
}
define <32 x i8> @test10(<32 x i8> %x) nounwind {
; SSE-LABEL: test10:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128]
; SSE-NEXT: psubusb %xmm2, %xmm0
; SSE-NEXT: psubusb %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: test10:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpgtb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpcmpgtb %xmm0, %xmm2, %xmm2
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
; AVX1-NEXT: vxorps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test10:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusb {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test10:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusb {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = icmp slt <32 x i8> %x, zeroinitializer
%1 = xor <32 x i8> %x, <i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128>
%res = select <32 x i1> %0, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %res
}
define <32 x i8> @test11(<32 x i8> %x) nounwind {
; SSE-LABEL: test11:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
; SSE-NEXT: psubusb %xmm2, %xmm0
; SSE-NEXT: psubusb %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: test11:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128]
; AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm3
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254]
; AVX1-NEXT: vpcmpgtb %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm2
; AVX1-NEXT: vpcmpgtb %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [129,129,129,129,129,129,129,129,129,129,129,129,129,129,129,129]
; AVX1-NEXT: vpaddb %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpaddb %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm0, %ymm2, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test11:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusb {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test11:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusb {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = icmp ugt <32 x i8> %x, <i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126, i8 126>
%1 = add <32 x i8> %x, <i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127, i8 -127>
%res = select <32 x i1> %0, <32 x i8> %1, <32 x i8> zeroinitializer
ret <32 x i8> %res
}
define <32 x i8> @test12(<32 x i8> %x, i8 zeroext %w) nounwind {
; SSE2-LABEL: test12:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movd %edi, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,0,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; SSE2-NEXT: psubusb %xmm2, %xmm0
; SSE2-NEXT: psubusb %xmm2, %xmm1
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test12:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movd %edi, %xmm2
; SSSE3-NEXT: pxor %xmm3, %xmm3
; SSSE3-NEXT: pshufb %xmm3, %xmm2
; SSSE3-NEXT: psubusb %xmm2, %xmm0
; SSSE3-NEXT: psubusb %xmm2, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test12:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movd %edi, %xmm2
; SSE41-NEXT: pxor %xmm3, %xmm3
; SSE41-NEXT: pshufb %xmm3, %xmm2
; SSE41-NEXT: psubusb %xmm2, %xmm0
; SSE41-NEXT: psubusb %xmm2, %xmm1
; SSE41-NEXT: retq
;
; AVX1-LABEL: test12:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vmovd %edi, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsubb %xmm1, %xmm2, %xmm3
; AVX1-NEXT: vpsubb %xmm1, %xmm0, %xmm4
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm4, %ymm3
; AVX1-NEXT: vpmaxub %xmm1, %xmm2, %xmm4
; AVX1-NEXT: vpcmpeqb %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpmaxub %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: test12:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vmovd %edi, %xmm1
; AVX2-NEXT: vpbroadcastb %xmm1, %ymm1
; AVX2-NEXT: vpsubusb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test12:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpbroadcastb %edi, %ymm1
; AVX512-NEXT: vpsubusb %ymm1, %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%0 = insertelement <32 x i8> undef, i8 %w, i32 0
%broadcast15 = shufflevector <32 x i8> %0, <32 x i8> undef, <32 x i32> zeroinitializer
%1 = icmp ult <32 x i8> %x, %broadcast15
%2 = sub <32 x i8> %x, %broadcast15
%res = select <32 x i1> %1, <32 x i8> zeroinitializer, <32 x i8> %2
ret <32 x i8> %res
}
define <8 x i16> @test13(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: test13:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm0, %xmm5
; SSE2-NEXT: psubd %xmm2, %xmm0
; SSE2-NEXT: movdqa %xmm2, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
; SSE2-NEXT: movdqa %xmm1, %xmm2
; SSE2-NEXT: pxor %xmm4, %xmm2
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: pcmpgtd %xmm4, %xmm2
; SSE2-NEXT: packssdw %xmm6, %xmm2
; SSE2-NEXT: psubd %xmm1, %xmm3
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: packssdw %xmm0, %xmm3
; SSE2-NEXT: pandn %xmm3, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test13:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: pxor %xmm3, %xmm3
; SSSE3-NEXT: movdqa %xmm0, %xmm4
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSSE3-NEXT: movdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm0, %xmm5
; SSSE3-NEXT: psubd %xmm2, %xmm0
; SSSE3-NEXT: movdqa %xmm2, %xmm6
; SSSE3-NEXT: pxor %xmm3, %xmm6
; SSSE3-NEXT: por %xmm3, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm6
; SSSE3-NEXT: movdqa %xmm1, %xmm2
; SSSE3-NEXT: pxor %xmm3, %xmm2
; SSSE3-NEXT: por %xmm4, %xmm3
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm2
; SSSE3-NEXT: packssdw %xmm6, %xmm2
; SSSE3-NEXT: psubd %xmm1, %xmm4
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: pshufb %xmm1, %xmm4
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm0[0]
; SSSE3-NEXT: pandn %xmm4, %xmm2
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test13:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm4 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; SSE41-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
; SSE41-NEXT: movdqa %xmm4, %xmm6
; SSE41-NEXT: psubd %xmm1, %xmm4
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: pxor %xmm5, %xmm0
; SSE41-NEXT: por %xmm5, %xmm6
; SSE41-NEXT: pcmpgtd %xmm6, %xmm0
; SSE41-NEXT: movdqa %xmm2, %xmm1
; SSE41-NEXT: pxor %xmm5, %xmm1
; SSE41-NEXT: por %xmm3, %xmm5
; SSE41-NEXT: pcmpgtd %xmm5, %xmm1
; SSE41-NEXT: packssdw %xmm1, %xmm0
; SSE41-NEXT: psubd %xmm2, %xmm3
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm1, %xmm4
; SSE41-NEXT: pshufb %xmm1, %xmm3
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm3[0]
; SSE41-NEXT: pandn %xmm4, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: test13:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
; AVX1-NEXT: vpor %xmm3, %xmm0, %xmm4
; AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm5
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpxor %xmm3, %xmm5, %xmm6
; AVX1-NEXT: vpor %xmm3, %xmm2, %xmm3
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpackssdw %xmm3, %xmm4, %xmm3
; AVX1-NEXT: vpsubd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpandn %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: test13:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
; AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm3
; AVX2-NEXT: vpor %ymm2, %ymm0, %ymm2
; AVX2-NEXT: vpcmpgtd %ymm2, %ymm3, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
; AVX2-NEXT: vpackssdw %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpandn %xmm0, %xmm2, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: test13:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512-NEXT: vpcmpnltud %ymm1, %ymm0, %k1
; AVX512-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %ymm0, %xmm0 {%k1} {z}
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ult <8 x i32> %lhs, %y
%sub = sub <8 x i32> %lhs, %y
%trunc = trunc <8 x i32> %sub to <8 x i16>
%res = select <8 x i1> %cond, <8 x i16> zeroinitializer, <8 x i16> %trunc
ret <8 x i16> %res
}
define <16 x i8> @test14(<16 x i8> %x, <16 x i32> %y) nounwind {
; SSE2-LABEL: test14:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm0, %xmm5
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: movdqa %xmm5, %xmm6
