forked from OSchip/llvm-project
2112 lines
95 KiB
LLVM
2112 lines
95 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+sse2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-SSE --check-prefix=X86-SSE2
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+sse4.2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-SSE --check-prefix=X86-SSE42
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=X86 --check-prefix=X86-AVX --check-prefix=X86-AVX1
|
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-AVX --check-prefix=X86-AVX2
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+sse2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE --check-prefix=X64-SSE2
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+sse4.2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE --check-prefix=X64-SSE42
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX1
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX2
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f,+avx512bw,+avx512dq,+avx512vl | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX --check-prefix=X64-AVX512
|
|
|
|
;
|
|
; 128-bit Vectors
|
|
;
|
|
|
|
define i64 @test_reduce_v2i64(<2 x i64> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v2i64:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2]
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm3, %xmm2
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm2
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: movd %xmm3, %eax
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X86-SSE2-NEXT: movd %xmm0, %edx
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v2i64:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; X86-SSE42-NEXT: movdqa {{.*#+}} xmm0 = [0,2147483648,0,2147483648]
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm3
|
|
; X86-SSE42-NEXT: pxor %xmm0, %xmm3
|
|
; X86-SSE42-NEXT: pxor %xmm2, %xmm0
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm2
|
|
; X86-SSE42-NEXT: movd %xmm2, %eax
|
|
; X86-SSE42-NEXT: pextrd $1, %xmm2, %edx
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: test_reduce_v2i64:
|
|
; X86-AVX: ## %bb.0:
|
|
; X86-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [0,2147483648,0,2147483648]
|
|
; X86-AVX-NEXT: vpxor %xmm2, %xmm0, %xmm3
|
|
; X86-AVX-NEXT: vpxor %xmm2, %xmm1, %xmm2
|
|
; X86-AVX-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm2
|
|
; X86-AVX-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
|
|
; X86-AVX-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX-NEXT: vpextrd $1, %xmm0, %edx
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v2i64:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm3, %xmm2
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm5, %xmm2
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: movq %xmm3, %rax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v2i64:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; X64-SSE42-NEXT: movdqa {{.*#+}} xmm0 = [9223372036854775808,9223372036854775808]
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm3
|
|
; X64-SSE42-NEXT: pxor %xmm0, %xmm3
|
|
; X64-SSE42-NEXT: pxor %xmm2, %xmm0
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm2
|
|
; X64-SSE42-NEXT: movq %xmm2, %rax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v2i64:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [9223372036854775808,9223372036854775808]
|
|
; X64-AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm3
|
|
; X64-AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm2
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm2
|
|
; X64-AVX1-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
|
|
; X64-AVX1-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v2i64:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [9223372036854775808,9223372036854775808]
|
|
; X64-AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm3
|
|
; X64-AVX2-NEXT: vpxor %xmm2, %xmm1, %xmm2
|
|
; X64-AVX2-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm2
|
|
; X64-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
|
|
; X64-AVX2-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v2i64:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminuq %xmm1, %xmm0, %xmm0
|
|
; X64-AVX512-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <2 x i64> %a0, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
|
%2 = icmp ult <2 x i64> %a0, %1
|
|
%3 = select <2 x i1> %2, <2 x i64> %a0, <2 x i64> %1
|
|
%4 = extractelement <2 x i64> %3, i32 0
|
|
ret i64 %4
|
|
}
|
|
|
|
define i32 @test_reduce_v4i32(<4 x i32> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v4i32:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: movd %xmm2, %eax
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v4i32:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: test_reduce_v4i32:
|
|
; X86-AVX: ## %bb.0:
|
|
; X86-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v4i32:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: movd %xmm2, %eax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v4i32:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX-LABEL: test_reduce_v4i32:
|
|
; X64-AVX: ## %bb.0:
|
|
; X64-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX-NEXT: retq
|
|
%1 = shufflevector <4 x i32> %a0, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
|
%2 = icmp ult <4 x i32> %a0, %1
|
|
%3 = select <4 x i1> %2, <4 x i32> %a0, <4 x i32> %1
|
|
%4 = shufflevector <4 x i32> %3, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <4 x i32> %3, %4
|
|
%6 = select <4 x i1> %5, <4 x i32> %3, <4 x i32> %4
|
|
%7 = extractelement <4 x i32> %6, i32 0
|
|
ret i32 %7
|
|
}
|
|
|
|
define i16 @test_reduce_v8i16(<8 x i16> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v8i16:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm1 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm0
|
|
; X86-SSE2-NEXT: psrld $16, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pand %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: movd %xmm1, %eax
|
|
; X86-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v8i16:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: test_reduce_v8i16:
|
|
; X86-AVX: ## %bb.0:
|
|
; X86-AVX-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v8i16:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm1 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm0
|
|
; X64-SSE2-NEXT: psrld $16, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pand %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: movd %xmm1, %eax
|
|
; X64-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v8i16:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX-LABEL: test_reduce_v8i16:
|
|
; X64-AVX: ## %bb.0:
|
|