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm0[0],xmm6[1],xmm0[1],xmm6[2],xmm0[2],xmm6[3],xmm0[3],xmm6[4],xmm0[4],xmm6[5],xmm0[5],xmm6[6],xmm0[6],xmm6[7],xmm0[7]
; SSE2-NEXT: movdqa %xmm6, %xmm8
; SSE2-NEXT: punpcklwd {{.*#+}} xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1],xmm8[2],xmm0[2],xmm8[3],xmm0[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm6 = xmm6[4],xmm0[4],xmm6[5],xmm0[5],xmm6[6],xmm0[6],xmm6[7],xmm0[7]
; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm0[8],xmm5[9],xmm0[9],xmm5[10],xmm0[10],xmm5[11],xmm0[11],xmm5[12],xmm0[12],xmm5[13],xmm0[13],xmm5[14],xmm0[14],xmm5[15],xmm0[15]
; SSE2-NEXT: movdqa %xmm5, %xmm10
; SSE2-NEXT: punpcklwd {{.*#+}} xmm10 = xmm10[0],xmm0[0],xmm10[1],xmm0[1],xmm10[2],xmm0[2],xmm10[3],xmm0[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm4, %xmm9
; SSE2-NEXT: pxor %xmm0, %xmm9
; SSE2-NEXT: psubd %xmm5, %xmm4
; SSE2-NEXT: por %xmm0, %xmm5
; SSE2-NEXT: pcmpgtd %xmm9, %xmm5
; SSE2-NEXT: movdqa {{.*#+}} xmm9 = [255,255,255,255]
; SSE2-NEXT: pand %xmm9, %xmm5
; SSE2-NEXT: movdqa %xmm3, %xmm7
; SSE2-NEXT: pxor %xmm0, %xmm7
; SSE2-NEXT: psubd %xmm10, %xmm3
; SSE2-NEXT: por %xmm0, %xmm10
; SSE2-NEXT: pcmpgtd %xmm7, %xmm10
; SSE2-NEXT: pand %xmm9, %xmm10
; SSE2-NEXT: packuswb %xmm5, %xmm10
; SSE2-NEXT: movdqa %xmm2, %xmm5
; SSE2-NEXT: pxor %xmm0, %xmm5
; SSE2-NEXT: psubd %xmm6, %xmm2
; SSE2-NEXT: por %xmm0, %xmm6
; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
; SSE2-NEXT: pand %xmm9, %xmm6
; SSE2-NEXT: movdqa %xmm1, %xmm5
; SSE2-NEXT: pxor %xmm0, %xmm5
; SSE2-NEXT: por %xmm8, %xmm0
; SSE2-NEXT: pcmpgtd %xmm5, %xmm0
; SSE2-NEXT: pand %xmm9, %xmm0
; SSE2-NEXT: packuswb %xmm6, %xmm0
; SSE2-NEXT: packuswb %xmm10, %xmm0
; SSE2-NEXT: psubd %xmm8, %xmm1
; SSE2-NEXT: pand %xmm9, %xmm4
; SSE2-NEXT: pand %xmm9, %xmm3
; SSE2-NEXT: packuswb %xmm4, %xmm3
; SSE2-NEXT: pand %xmm9, %xmm2
; SSE2-NEXT: pand %xmm9, %xmm1
; SSE2-NEXT: packuswb %xmm2, %xmm1
; SSE2-NEXT: packuswb %xmm3, %xmm1
; SSE2-NEXT: pandn %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test14:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa %xmm0, %xmm5
; SSSE3-NEXT: pxor %xmm0, %xmm0
; SSSE3-NEXT: movdqa %xmm5, %xmm7
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm7 = xmm7[8],xmm0[8],xmm7[9],xmm0[9],xmm7[10],xmm0[10],xmm7[11],xmm0[11],xmm7[12],xmm0[12],xmm7[13],xmm0[13],xmm7[14],xmm0[14],xmm7[15],xmm0[15]
; SSSE3-NEXT: movdqa %xmm7, %xmm8
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1],xmm8[2],xmm0[2],xmm8[3],xmm0[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm7 = xmm7[4],xmm0[4],xmm7[5],xmm0[5],xmm7[6],xmm0[6],xmm7[7],xmm0[7]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1],xmm5[2],xmm0[2],xmm5[3],xmm0[3],xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSSE3-NEXT: movdqa %xmm5, %xmm10
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm10 = xmm10[0],xmm0[0],xmm10[1],xmm0[1],xmm10[2],xmm0[2],xmm10[3],xmm0[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSSE3-NEXT: movdqa {{.*#+}} xmm0 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm2, %xmm9
; SSSE3-NEXT: pxor %xmm0, %xmm9
; SSSE3-NEXT: psubd %xmm5, %xmm2
; SSSE3-NEXT: por %xmm0, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm9, %xmm5
; SSSE3-NEXT: movdqa {{.*#+}} xmm9 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm9, %xmm5
; SSSE3-NEXT: movdqa %xmm1, %xmm6
; SSSE3-NEXT: pxor %xmm0, %xmm6
; SSSE3-NEXT: psubd %xmm10, %xmm1
; SSSE3-NEXT: por %xmm0, %xmm10
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm10
; SSSE3-NEXT: pshufb %xmm9, %xmm10
; SSSE3-NEXT: punpckldq {{.*#+}} xmm10 = xmm10[0],xmm5[0],xmm10[1],xmm5[1]
; SSSE3-NEXT: movdqa %xmm4, %xmm5
; SSSE3-NEXT: pxor %xmm0, %xmm5
; SSSE3-NEXT: psubd %xmm7, %xmm4
; SSSE3-NEXT: por %xmm0, %xmm7
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm7
; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm5, %xmm7
; SSSE3-NEXT: movdqa %xmm3, %xmm6
; SSSE3-NEXT: pxor %xmm0, %xmm6
; SSSE3-NEXT: por %xmm8, %xmm0
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm0
; SSSE3-NEXT: pshufb %xmm5, %xmm0
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1]
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm10[0],xmm0[1]
; SSSE3-NEXT: psubd %xmm8, %xmm3
; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSSE3-NEXT: pand %xmm5, %xmm4
; SSSE3-NEXT: pand %xmm5, %xmm3
; SSSE3-NEXT: packuswb %xmm4, %xmm3
; SSSE3-NEXT: pand %xmm5, %xmm2
; SSSE3-NEXT: pand %xmm5, %xmm1
; SSSE3-NEXT: packuswb %xmm2, %xmm1
; SSSE3-NEXT: packuswb %xmm3, %xmm1
; SSSE3-NEXT: andnpd %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test14:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movdqa %xmm0, %xmm5
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm8 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm0 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero,xmm5[2],zero,zero,zero,xmm5[3],zero,zero,zero
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm5[2,3,0,1]
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm9 = xmm6[0],zero,zero,zero,xmm6[1],zero,zero,zero,xmm6[2],zero,zero,zero,xmm6[3],zero,zero,zero
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm5[3,1,2,3]
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm6 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero,xmm5[2],zero,zero,zero,xmm5[3],zero,zero,zero
; SSE41-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
; SSE41-NEXT: movdqa %xmm4, %xmm7
; SSE41-NEXT: pxor %xmm5, %xmm7
; SSE41-NEXT: psubd %xmm6, %xmm4
; SSE41-NEXT: por %xmm5, %xmm6
; SSE41-NEXT: pcmpgtd %xmm7, %xmm6
; SSE41-NEXT: movdqa {{.*#+}} xmm10 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm10, %xmm6
; SSE41-NEXT: movdqa %xmm3, %xmm7
; SSE41-NEXT: pxor %xmm5, %xmm7
; SSE41-NEXT: psubd %xmm9, %xmm3
; SSE41-NEXT: por %xmm5, %xmm9
; SSE41-NEXT: pcmpgtd %xmm7, %xmm9
; SSE41-NEXT: pshufb %xmm10, %xmm9
; SSE41-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm6[0],xmm9[1],xmm6[1]
; SSE41-NEXT: movdqa %xmm1, %xmm6
; SSE41-NEXT: pxor %xmm5, %xmm6
; SSE41-NEXT: psubd %xmm0, %xmm1
; SSE41-NEXT: por %xmm5, %xmm0
; SSE41-NEXT: pcmpgtd %xmm6, %xmm0
; SSE41-NEXT: movdqa {{.*#+}} xmm6 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm6, %xmm0
; SSE41-NEXT: movdqa %xmm2, %xmm7
; SSE41-NEXT: pxor %xmm5, %xmm7
; SSE41-NEXT: por %xmm8, %xmm5
; SSE41-NEXT: pcmpgtd %xmm7, %xmm5
; SSE41-NEXT: pshufb %xmm6, %xmm5
; SSE41-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm9[4,5,6,7]
; SSE41-NEXT: psubd %xmm8, %xmm2
; SSE41-NEXT: movdqa {{.*#+}} xmm5 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE41-NEXT: pand %xmm5, %xmm4
; SSE41-NEXT: pand %xmm5, %xmm3
; SSE41-NEXT: packuswb %xmm4, %xmm3
; SSE41-NEXT: pand %xmm5, %xmm1
; SSE41-NEXT: pand %xmm5, %xmm2
; SSE41-NEXT: packuswb %xmm2, %xmm1
; SSE41-NEXT: packuswb %xmm3, %xmm1
; SSE41-NEXT: pandn %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: test14:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm8 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm9 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm0[2,3,0,1]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm10 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero,xmm5[2],zero,zero,zero,xmm5[3],zero,zero,zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm7
; AVX1-NEXT: vpxor %xmm6, %xmm7, %xmm3
; AVX1-NEXT: vpor %xmm6, %xmm0, %xmm4
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm4, %xmm3
; AVX1-NEXT: vpxor %xmm6, %xmm2, %xmm4
; AVX1-NEXT: vpor %xmm6, %xmm10, %xmm5
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vpackssdw %xmm3, %xmm4, %xmm11
; AVX1-NEXT: vpxor %xmm6, %xmm1, %xmm4
; AVX1-NEXT: vpor %xmm6, %xmm9, %xmm5
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpxor %xmm6, %xmm5, %xmm3
; AVX1-NEXT: vpor %xmm6, %xmm8, %xmm6
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpackssdw %xmm3, %xmm4, %xmm3
; AVX1-NEXT: vpacksswb %xmm11, %xmm3, %xmm3
; AVX1-NEXT: vpsubd %xmm8, %xmm5, %xmm4
; AVX1-NEXT: vpsubd %xmm9, %xmm1, %xmm1
; AVX1-NEXT: vpsubd %xmm10, %xmm2, %xmm2
; AVX1-NEXT: vpsubd %xmm0, %xmm7, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm5 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; AVX1-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpackuswb %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpand %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm5, %xmm4, %xmm2
; AVX1-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vpandn %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: test14:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero,xmm3[4],zero,zero,zero,xmm3[5],zero,zero,zero,xmm3[6],zero,zero,zero,xmm3[7],zero,zero,zero
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm4 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
; AVX2-NEXT: vpxor %ymm4, %ymm1, %ymm5
; AVX2-NEXT: vpor %ymm4, %ymm0, %ymm6
; AVX2-NEXT: vpcmpgtd %ymm5, %ymm6, %ymm5
; AVX2-NEXT: vextracti128 $1, %ymm5, %xmm6
; AVX2-NEXT: vpackssdw %xmm6, %xmm5, %xmm5
; AVX2-NEXT: vpxor %ymm4, %ymm2, %ymm6
; AVX2-NEXT: vpor %ymm4, %ymm3, %ymm4
; AVX2-NEXT: vpcmpgtd %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vextracti128 $1, %ymm4, %xmm6
; AVX2-NEXT: vpackssdw %xmm6, %xmm4, %xmm4
; AVX2-NEXT: vpacksswb %xmm4, %xmm5, %xmm4
; AVX2-NEXT: vpsubd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpsubd %ymm0, %ymm1, %ymm0
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpshufb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpshufb %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vpandn %xmm0, %xmm4, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: test14:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
; AVX512-NEXT: vpcmpnltud %zmm0, %zmm1, %k1
; AVX512-NEXT: vpsubd %zmm0, %zmm1, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0 {%k1} {z}
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%rhs = zext <16 x i8> %x to <16 x i32>
%cond = icmp ult <16 x i32> %y, %rhs
%sub = sub <16 x i32> %y, %rhs
%truncsub = trunc <16 x i32> %sub to <16 x i8>
%res = select <16 x i1> %cond, <16 x i8> zeroinitializer, <16 x i8> %truncsub
ret <16 x i8> %res
}
define <8 x i16> @test15(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: test15:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm3, %xmm5
; SSE2-NEXT: psubd %xmm2, %xmm3
; SSE2-NEXT: pxor %xmm4, %xmm2
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
; SSE2-NEXT: movdqa %xmm1, %xmm2
; SSE2-NEXT: pxor %xmm4, %xmm2
; SSE2-NEXT: por %xmm0, %xmm4
; SSE2-NEXT: pcmpgtd %xmm2, %xmm4
; SSE2-NEXT: packssdw %xmm5, %xmm4
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm3, %xmm0
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test15:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: pxor %xmm4, %xmm4
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm0, %xmm5
; SSSE3-NEXT: psubd %xmm2, %xmm0
; SSSE3-NEXT: pxor %xmm4, %xmm2
; SSSE3-NEXT: por %xmm4, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
; SSSE3-NEXT: movdqa %xmm1, %xmm2
; SSSE3-NEXT: pxor %xmm4, %xmm2
; SSSE3-NEXT: por %xmm3, %xmm4
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm4
; SSSE3-NEXT: packssdw %xmm5, %xmm4
; SSSE3-NEXT: psubd %xmm1, %xmm3
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: pshufb %xmm1, %xmm3
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: movdqa %xmm3, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test15:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE41-NEXT: movdqa %xmm0, %xmm5
; SSE41-NEXT: psubd %xmm1, %xmm0
; SSE41-NEXT: pxor %xmm4, %xmm1
; SSE41-NEXT: por %xmm4, %xmm5
; SSE41-NEXT: pcmpgtd %xmm1, %xmm5
; SSE41-NEXT: movdqa %xmm2, %xmm1
; SSE41-NEXT: pxor %xmm4, %xmm1
; SSE41-NEXT: por %xmm3, %xmm4
; SSE41-NEXT: pcmpgtd %xmm1, %xmm4
; SSE41-NEXT: packssdw %xmm4, %xmm5
; SSE41-NEXT: psubd %xmm2, %xmm3
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: pshufb %xmm1, %xmm3
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
; SSE41-NEXT: pand %xmm5, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: test15:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
; AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm4
; AVX1-NEXT: vpor %xmm3, %xmm0, %xmm5
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpxor %xmm3, %xmm5, %xmm6
; AVX1-NEXT: vpor %xmm3, %xmm2, %xmm3
; AVX1-NEXT: vpcmpgtd %xmm6, %xmm3, %xmm3
; AVX1-NEXT: vpackssdw %xmm3, %xmm4, %xmm3
; AVX1-NEXT: vpsubd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpand %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: test15:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
; AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm3
; AVX2-NEXT: vpor %ymm2, %ymm0, %ymm2
; AVX2-NEXT: vpcmpgtd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
; AVX2-NEXT: vpackssdw %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm0, %xmm2, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: test15:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512-NEXT: vpcmpnleud %ymm1, %ymm0, %k1
; AVX512-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %ymm0, %xmm0 {%k1} {z}
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ugt <8 x i32> %lhs, %y
%sub = sub <8 x i32> %lhs, %y
%truncsub = trunc <8 x i32> %sub to <8 x i16>
%res = select <8 x i1> %cond, <8 x i16> %truncsub, <8 x i16> zeroinitializer
ret <8 x i16> %res
}
define <8 x i16> @test16(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: test16:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm3, %xmm5
; SSE2-NEXT: psubd %xmm2, %xmm3
; SSE2-NEXT: pxor %xmm4, %xmm2
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
; SSE2-NEXT: movdqa %xmm1, %xmm2
; SSE2-NEXT: pxor %xmm4, %xmm2
; SSE2-NEXT: por %xmm0, %xmm4
; SSE2-NEXT: pcmpgtd %xmm2, %xmm4
; SSE2-NEXT: packssdw %xmm5, %xmm4
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm3, %xmm0
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: test16:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: pxor %xmm4, %xmm4
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm0, %xmm5
; SSSE3-NEXT: psubd %xmm2, %xmm0
; SSSE3-NEXT: pxor %xmm4, %xmm2
; SSSE3-NEXT: por %xmm4, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
; SSSE3-NEXT: movdqa %xmm1, %xmm2
; SSSE3-NEXT: pxor %xmm4, %xmm2
; SSSE3-NEXT: por %xmm3, %xmm4
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm4
; SSSE3-NEXT: packssdw %xmm5, %xmm4
; SSSE3-NEXT: psubd %xmm1, %xmm3
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: pshufb %xmm1, %xmm3
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: movdqa %xmm3, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: test16:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE41-NEXT: movdqa %xmm0, %xmm5
; SSE41-NEXT: psubd %xmm1, %xmm0
; SSE41-NEXT: pxor %xmm4, %xmm1
; SSE41-NEXT: por %xmm4, %xmm5
; SSE41-NEXT: pcmpgtd %xmm1, %xmm5
; SSE41-NEXT: movdqa %xmm2, %xmm1
; SSE41-NEXT: pxor %xmm4, %xmm1
; SSE41-NEXT: por %xmm3, %xmm4
; SSE41-NEXT: pcmpgtd %xmm1, %xmm4
; SSE41-NEXT: packssdw %xmm4, %xmm5
; SSE41-NEXT: psubd %xmm2, %xmm3
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: pshufb %xmm1, %xmm3
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
; SSE41-NEXT: pand %xmm5, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: test16:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
; AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm4
; AVX1-NEXT: vpor %xmm3, %xmm0, %xmm5
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpxor %xmm3, %xmm5, %xmm6
; AVX1-NEXT: vpor %xmm3, %xmm2, %xmm3
; AVX1-NEXT: vpcmpgtd %xmm6, %xmm3, %xmm3
; AVX1-NEXT: vpackssdw %xmm3, %xmm4, %xmm3
; AVX1-NEXT: vpsubd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vpand %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: test16:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
; AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm3
; AVX2-NEXT: vpor %ymm2, %ymm0, %ymm2
; AVX2-NEXT: vpcmpgtd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
; AVX2-NEXT: vpackssdw %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm0, %xmm2, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: test16:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512-NEXT: vpcmpltud %ymm0, %ymm1, %k1
; AVX512-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %ymm0, %xmm0 {%k1} {z}