; X64-AVX-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX-NEXT: retq
|
|
%1 = shufflevector <8 x i16> %a0, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <8 x i16> %a0, %1
|
|
%3 = select <8 x i1> %2, <8 x i16> %a0, <8 x i16> %1
|
|
%4 = shufflevector <8 x i16> %3, <8 x i16> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <8 x i16> %3, %4
|
|
%6 = select <8 x i1> %5, <8 x i16> %3, <8 x i16> %4
|
|
%7 = shufflevector <8 x i16> %6, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <8 x i16> %6, %7
|
|
%9 = select <8 x i1> %8, <8 x i16> %6, <8 x i16> %7
|
|
%10 = extractelement <8 x i16> %9, i32 0
|
|
ret i16 %10
|
|
}
|
|
|
|
define i8 @test_reduce_v16i8(<16 x i8> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v16i8:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: psrld $16, %xmm1
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movd %xmm0, %eax
|
|
; X86-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v16i8:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: psrld $16, %xmm1
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: test_reduce_v16i8:
|
|
; X86-AVX: ## %bb.0:
|
|
; X86-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X86-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X86-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X86-AVX-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v16i8:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: psrld $16, %xmm1
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movd %xmm0, %eax
|
|
; X64-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v16i8:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: psrld $16, %xmm1
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX-LABEL: test_reduce_v16i8:
|
|
; X64-AVX: ## %bb.0:
|
|
; X64-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX-NEXT: retq
|
|
%1 = shufflevector <16 x i8> %a0, <16 x i8> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <16 x i8> %a0, %1
|
|
%3 = select <16 x i1> %2, <16 x i8> %a0, <16 x i8> %1
|
|
%4 = shufflevector <16 x i8> %3, <16 x i8> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <16 x i8> %3, %4
|
|
%6 = select <16 x i1> %5, <16 x i8> %3, <16 x i8> %4
|
|
%7 = shufflevector <16 x i8> %6, <16 x i8> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <16 x i8> %6, %7
|
|
%9 = select <16 x i1> %8, <16 x i8> %6, <16 x i8> %7
|
|
%10 = shufflevector <16 x i8> %9, <16 x i8> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <16 x i8> %9, %10
|
|
%12 = select <16 x i1> %11, <16 x i8> %9, <16 x i8> %10
|
|
%13 = extractelement <16 x i8> %12, i32 0
|
|
ret i8 %13
|
|
}
|
|
|
|
;
|
|
; 256-bit Vectors
|
|
;
|
|
|
|
define i64 @test_reduce_v4i64(<4 x i64> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v4i64:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm3, %xmm5
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm6, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[0,0,2,2]
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: movd %xmm2, %eax
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,2,3]
|
|
; X86-SSE2-NEXT: movd %xmm0, %edx
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v4i64:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm2
|
|
; X86-SSE42-NEXT: movdqa {{.*#+}} xmm3 = [0,2147483648,0,2147483648]
|
|
; X86-SSE42-NEXT: movdqa %xmm2, %xmm4
|
|
; X86-SSE42-NEXT: pxor %xmm3, %xmm4
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm2, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm0, %xmm3
|
|
; X86-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm2
|
|
; X86-SSE42-NEXT: movd %xmm2, %eax
|
|
; X86-SSE42-NEXT: pextrd $1, %xmm2, %edx
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v4i64:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,2147483648,0,2147483648]
|
|
; X86-AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm3
|
|
; X86-AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm4
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm3, %xmm4, %xmm3
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm4, %xmm0, %xmm4
|
|
; X86-AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; X86-AVX1-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vxorpd %xmm2, %xmm0, %xmm3
|
|
; X86-AVX1-NEXT: vxorpd %xmm2, %xmm1, %xmm4
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm3, %xmm4, %xmm3
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; X86-AVX1-NEXT: vpxor %xmm2, %xmm4, %xmm2
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm2, %xmm0, %xmm2
|
|
; X86-AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
|
; X86-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: vpextrd $1, %xmm0, %edx
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v4i64:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2147483648,0,2147483648,0,2147483648,0,2147483648]
|
|
; X86-AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm3
|
|
; X86-AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm4
|
|
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X86-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
|
|
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
|
|
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v4i64:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm3, %xmm5
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm6, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm5, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: movq %xmm2, %rax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v4i64:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm2
|
|
; X64-SSE42-NEXT: movdqa {{.*#+}} xmm3 = [9223372036854775808,9223372036854775808]
|
|
; X64-SSE42-NEXT: movdqa %xmm2, %xmm4
|
|
; X64-SSE42-NEXT: pxor %xmm3, %xmm4
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm2, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm0, %xmm3
|
|
; X64-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm2
|
|
; X64-SSE42-NEXT: movq %xmm2, %rax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v4i64:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [9223372036854775808,9223372036854775808]
|
|
; X64-AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm3
|
|
; X64-AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm4
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm3, %xmm4, %xmm3
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm4, %xmm0, %xmm4
|
|
; X64-AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; X64-AVX1-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vxorpd %xmm2, %xmm0, %xmm3
|
|
; X64-AVX1-NEXT: vxorpd %xmm2, %xmm1, %xmm4
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm3, %xmm4, %xmm3
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; X64-AVX1-NEXT: vpxor %xmm2, %xmm4, %xmm2
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm2, %xmm0, %xmm2