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ult <8 x i32> %y, %lhs
%sub = sub <8 x i32> %lhs, %y
%truncsub = trunc <8 x i32> %sub to <8 x i16>
%res = select <8 x i1> %cond, <8 x i16> %truncsub, <8 x i16> zeroinitializer
ret <8 x i16> %res
}
define <8 x i16> @psubus_8i16_max(<8 x i16> %x, <8 x i16> %y) nounwind {
; SSE2-LABEL: psubus_8i16_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm2, %xmm3
; SSE2-NEXT: pxor %xmm1, %xmm2
; SSE2-NEXT: pcmpgtw %xmm3, %xmm2
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: pand %xmm2, %xmm3
; SSE2-NEXT: pandn %xmm0, %xmm2
; SSE2-NEXT: por %xmm3, %xmm2
; SSE2-NEXT: psubw %xmm1, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_8i16_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: pxor %xmm2, %xmm3
; SSSE3-NEXT: pxor %xmm1, %xmm2
; SSSE3-NEXT: pcmpgtw %xmm3, %xmm2
; SSSE3-NEXT: movdqa %xmm1, %xmm3
; SSSE3-NEXT: pand %xmm2, %xmm3
; SSSE3-NEXT: pandn %xmm0, %xmm2
; SSSE3-NEXT: por %xmm3, %xmm2
; SSSE3-NEXT: psubw %xmm1, %xmm2
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_8i16_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: psubusw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: psubus_8i16_max:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%cmp = icmp ult <8 x i16> %x, %y
%max = select <8 x i1> %cmp, <8 x i16> %y, <8 x i16> %x
%res = sub <8 x i16> %max, %y
ret <8 x i16> %res
}
define <16 x i8> @psubus_16i8_max(<16 x i8> %x, <16 x i8> %y) nounwind {
; SSE-LABEL: psubus_16i8_max:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: psubus_16i8_max:
; AVX: # %bb.0: # %vector.ph
; AVX-NEXT: vpsubusb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
vector.ph:
%cmp = icmp ult <16 x i8> %x, %y
%max = select <16 x i1> %cmp, <16 x i8> %y, <16 x i8> %x
%res = sub <16 x i8> %max, %y
ret <16 x i8> %res
}
define <16 x i16> @psubus_16i16_max(<16 x i16> %x, <16 x i16> %y) nounwind {
; SSE2-LABEL: psubus_16i16_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSE2-NEXT: movdqa %xmm0, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: movdqa %xmm2, %xmm5
; SSE2-NEXT: pxor %xmm4, %xmm5
; SSE2-NEXT: pcmpgtw %xmm6, %xmm5
; SSE2-NEXT: movdqa %xmm1, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: pxor %xmm3, %xmm4
; SSE2-NEXT: pcmpgtw %xmm6, %xmm4
; SSE2-NEXT: movdqa %xmm3, %xmm6
; SSE2-NEXT: pand %xmm4, %xmm6
; SSE2-NEXT: pandn %xmm1, %xmm4
; SSE2-NEXT: por %xmm6, %xmm4
; SSE2-NEXT: movdqa %xmm2, %xmm1
; SSE2-NEXT: pand %xmm5, %xmm1
; SSE2-NEXT: pandn %xmm0, %xmm5
; SSE2-NEXT: por %xmm1, %xmm5
; SSE2-NEXT: psubw %xmm2, %xmm5
; SSE2-NEXT: psubw %xmm3, %xmm4
; SSE2-NEXT: movdqa %xmm5, %xmm0
; SSE2-NEXT: movdqa %xmm4, %xmm1
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_16i16_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSSE3-NEXT: movdqa %xmm0, %xmm6
; SSSE3-NEXT: pxor %xmm4, %xmm6
; SSSE3-NEXT: movdqa %xmm2, %xmm5
; SSSE3-NEXT: pxor %xmm4, %xmm5
; SSSE3-NEXT: pcmpgtw %xmm6, %xmm5
; SSSE3-NEXT: movdqa %xmm1, %xmm6
; SSSE3-NEXT: pxor %xmm4, %xmm6
; SSSE3-NEXT: pxor %xmm3, %xmm4
; SSSE3-NEXT: pcmpgtw %xmm6, %xmm4
; SSSE3-NEXT: movdqa %xmm3, %xmm6
; SSSE3-NEXT: pand %xmm4, %xmm6
; SSSE3-NEXT: pandn %xmm1, %xmm4
; SSSE3-NEXT: por %xmm6, %xmm4
; SSSE3-NEXT: movdqa %xmm2, %xmm1
; SSSE3-NEXT: pand %xmm5, %xmm1
; SSSE3-NEXT: pandn %xmm0, %xmm5
; SSSE3-NEXT: por %xmm1, %xmm5
; SSSE3-NEXT: psubw %xmm2, %xmm5
; SSSE3-NEXT: psubw %xmm3, %xmm4
; SSSE3-NEXT: movdqa %xmm5, %xmm0
; SSSE3-NEXT: movdqa %xmm4, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_16i16_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: psubusw %xmm2, %xmm0
; SSE41-NEXT: psubusw %xmm3, %xmm1
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_16i16_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpsubusw %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_16i16_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_16i16_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusw %ymm1, %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%cmp = icmp ult <16 x i16> %x, %y
%max = select <16 x i1> %cmp, <16 x i16> %y, <16 x i16> %x
%res = sub <16 x i16> %max, %y
ret <16 x i16> %res
}
define <32 x i16> @psubus_32i16_max(<32 x i16> %x, <32 x i16> %y) nounwind {
; SSE2-LABEL: psubus_32i16_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm3, %xmm11
; SSE2-NEXT: movdqa %xmm2, %xmm10
; SSE2-NEXT: movdqa %xmm1, %xmm9
; SSE2-NEXT: movdqa %xmm0, %xmm8
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pxor %xmm3, %xmm1
; SSE2-NEXT: movdqa %xmm4, %xmm0
; SSE2-NEXT: pxor %xmm3, %xmm0
; SSE2-NEXT: pcmpgtw %xmm1, %xmm0
; SSE2-NEXT: movdqa %xmm9, %xmm2
; SSE2-NEXT: pxor %xmm3, %xmm2
; SSE2-NEXT: movdqa %xmm5, %xmm1
; SSE2-NEXT: pxor %xmm3, %xmm1
; SSE2-NEXT: pcmpgtw %xmm2, %xmm1
; SSE2-NEXT: movdqa %xmm10, %xmm12
; SSE2-NEXT: pxor %xmm3, %xmm12
; SSE2-NEXT: movdqa %xmm6, %xmm2
; SSE2-NEXT: pxor %xmm3, %xmm2
; SSE2-NEXT: pcmpgtw %xmm12, %xmm2
; SSE2-NEXT: movdqa %xmm11, %xmm12
; SSE2-NEXT: pxor %xmm3, %xmm12
; SSE2-NEXT: pxor %xmm7, %xmm3
; SSE2-NEXT: pcmpgtw %xmm12, %xmm3
; SSE2-NEXT: movdqa %xmm7, %xmm12
; SSE2-NEXT: pand %xmm3, %xmm12
; SSE2-NEXT: pandn %xmm11, %xmm3
; SSE2-NEXT: por %xmm12, %xmm3
; SSE2-NEXT: movdqa %xmm6, %xmm11
; SSE2-NEXT: pand %xmm2, %xmm11
; SSE2-NEXT: pandn %xmm10, %xmm2
; SSE2-NEXT: por %xmm11, %xmm2
; SSE2-NEXT: movdqa %xmm5, %xmm10
; SSE2-NEXT: pand %xmm1, %xmm10
; SSE2-NEXT: pandn %xmm9, %xmm1
; SSE2-NEXT: por %xmm10, %xmm1
; SSE2-NEXT: movdqa %xmm4, %xmm9
; SSE2-NEXT: pand %xmm0, %xmm9
; SSE2-NEXT: pandn %xmm8, %xmm0
; SSE2-NEXT: por %xmm9, %xmm0
; SSE2-NEXT: psubw %xmm4, %xmm0
; SSE2-NEXT: psubw %xmm5, %xmm1
; SSE2-NEXT: psubw %xmm6, %xmm2
; SSE2-NEXT: psubw %xmm7, %xmm3
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_32i16_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa %xmm3, %xmm11
; SSSE3-NEXT: movdqa %xmm2, %xmm10
; SSSE3-NEXT: movdqa %xmm1, %xmm9
; SSSE3-NEXT: movdqa %xmm0, %xmm8
; SSSE3-NEXT: movdqa {{.*#+}} xmm3 = [32768,32768,32768,32768,32768,32768,32768,32768]
; SSSE3-NEXT: movdqa %xmm0, %xmm1
; SSSE3-NEXT: pxor %xmm3, %xmm1
; SSSE3-NEXT: movdqa %xmm4, %xmm0
; SSSE3-NEXT: pxor %xmm3, %xmm0
; SSSE3-NEXT: pcmpgtw %xmm1, %xmm0
; SSSE3-NEXT: movdqa %xmm9, %xmm2
; SSSE3-NEXT: pxor %xmm3, %xmm2
; SSSE3-NEXT: movdqa %xmm5, %xmm1
; SSSE3-NEXT: pxor %xmm3, %xmm1
; SSSE3-NEXT: pcmpgtw %xmm2, %xmm1
; SSSE3-NEXT: movdqa %xmm10, %xmm12
; SSSE3-NEXT: pxor %xmm3, %xmm12
; SSSE3-NEXT: movdqa %xmm6, %xmm2
; SSSE3-NEXT: pxor %xmm3, %xmm2
; SSSE3-NEXT: pcmpgtw %xmm12, %xmm2
; SSSE3-NEXT: movdqa %xmm11, %xmm12
; SSSE3-NEXT: pxor %xmm3, %xmm12
; SSSE3-NEXT: pxor %xmm7, %xmm3
; SSSE3-NEXT: pcmpgtw %xmm12, %xmm3
; SSSE3-NEXT: movdqa %xmm7, %xmm12
; SSSE3-NEXT: pand %xmm3, %xmm12
; SSSE3-NEXT: pandn %xmm11, %xmm3
; SSSE3-NEXT: por %xmm12, %xmm3
; SSSE3-NEXT: movdqa %xmm6, %xmm11
; SSSE3-NEXT: pand %xmm2, %xmm11
; SSSE3-NEXT: pandn %xmm10, %xmm2
; SSSE3-NEXT: por %xmm11, %xmm2
; SSSE3-NEXT: movdqa %xmm5, %xmm10
; SSSE3-NEXT: pand %xmm1, %xmm10
; SSSE3-NEXT: pandn %xmm9, %xmm1
; SSSE3-NEXT: por %xmm10, %xmm1
; SSSE3-NEXT: movdqa %xmm4, %xmm9
; SSSE3-NEXT: pand %xmm0, %xmm9
; SSSE3-NEXT: pandn %xmm8, %xmm0
; SSSE3-NEXT: por %xmm9, %xmm0
; SSSE3-NEXT: psubw %xmm4, %xmm0
; SSSE3-NEXT: psubw %xmm5, %xmm1
; SSSE3-NEXT: psubw %xmm6, %xmm2
; SSSE3-NEXT: psubw %xmm7, %xmm3
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_32i16_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: psubusw %xmm4, %xmm0
; SSE41-NEXT: psubusw %xmm5, %xmm1
; SSE41-NEXT: psubusw %xmm6, %xmm2
; SSE41-NEXT: psubusw %xmm7, %xmm3
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_32i16_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpsubusw %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm6
; AVX1-NEXT: vpsubusw %xmm5, %xmm6, %xmm5
; AVX1-NEXT: vpsubusw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm0
; AVX1-NEXT: vpsubusw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_32i16_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusw %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpsubusw %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_32i16_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusw %zmm1, %zmm0, %zmm0
; AVX512-NEXT: retq
vector.ph:
%cmp = icmp ult <32 x i16> %x, %y
%max = select <32 x i1> %cmp, <32 x i16> %y, <32 x i16> %x
%res = sub <32 x i16> %max, %y
ret <32 x i16> %res
}
define <64 x i8> @psubus_64i8_max(<64 x i8> %x, <64 x i8> %y) nounwind {
; SSE-LABEL: psubus_64i8_max:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusb %xmm4, %xmm0
; SSE-NEXT: psubusb %xmm5, %xmm1
; SSE-NEXT: psubusb %xmm6, %xmm2
; SSE-NEXT: psubusb %xmm7, %xmm3
; SSE-NEXT: retq
;
; AVX1-LABEL: psubus_64i8_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
; AVX1-NEXT: vpsubusb %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm6
; AVX1-NEXT: vpsubusb %xmm5, %xmm6, %xmm5
; AVX1-NEXT: vpsubusb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm0
; AVX1-NEXT: vpsubusb %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_64i8_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpsubusb %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_64i8_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusb %zmm1, %zmm0, %zmm0
; AVX512-NEXT: retq
vector.ph:
%cmp = icmp ult <64 x i8> %x, %y
%max = select <64 x i1> %cmp, <64 x i8> %y, <64 x i8> %x
%res = sub <64 x i8> %max, %y
ret <64 x i8> %res
}
define <32 x i8> @psubus_32i8_max(<32 x i8> %x, <32 x i8> %y) nounwind {
; SSE-LABEL: psubus_32i8_max:
; SSE: # %bb.0: # %vector.ph
; SSE-NEXT: psubusb %xmm2, %xmm0
; SSE-NEXT: psubusb %xmm3, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: psubus_32i8_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpsubusb %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsubusb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_32i8_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpsubusb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_32i8_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpsubusb %ymm1, %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%cmp = icmp ult <32 x i8> %x, %y
%max = select <32 x i1> %cmp, <32 x i8> %y, <32 x i8> %x
%res = sub <32 x i8> %max, %y
ret <32 x i8> %res
}
define <8 x i16> @psubus_8i32_max(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_8i32_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: pxor %xmm5, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm6
; SSE2-NEXT: por %xmm5, %xmm6
; SSE2-NEXT: pcmpgtd %xmm6, %xmm0
; SSE2-NEXT: movdqa %xmm2, %xmm6
; SSE2-NEXT: pxor %xmm5, %xmm6
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
; SSE2-NEXT: movdqa %xmm2, %xmm5
; SSE2-NEXT: pand %xmm6, %xmm5
; SSE2-NEXT: pandn %xmm4, %xmm6
; SSE2-NEXT: por %xmm5, %xmm6
; SSE2-NEXT: movdqa %xmm1, %xmm4
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm3, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: psubd %xmm2, %xmm6
; SSE2-NEXT: pslld $16, %xmm6
; SSE2-NEXT: psrad $16, %xmm6
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm6, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_8i32_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: pxor %xmm0, %xmm0
; SSSE3-NEXT: movdqa %xmm3, %xmm4
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: pxor %xmm5, %xmm0
; SSSE3-NEXT: movdqa %xmm3, %xmm6
; SSSE3-NEXT: por %xmm5, %xmm6
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm0
; SSSE3-NEXT: movdqa %xmm2, %xmm6
; SSSE3-NEXT: pxor %xmm5, %xmm6
; SSSE3-NEXT: por %xmm4, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm6
; SSSE3-NEXT: movdqa %xmm2, %xmm5
; SSSE3-NEXT: pand %xmm6, %xmm5
; SSSE3-NEXT: pandn %xmm4, %xmm6
; SSSE3-NEXT: por %xmm5, %xmm6
; SSSE3-NEXT: movdqa %xmm1, %xmm4
; SSSE3-NEXT: pand %xmm0, %xmm4
; SSSE3-NEXT: pandn %xmm3, %xmm0
; SSSE3-NEXT: por %xmm4, %xmm0
; SSSE3-NEXT: psubd %xmm1, %xmm0
; SSSE3-NEXT: psubd %xmm2, %xmm6
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm6
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_8i32_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; SSE41-NEXT: pminud %xmm3, %xmm2
; SSE41-NEXT: pminud %xmm3, %xmm1
; SSE41-NEXT: packusdw %xmm2, %xmm1
; SSE41-NEXT: psubusw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_8i32_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; AVX1-NEXT: vpminud %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpminud %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_8i32_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [65535,65535,65535,65535,65535,65535,65535,65535]
; AVX2-NEXT: vpminud %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_8i32_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovusdw %ymm1, %xmm1
; AVX512-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ult <8 x i32> %lhs, %y
%max = select <8 x i1> %cond, <8 x i32> %y, <8 x i32> %lhs
%sub = sub <8 x i32> %max, %y
%res = trunc <8 x i32> %sub to <8 x i16>
ret <8 x i16> %res
}
define <8 x i16> @psubus_8i64_max(<8 x i16> %x, <8 x i64> %y) nounwind {
; SSE2-LABEL: psubus_8i64_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: pxor %xmm5, %xmm5
; SSE2-NEXT: movdqa %xmm0, %xmm10
; SSE2-NEXT: punpcklwd {{.*#+}} xmm10 = xmm10[0],xmm5[0],xmm10[1],xmm5[1],xmm10[2],xmm5[2],xmm10[3],xmm5[3]
; SSE2-NEXT: movdqa %xmm10, %xmm9
; SSE2-NEXT: punpckhdq {{.*#+}} xmm9 = xmm9[2],xmm5[2],xmm9[3],xmm5[3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm10 = xmm10[0],xmm5[0],xmm10[1],xmm5[1]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
; SSE2-NEXT: movdqa %xmm0, %xmm8
; SSE2-NEXT: punpckhdq {{.*#+}} xmm8 = xmm8[2],xmm5[2],xmm8[3],xmm5[3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
; SSE2-NEXT: movdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm3, %xmm5
; SSE2-NEXT: pxor %xmm6, %xmm5
; SSE2-NEXT: movdqa %xmm0, %xmm7
; SSE2-NEXT: por %xmm6, %xmm7
; SSE2-NEXT: movdqa %xmm5, %xmm11
; SSE2-NEXT: pcmpgtd %xmm7, %xmm11
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm11[0,0,2,2]
; SSE2-NEXT: pcmpeqd %xmm5, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
; SSE2-NEXT: pand %xmm12, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm11[1,1,3,3]
; SSE2-NEXT: por %xmm5, %xmm11
; SSE2-NEXT: movdqa %xmm4, %xmm5
; SSE2-NEXT: pxor %xmm6, %xmm5
; SSE2-NEXT: movdqa %xmm8, %xmm7
; SSE2-NEXT: por %xmm6, %xmm7
; SSE2-NEXT: movdqa %xmm5, %xmm12
; SSE2-NEXT: pcmpgtd %xmm7, %xmm12
; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm12[0,0,2,2]
; SSE2-NEXT: pcmpeqd %xmm5, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
; SSE2-NEXT: pand %xmm13, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm12[1,1,3,3]
; SSE2-NEXT: por %xmm5, %xmm12
; SSE2-NEXT: movdqa %xmm1, %xmm5
; SSE2-NEXT: pxor %xmm6, %xmm5
; SSE2-NEXT: movdqa %xmm10, %xmm7
; SSE2-NEXT: por %xmm6, %xmm7
; SSE2-NEXT: movdqa %xmm5, %xmm13
; SSE2-NEXT: pcmpgtd %xmm7, %xmm13
; SSE2-NEXT: pshufd {{.*#+}} xmm14 = xmm13[0,0,2,2]
; SSE2-NEXT: pcmpeqd %xmm5, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
; SSE2-NEXT: pand %xmm14, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm13[1,1,3,3]
; SSE2-NEXT: por %xmm7, %xmm13
; SSE2-NEXT: movdqa %xmm2, %xmm7
; SSE2-NEXT: pxor %xmm6, %xmm7
; SSE2-NEXT: por %xmm9, %xmm6
; SSE2-NEXT: movdqa %xmm7, %xmm5
; SSE2-NEXT: pcmpgtd %xmm6, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm14 = xmm5[0,0,2,2]
; SSE2-NEXT: pcmpeqd %xmm7, %xmm6
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm6[1,1,3,3]
; SSE2-NEXT: pand %xmm14, %xmm7
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[1,1,3,3]
; SSE2-NEXT: por %xmm7, %xmm6
; SSE2-NEXT: movdqa %xmm2, %xmm5
; SSE2-NEXT: pand %xmm6, %xmm5
; SSE2-NEXT: pandn %xmm9, %xmm6
; SSE2-NEXT: por %xmm5, %xmm6
; SSE2-NEXT: movdqa %xmm1, %xmm5
; SSE2-NEXT: pand %xmm13, %xmm5
; SSE2-NEXT: pandn %xmm10, %xmm13
; SSE2-NEXT: por %xmm5, %xmm13
; SSE2-NEXT: movdqa %xmm4, %xmm5
; SSE2-NEXT: pand %xmm12, %xmm5
; SSE2-NEXT: pandn %xmm8, %xmm12
; SSE2-NEXT: por %xmm5, %xmm12
; SSE2-NEXT: movdqa %xmm3, %xmm5
; SSE2-NEXT: pand %xmm11, %xmm5
; SSE2-NEXT: pandn %xmm0, %xmm11
; SSE2-NEXT: por %xmm5, %xmm11
; SSE2-NEXT: psubq %xmm3, %xmm11
; SSE2-NEXT: psubq %xmm4, %xmm12
; SSE2-NEXT: psubq %xmm1, %xmm13
; SSE2-NEXT: psubq %xmm2, %xmm6
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm13[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm12[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm11[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_8i64_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: pxor %xmm5, %xmm5
; SSSE3-NEXT: movdqa %xmm0, %xmm10
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm10 = xmm10[0],xmm5[0],xmm10[1],xmm5[1],xmm10[2],xmm5[2],xmm10[3],xmm5[3]
; SSSE3-NEXT: movdqa %xmm10, %xmm9
; SSSE3-NEXT: punpckhdq {{.*#+}} xmm9 = xmm9[2],xmm5[2],xmm9[3],xmm5[3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm10 = xmm10[0],xmm5[0],xmm10[1],xmm5[1]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
; SSSE3-NEXT: movdqa %xmm0, %xmm8
; SSSE3-NEXT: punpckhdq {{.*#+}} xmm8 = xmm8[2],xmm5[2],xmm8[3],xmm5[3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
; SSSE3-NEXT: movdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm3, %xmm5
; SSSE3-NEXT: pxor %xmm6, %xmm5
; SSSE3-NEXT: movdqa %xmm0, %xmm7
; SSSE3-NEXT: por %xmm6, %xmm7
; SSSE3-NEXT: movdqa %xmm5, %xmm11
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm11
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm11[0,0,2,2]
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm7
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
; SSSE3-NEXT: pand %xmm12, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm11 = xmm11[1,1,3,3]
; SSSE3-NEXT: por %xmm5, %xmm11
; SSSE3-NEXT: movdqa %xmm4, %xmm5
; SSSE3-NEXT: pxor %xmm6, %xmm5
; SSSE3-NEXT: movdqa %xmm8, %xmm7
; SSSE3-NEXT: por %xmm6, %xmm7
; SSSE3-NEXT: movdqa %xmm5, %xmm12
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm12
; SSSE3-NEXT: pshufd {{.*#+}} xmm13 = xmm12[0,0,2,2]
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm7
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
; SSSE3-NEXT: pand %xmm13, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm12[1,1,3,3]
; SSSE3-NEXT: por %xmm5, %xmm12
; SSSE3-NEXT: movdqa %xmm1, %xmm5
; SSSE3-NEXT: pxor %xmm6, %xmm5
; SSSE3-NEXT: movdqa %xmm10, %xmm7
; SSSE3-NEXT: por %xmm6, %xmm7
; SSSE3-NEXT: movdqa %xmm5, %xmm13
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm13
; SSSE3-NEXT: pshufd {{.*#+}} xmm14 = xmm13[0,0,2,2]
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm7
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
; SSSE3-NEXT: pand %xmm14, %xmm7
; SSSE3-NEXT: pshufd {{.*#+}} xmm13 = xmm13[1,1,3,3]
; SSSE3-NEXT: por %xmm7, %xmm13
; SSSE3-NEXT: movdqa %xmm2, %xmm7
; SSSE3-NEXT: pxor %xmm6, %xmm7
; SSSE3-NEXT: por %xmm9, %xmm6
; SSSE3-NEXT: movdqa %xmm7, %xmm5
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm14 = xmm5[0,0,2,2]
; SSSE3-NEXT: pcmpeqd %xmm7, %xmm6
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm6[1,1,3,3]
; SSSE3-NEXT: pand %xmm14, %xmm7
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm5[1,1,3,3]
; SSSE3-NEXT: por %xmm7, %xmm6
; SSSE3-NEXT: movdqa %xmm2, %xmm5
; SSSE3-NEXT: pand %xmm6, %xmm5
; SSSE3-NEXT: pandn %xmm9, %xmm6
; SSSE3-NEXT: por %xmm5, %xmm6
; SSSE3-NEXT: movdqa %xmm1, %xmm5
; SSSE3-NEXT: pand %xmm13, %xmm5
; SSSE3-NEXT: pandn %xmm10, %xmm13
; SSSE3-NEXT: por %xmm5, %xmm13
; SSSE3-NEXT: movdqa %xmm4, %xmm5
; SSSE3-NEXT: pand %xmm12, %xmm5
; SSSE3-NEXT: pandn %xmm8, %xmm12
; SSSE3-NEXT: por %xmm5, %xmm12
; SSSE3-NEXT: movdqa %xmm3, %xmm5
; SSSE3-NEXT: pand %xmm11, %xmm5
; SSSE3-NEXT: pandn %xmm0, %xmm11
; SSSE3-NEXT: por %xmm5, %xmm11
; SSSE3-NEXT: psubq %xmm3, %xmm11
; SSSE3-NEXT: psubq %xmm4, %xmm12
; SSSE3-NEXT: psubq %xmm1, %xmm13
; SSSE3-NEXT: psubq %xmm2, %xmm6
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm13[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm12[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm2 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm11[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_8i64_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm0[3,1,2,3]
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm11 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm0[2,3,0,1]
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm12 = xmm5[0],zero,zero,zero,xmm5[1],zero,zero,zero
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm13 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm10 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [2147483648,2147483648,2147483648,2147483648]
; SSE41-NEXT: movdqa %xmm2, %xmm6
; SSE41-NEXT: pxor %xmm0, %xmm6
; SSE41-NEXT: movdqa %xmm10, %xmm7
; SSE41-NEXT: por %xmm0, %xmm7
; SSE41-NEXT: movdqa %xmm6, %xmm5
; SSE41-NEXT: pcmpgtd %xmm7, %xmm5
; SSE41-NEXT: pshufd {{.*#+}} xmm8 = xmm5[0,0,2,2]
; SSE41-NEXT: pcmpeqd %xmm6, %xmm7
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm7[1,1,3,3]
; SSE41-NEXT: pand %xmm8, %xmm6
; SSE41-NEXT: pshufd {{.*#+}} xmm8 = xmm5[1,1,3,3]
; SSE41-NEXT: por %xmm6, %xmm8
; SSE41-NEXT: movdqa %xmm1, %xmm5
; SSE41-NEXT: pxor %xmm0, %xmm5
; SSE41-NEXT: movdqa %xmm13, %xmm6
; SSE41-NEXT: por %xmm0, %xmm6
; SSE41-NEXT: movdqa %xmm5, %xmm7
; SSE41-NEXT: pcmpgtd %xmm6, %xmm7
; SSE41-NEXT: pshufd {{.*#+}} xmm9 = xmm7[0,0,2,2]
; SSE41-NEXT: pcmpeqd %xmm5, %xmm6
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
; SSE41-NEXT: pand %xmm9, %xmm5
; SSE41-NEXT: pshufd {{.*#+}} xmm9 = xmm7[1,1,3,3]
; SSE41-NEXT: por %xmm5, %xmm9
; SSE41-NEXT: movdqa %xmm3, %xmm5
; SSE41-NEXT: pxor %xmm0, %xmm5
; SSE41-NEXT: movdqa %xmm12, %xmm6
; SSE41-NEXT: por %xmm0, %xmm6
; SSE41-NEXT: movdqa %xmm5, %xmm7
; SSE41-NEXT: pcmpgtd %xmm6, %xmm7
; SSE41-NEXT: pshufd {{.*#+}} xmm14 = xmm7[0,0,2,2]
; SSE41-NEXT: pcmpeqd %xmm5, %xmm6
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
; SSE41-NEXT: pand %xmm14, %xmm5
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm7[1,1,3,3]
; SSE41-NEXT: por %xmm5, %xmm6
; SSE41-NEXT: movdqa %xmm4, %xmm5
; SSE41-NEXT: pxor %xmm0, %xmm5
; SSE41-NEXT: por %xmm11, %xmm0
; SSE41-NEXT: movdqa %xmm5, %xmm7
; SSE41-NEXT: pcmpgtd %xmm0, %xmm7
; SSE41-NEXT: pshufd {{.*#+}} xmm14 = xmm7[0,0,2,2]
; SSE41-NEXT: pcmpeqd %xmm5, %xmm0
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
; SSE41-NEXT: pand %xmm14, %xmm5
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm7[1,1,3,3]
; SSE41-NEXT: por %xmm5, %xmm0
; SSE41-NEXT: blendvpd %xmm0, %xmm4, %xmm11
; SSE41-NEXT: movdqa %xmm6, %xmm0
; SSE41-NEXT: blendvpd %xmm0, %xmm3, %xmm12
; SSE41-NEXT: movdqa %xmm9, %xmm0
; SSE41-NEXT: blendvpd %xmm0, %xmm1, %xmm13
; SSE41-NEXT: movdqa %xmm8, %xmm0
; SSE41-NEXT: blendvpd %xmm0, %xmm2, %xmm10
; SSE41-NEXT: psubq %xmm2, %xmm10
; SSE41-NEXT: psubq %xmm1, %xmm13
; SSE41-NEXT: psubq %xmm3, %xmm12
; SSE41-NEXT: psubq %xmm4, %xmm11
; SSE41-NEXT: pxor %xmm0, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm11 = xmm11[0],xmm0[1,2,3],xmm11[4],xmm0[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm12 = xmm12[0],xmm0[1,2,3],xmm12[4],xmm0[5,6,7]
; SSE41-NEXT: packusdw %xmm11, %xmm12
; SSE41-NEXT: pblendw {{.*#+}} xmm13 = xmm13[0],xmm0[1,2,3],xmm13[4],xmm0[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm10 = xmm10[0],xmm0[1,2,3],xmm10[4],xmm0[5,6,7]
; SSE41-NEXT: packusdw %xmm10, %xmm13
; SSE41-NEXT: packusdw %xmm12, %xmm13
; SSE41-NEXT: movdqa %xmm13, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_8i64_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm0[3,1,2,3]
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,xmm4[1],zero,zero,zero
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm8
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm6 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm6, %ymm9
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm10
; AVX1-NEXT: vmovdqa {{.*#+}} xmm7 = [9223372036854775808,9223372036854775808]
; AVX1-NEXT: vpxor %xmm7, %xmm10, %xmm5
; AVX1-NEXT: vpor %xmm7, %xmm4, %xmm4
; AVX1-NEXT: vpcmpgtq %xmm4, %xmm5, %xmm4
; AVX1-NEXT: vpxor %xmm7, %xmm2, %xmm5
; AVX1-NEXT: vpor %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vpcmpgtq %xmm3, %xmm5, %xmm3
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
; AVX1-NEXT: vpxor %xmm7, %xmm4, %xmm5
; AVX1-NEXT: vpor %xmm7, %xmm0, %xmm0
; AVX1-NEXT: vpcmpgtq %xmm0, %xmm5, %xmm0
; AVX1-NEXT: vpor %xmm7, %xmm6, %xmm5
; AVX1-NEXT: vpxor %xmm7, %xmm1, %xmm6
; AVX1-NEXT: vpcmpgtq %xmm5, %xmm6, %xmm5
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm5, %ymm0
; AVX1-NEXT: vblendvpd %ymm0, %ymm1, %ymm9, %ymm0
; AVX1-NEXT: vblendvpd %ymm3, %ymm2, %ymm8, %ymm3
; AVX1-NEXT: vpsubq %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vpsubq %xmm10, %xmm3, %xmm3
; AVX1-NEXT: vpsubq %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubq %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpxor %xmm4, %xmm4, %xmm4
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
; AVX1-NEXT: vpackusdw %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: psubus_8i64_max:
; AVX2-SLOW: # %bb.0: # %vector.ph
; AVX2-SLOW-NEXT: vpmovzxwq {{.*#+}} ymm3 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX2-SLOW-NEXT: vpmovzxwq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm4 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-SLOW-NEXT: vpxor %ymm4, %ymm2, %ymm5
; AVX2-SLOW-NEXT: vpor %ymm4, %ymm0, %ymm6
; AVX2-SLOW-NEXT: vpcmpgtq %ymm6, %ymm5, %ymm5
; AVX2-SLOW-NEXT: vpxor %ymm4, %ymm1, %ymm6
; AVX2-SLOW-NEXT: vpor %ymm4, %ymm3, %ymm4
; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm6, %ymm4
; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm1, %ymm3, %ymm3
; AVX2-SLOW-NEXT: vblendvpd %ymm5, %ymm2, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsubq %ymm2, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsubq %ymm1, %ymm3, %ymm1
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: psubus_8i64_max:
; AVX2-FAST: # %bb.0: # %vector.ph
; AVX2-FAST-NEXT: vpmovzxwq {{.*#+}} ymm3 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX2-FAST-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX2-FAST-NEXT: vpmovzxwq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX2-FAST-NEXT: vpbroadcastq {{.*#+}} ymm4 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-FAST-NEXT: vpxor %ymm4, %ymm2, %ymm5
; AVX2-FAST-NEXT: vpor %ymm4, %ymm0, %ymm6
; AVX2-FAST-NEXT: vpcmpgtq %ymm6, %ymm5, %ymm5
; AVX2-FAST-NEXT: vpxor %ymm4, %ymm1, %ymm6
; AVX2-FAST-NEXT: vpor %ymm4, %ymm3, %ymm4
; AVX2-FAST-NEXT: vpcmpgtq %ymm4, %ymm6, %ymm4
; AVX2-FAST-NEXT: vblendvpd %ymm4, %ymm1, %ymm3, %ymm3
; AVX2-FAST-NEXT: vblendvpd %ymm5, %ymm2, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpsubq %ymm2, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpsubq %ymm1, %ymm3, %ymm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: psubus_8i64_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovusqw %zmm1, %xmm1
; AVX512-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i64>
%cond = icmp ult <8 x i64> %lhs, %y
%max = select <8 x i1> %cond, <8 x i64> %y, <8 x i64> %lhs
%sub = sub <8 x i64> %max, %y
%res = trunc <8 x i64> %sub to <8 x i16>
ret <8 x i16> %res
}
define <16 x i16> @psubus_16i32_max(<16 x i16> %x, <16 x i32> %y) nounwind {
; SSE2-LABEL: psubus_16i32_max:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm1, %xmm8
; SSE2-NEXT: movdqa %xmm0, %xmm9
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: movdqa %xmm9, %xmm11
; SSE2-NEXT: punpckhwd {{.*#+}} xmm11 = xmm11[4],xmm0[4],xmm11[5],xmm0[5],xmm11[6],xmm0[6],xmm11[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm9 = xmm9[0],xmm0[0],xmm9[1],xmm0[1],xmm9[2],xmm0[2],xmm9[3],xmm0[3]
; SSE2-NEXT: movdqa %xmm1, %xmm10
; SSE2-NEXT: punpckhwd {{.*#+}} xmm10 = xmm10[4],xmm0[4],xmm10[5],xmm0[5],xmm10[6],xmm0[6],xmm10[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1],xmm8[2],xmm0[2],xmm8[3],xmm0[3]
; SSE2-NEXT: movdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm4, %xmm1
; SSE2-NEXT: pxor %xmm6, %xmm1
; SSE2-NEXT: movdqa %xmm8, %xmm0
; SSE2-NEXT: por %xmm6, %xmm0
; SSE2-NEXT: pcmpgtd %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm5, %xmm12
; SSE2-NEXT: pxor %xmm6, %xmm12
; SSE2-NEXT: movdqa %xmm10, %xmm0
; SSE2-NEXT: por %xmm6, %xmm0
; SSE2-NEXT: pcmpgtd %xmm0, %xmm12
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: pxor %xmm6, %xmm0
; SSE2-NEXT: movdqa %xmm9, %xmm7
; SSE2-NEXT: por %xmm6, %xmm7
; SSE2-NEXT: pcmpgtd %xmm7, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm7
; SSE2-NEXT: pxor %xmm6, %xmm7
; SSE2-NEXT: por %xmm11, %xmm6
; SSE2-NEXT: pcmpgtd %xmm6, %xmm7
; SSE2-NEXT: movdqa %xmm3, %xmm6
; SSE2-NEXT: pand %xmm7, %xmm6
; SSE2-NEXT: pandn %xmm11, %xmm7
; SSE2-NEXT: por %xmm6, %xmm7
; SSE2-NEXT: movdqa %xmm2, %xmm6
; SSE2-NEXT: pand %xmm0, %xmm6
; SSE2-NEXT: pandn %xmm9, %xmm0
; SSE2-NEXT: por %xmm6, %xmm0
; SSE2-NEXT: movdqa %xmm5, %xmm6
; SSE2-NEXT: pand %xmm12, %xmm6
; SSE2-NEXT: pandn %xmm10, %xmm12
; SSE2-NEXT: por %xmm6, %xmm12
; SSE2-NEXT: movdqa %xmm4, %xmm6
; SSE2-NEXT: pand %xmm1, %xmm6
; SSE2-NEXT: pandn %xmm8, %xmm1
; SSE2-NEXT: por %xmm6, %xmm1
; SSE2-NEXT: psubd %xmm4, %xmm1
; SSE2-NEXT: psubd %xmm5, %xmm12
; SSE2-NEXT: psubd %xmm2, %xmm0
; SSE2-NEXT: psubd %xmm3, %xmm7
; SSE2-NEXT: pslld $16, %xmm7
; SSE2-NEXT: psrad $16, %xmm7
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm7, %xmm0
; SSE2-NEXT: pslld $16, %xmm12
; SSE2-NEXT: psrad $16, %xmm12
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: packssdw %xmm12, %xmm1
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_16i32_max:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa %xmm1, %xmm8
; SSSE3-NEXT: movdqa %xmm0, %xmm9
; SSSE3-NEXT: pxor %xmm0, %xmm0
; SSSE3-NEXT: movdqa %xmm9, %xmm11
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm11 = xmm11[4],xmm0[4],xmm11[5],xmm0[5],xmm11[6],xmm0[6],xmm11[7],xmm0[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm9 = xmm9[0],xmm0[0],xmm9[1],xmm0[1],xmm9[2],xmm0[2],xmm9[3],xmm0[3]
; SSSE3-NEXT: movdqa %xmm1, %xmm10
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm10 = xmm10[4],xmm0[4],xmm10[5],xmm0[5],xmm10[6],xmm0[6],xmm10[7],xmm0[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1],xmm8[2],xmm0[2],xmm8[3],xmm0[3]
; SSSE3-NEXT: movdqa {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm4, %xmm1
; SSSE3-NEXT: pxor %xmm6, %xmm1
; SSSE3-NEXT: movdqa %xmm8, %xmm0
; SSSE3-NEXT: por %xmm6, %xmm0
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm1
; SSSE3-NEXT: movdqa %xmm5, %xmm12
; SSSE3-NEXT: pxor %xmm6, %xmm12
; SSSE3-NEXT: movdqa %xmm10, %xmm0
; SSSE3-NEXT: por %xmm6, %xmm0
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm12
; SSSE3-NEXT: movdqa %xmm2, %xmm0
; SSSE3-NEXT: pxor %xmm6, %xmm0
; SSSE3-NEXT: movdqa %xmm9, %xmm7
; SSSE3-NEXT: por %xmm6, %xmm7
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm0
; SSSE3-NEXT: movdqa %xmm3, %xmm7
; SSSE3-NEXT: pxor %xmm6, %xmm7
; SSSE3-NEXT: por %xmm11, %xmm6
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm7
; SSSE3-NEXT: movdqa %xmm3, %xmm6
; SSSE3-NEXT: pand %xmm7, %xmm6
; SSSE3-NEXT: pandn %xmm11, %xmm7
; SSSE3-NEXT: por %xmm6, %xmm7
; SSSE3-NEXT: movdqa %xmm2, %xmm6
; SSSE3-NEXT: pand %xmm0, %xmm6
; SSSE3-NEXT: pandn %xmm9, %xmm0
; SSSE3-NEXT: por %xmm6, %xmm0
; SSSE3-NEXT: movdqa %xmm5, %xmm6
; SSSE3-NEXT: pand %xmm12, %xmm6
; SSSE3-NEXT: pandn %xmm10, %xmm12
; SSSE3-NEXT: por %xmm6, %xmm12
; SSSE3-NEXT: movdqa %xmm4, %xmm6
; SSSE3-NEXT: pand %xmm1, %xmm6
; SSSE3-NEXT: pandn %xmm8, %xmm1
; SSSE3-NEXT: por %xmm6, %xmm1
; SSSE3-NEXT: psubd %xmm4, %xmm1
; SSSE3-NEXT: psubd %xmm5, %xmm12
; SSSE3-NEXT: psubd %xmm2, %xmm0
; SSSE3-NEXT: psubd %xmm3, %xmm7
; SSSE3-NEXT: pslld $16, %xmm7
; SSSE3-NEXT: psrad $16, %xmm7
; SSSE3-NEXT: pslld $16, %xmm0
; SSSE3-NEXT: psrad $16, %xmm0
; SSSE3-NEXT: packssdw %xmm7, %xmm0
; SSSE3-NEXT: pslld $16, %xmm12
; SSSE3-NEXT: psrad $16, %xmm12
; SSSE3-NEXT: pslld $16, %xmm1
; SSSE3-NEXT: psrad $16, %xmm1
; SSSE3-NEXT: packssdw %xmm12, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_16i32_max:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm1[2,3,0,1]
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm6 = xmm6[0],zero,xmm6[1],zero,xmm6[2],zero,xmm6[3],zero
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
; SSE41-NEXT: pshufd {{.*#+}} xmm7 = xmm0[2,3,0,1]
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm7 = xmm7[0],zero,xmm7[1],zero,xmm7[2],zero,xmm7[3],zero
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; SSE41-NEXT: pmaxud %xmm2, %xmm0
; SSE41-NEXT: pmaxud %xmm3, %xmm7
; SSE41-NEXT: pmaxud %xmm4, %xmm1
; SSE41-NEXT: pmaxud %xmm5, %xmm6
; SSE41-NEXT: psubd %xmm5, %xmm6
; SSE41-NEXT: psubd %xmm4, %xmm1
; SSE41-NEXT: psubd %xmm3, %xmm7
; SSE41-NEXT: psubd %xmm2, %xmm0
; SSE41-NEXT: pxor %xmm2, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3],xmm0[4],xmm2[5],xmm0[6],xmm2[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm7 = xmm7[0],xmm2[1],xmm7[2],xmm2[3],xmm7[4],xmm2[5],xmm7[6],xmm2[7]
; SSE41-NEXT: packusdw %xmm7, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm6 = xmm6[0],xmm2[1],xmm6[2],xmm2[3],xmm6[4],xmm2[5],xmm6[6],xmm2[7]
; SSE41-NEXT: packusdw %xmm6, %xmm1
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_16i32_max:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vmovdqa {{.*#+}} xmm4 = [65535,65535,65535,65535]
; AVX1-NEXT: vpminud %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpminud %xmm4, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm3
; AVX1-NEXT: vpminud %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpminud %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpsubusw %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_16i32_max:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm3 = [65535,65535,65535,65535,65535,65535,65535,65535]
; AVX2-NEXT: vpminud %ymm3, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm4
; AVX2-NEXT: vpackusdw %xmm4, %xmm1, %xmm1
; AVX2-NEXT: vpminud %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
; AVX2-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4
; AVX2-NEXT: vpackusdw %xmm4, %xmm3, %xmm3
; AVX2-NEXT: vpsubusw %xmm1, %xmm3, %xmm1
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX2-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpsubusw %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_16i32_max:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovusdw %zmm1, %ymm1
; AVX512-NEXT: vpsubusw %ymm1, %ymm0, %ymm0
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <16 x i16> %x to <16 x i32>
%cond = icmp ult <16 x i32> %lhs, %y
%max = select <16 x i1> %cond, <16 x i32> %y, <16 x i32> %lhs
%sub = sub <16 x i32> %max, %y
%res = trunc <16 x i32> %sub to <16 x i16>
ret <16 x i16> %res
}
define <8 x i16> @psubus_i16_i32_max_swapped(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_i16_i32_max_swapped:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm5
; SSE2-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm1, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: movdqa %xmm3, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: pcmpgtd %xmm6, %xmm0
; SSE2-NEXT: movdqa %xmm2, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: por %xmm5, %xmm4
; SSE2-NEXT: pcmpgtd %xmm6, %xmm4
; SSE2-NEXT: pand %xmm4, %xmm5
; SSE2-NEXT: pandn %xmm2, %xmm4
; SSE2-NEXT: por %xmm5, %xmm4
; SSE2-NEXT: pand %xmm0, %xmm3
; SSE2-NEXT: pandn %xmm1, %xmm0
; SSE2-NEXT: por %xmm3, %xmm0
; SSE2-NEXT: psubd %xmm1, %xmm0
; SSE2-NEXT: psubd %xmm2, %xmm4
; SSE2-NEXT: pslld $16, %xmm4
; SSE2-NEXT: psrad $16, %xmm4
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_i16_i32_max_swapped:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: pxor %xmm0, %xmm0
; SSSE3-NEXT: movdqa %xmm3, %xmm5
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3]
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm1, %xmm6
; SSSE3-NEXT: pxor %xmm4, %xmm6
; SSSE3-NEXT: movdqa %xmm3, %xmm0
; SSSE3-NEXT: por %xmm4, %xmm0
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm0
; SSSE3-NEXT: movdqa %xmm2, %xmm6
; SSSE3-NEXT: pxor %xmm4, %xmm6
; SSSE3-NEXT: por %xmm5, %xmm4
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm4
; SSSE3-NEXT: pand %xmm4, %xmm5
; SSSE3-NEXT: pandn %xmm2, %xmm4
; SSSE3-NEXT: por %xmm5, %xmm4
; SSSE3-NEXT: pand %xmm0, %xmm3
; SSSE3-NEXT: pandn %xmm1, %xmm0
; SSSE3-NEXT: por %xmm3, %xmm0
; SSSE3-NEXT: psubd %xmm1, %xmm0
; SSSE3-NEXT: psubd %xmm2, %xmm4
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm4
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_i16_i32_max_swapped:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; SSE41-NEXT: pminud %xmm3, %xmm2
; SSE41-NEXT: pminud %xmm3, %xmm1
; SSE41-NEXT: packusdw %xmm2, %xmm1
; SSE41-NEXT: psubusw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_i16_i32_max_swapped:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; AVX1-NEXT: vpminud %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpminud %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_i16_i32_max_swapped:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [65535,65535,65535,65535,65535,65535,65535,65535]
; AVX2-NEXT: vpminud %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_i16_i32_max_swapped:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovusdw %ymm1, %xmm1
; AVX512-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ult <8 x i32> %y, %lhs
%max = select <8 x i1> %cond, <8 x i32> %lhs, <8 x i32> %y
%sub = sub <8 x i32> %max, %y
%res = trunc <8 x i32> %sub to <8 x i16>
ret <8 x i16> %res
}
define <8 x i16> @psubus_i16_i32_min(<8 x i16> %x, <8 x i32> %y) nounwind {
; SSE2-LABEL: psubus_i16_i32_min:
; SSE2: # %bb.0: # %vector.ph
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSE2-NEXT: movdqa %xmm1, %xmm5
; SSE2-NEXT: pxor %xmm4, %xmm5
; SSE2-NEXT: movdqa %xmm0, %xmm6
; SSE2-NEXT: por %xmm4, %xmm6
; SSE2-NEXT: pcmpgtd %xmm6, %xmm5
; SSE2-NEXT: movdqa %xmm2, %xmm6
; SSE2-NEXT: pxor %xmm4, %xmm6
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: pcmpgtd %xmm4, %xmm6
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: pand %xmm6, %xmm4
; SSE2-NEXT: pandn %xmm2, %xmm6
; SSE2-NEXT: por %xmm4, %xmm6
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: pand %xmm5, %xmm2
; SSE2-NEXT: pandn %xmm1, %xmm5
; SSE2-NEXT: por %xmm2, %xmm5
; SSE2-NEXT: psubd %xmm5, %xmm0
; SSE2-NEXT: psubd %xmm6, %xmm3
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm3, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: psubus_i16_i32_min:
; SSSE3: # %bb.0: # %vector.ph
; SSSE3-NEXT: pxor %xmm4, %xmm4
; SSSE3-NEXT: movdqa %xmm0, %xmm3
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
; SSSE3-NEXT: movdqa %xmm1, %xmm5
; SSSE3-NEXT: pxor %xmm4, %xmm5
; SSSE3-NEXT: movdqa %xmm0, %xmm6
; SSSE3-NEXT: por %xmm4, %xmm6
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm5
; SSSE3-NEXT: movdqa %xmm2, %xmm6
; SSSE3-NEXT: pxor %xmm4, %xmm6
; SSSE3-NEXT: por %xmm3, %xmm4
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm6
; SSSE3-NEXT: movdqa %xmm3, %xmm4
; SSSE3-NEXT: pand %xmm6, %xmm4
; SSSE3-NEXT: pandn %xmm2, %xmm6
; SSSE3-NEXT: por %xmm4, %xmm6
; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: pand %xmm5, %xmm2
; SSSE3-NEXT: pandn %xmm1, %xmm5
; SSSE3-NEXT: por %xmm2, %xmm5
; SSSE3-NEXT: psubd %xmm5, %xmm0
; SSSE3-NEXT: psubd %xmm6, %xmm3
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm1, %xmm3
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: psubus_i16_i32_min:
; SSE41: # %bb.0: # %vector.ph
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; SSE41-NEXT: pminud %xmm3, %xmm2
; SSE41-NEXT: pminud %xmm3, %xmm1
; SSE41-NEXT: packusdw %xmm2, %xmm1
; SSE41-NEXT: psubusw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: psubus_i16_i32_min:
; AVX1: # %bb.0: # %vector.ph
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [65535,65535,65535,65535]
; AVX1-NEXT: vpminud %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpminud %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: psubus_i16_i32_min:
; AVX2: # %bb.0: # %vector.ph
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm2 = [65535,65535,65535,65535,65535,65535,65535,65535]
; AVX2-NEXT: vpminud %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: psubus_i16_i32_min:
; AVX512: # %bb.0: # %vector.ph
; AVX512-NEXT: vpmovusdw %ymm1, %xmm1
; AVX512-NEXT: vpsubusw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
vector.ph:
%lhs = zext <8 x i16> %x to <8 x i32>
%cond = icmp ult <8 x i32> %lhs, %y
%min = select <8 x i1> %cond, <8 x i32> %lhs, <8 x i32> %y
%sub = sub <8 x i32> %lhs, %min
%res = trunc <8 x i32> %sub to <8 x i16>
ret <8 x i16> %res
}
Reference in New Issue View Git Blame Copy Permalink