|
|
; X64-AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
|
; X64-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX1-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v4i64:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; X64-AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm3
|
|
; X64-AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm4
|
|
; X64-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X64-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
|
|
; X64-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
|
|
; X64-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX2-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v4i64:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminuq %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminuq %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
|
%2 = icmp ult <4 x i64> %a0, %1
|
|
%3 = select <4 x i1> %2, <4 x i64> %a0, <4 x i64> %1
|
|
%4 = shufflevector <4 x i64> %3, <4 x i64> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <4 x i64> %3, %4
|
|
%6 = select <4 x i1> %5, <4 x i64> %3, <4 x i64> %4
|
|
%7 = extractelement <4 x i64> %6, i32 0
|
|
ret i64 %7
|
|
}
|
|
|
|
define i32 @test_reduce_v8i32(<8 x i32> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v8i32:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm2
|
|
; X86-SSE2-NEXT: movd %xmm2, %eax
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v8i32:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v8i32:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v8i32:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v8i32:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pand %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm2
|
|
; X64-SSE2-NEXT: movd %xmm2, %eax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v8i32:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v8i32:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v8i32:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v8i32:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX512-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <8 x i32> %a0, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <8 x i32> %a0, %1
|
|
%3 = select <8 x i1> %2, <8 x i32> %a0, <8 x i32> %1
|
|
%4 = shufflevector <8 x i32> %3, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <8 x i32> %3, %4
|
|
%6 = select <8 x i1> %5, <8 x i32> %3, <8 x i32> %4
|
|
%7 = shufflevector <8 x i32> %6, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <8 x i32> %6, %7
|
|
%9 = select <8 x i1> %8, <8 x i32> %6, <8 x i32> %7
|
|
%10 = extractelement <8 x i32> %9, i32 0
|
|
ret i32 %10
|
|
}
|
|
|
|
define i16 @test_reduce_v16i16(<16 x i16> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v16i16:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: psrld $16, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: movd %xmm2, %eax
|
|
; X86-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v16i16:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminuw %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v16i16:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v16i16:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X86-AVX2-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v16i16:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm2 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm4[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: psrld $16, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: movd %xmm2, %eax
|
|
; X64-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v16i16:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminuw %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v16i16:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX1-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v16i16:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX2-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v16i16:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX512-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX512-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX512-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <16 x i16> %a0, <16 x i16> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <16 x i16> %a0, %1
|
|
%3 = select <16 x i1> %2, <16 x i16> %a0, <16 x i16> %1
|
|
%4 = shufflevector <16 x i16> %3, <16 x i16> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <16 x i16> %3, %4
|
|
%6 = select <16 x i1> %5, <16 x i16> %3, <16 x i16> %4
|
|
%7 = shufflevector <16 x i16> %6, <16 x i16> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <16 x i16> %6, %7
|
|
%9 = select <16 x i1> %8, <16 x i16> %6, <16 x i16> %7
|
|
%10 = shufflevector <16 x i16> %9, <16 x i16> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <16 x i16> %9, %10
|
|
%12 = select <16 x i1> %11, <16 x i16> %9, <16 x i16> %10
|
|
%13 = extractelement <16 x i16> %12, i32 0
|
|
ret i16 %13
|
|
}
|
|
|
|
define i8 @test_reduce_v32i8(<32 x i8> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v32i8:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: psrld $16, %xmm1
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movd %xmm0, %eax
|
|
; X86-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v32i8:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: psrld $16, %xmm1
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v32i8:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X86-AVX1-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v32i8:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X86-AVX2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v32i8:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: psrld $16, %xmm1
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movd %xmm0, %eax
|
|
; X64-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v32i8:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: psrld $16, %xmm1
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v32i8:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX1-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v32i8:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v32i8:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX512-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX512-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <32 x i8> %a0, <32 x i8> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <32 x i8> %a0, %1
|
|
%3 = select <32 x i1> %2, <32 x i8> %a0, <32 x i8> %1
|
|
%4 = shufflevector <32 x i8> %3, <32 x i8> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <32 x i8> %3, %4
|
|
%6 = select <32 x i1> %5, <32 x i8> %3, <32 x i8> %4
|
|
%7 = shufflevector <32 x i8> %6, <32 x i8> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <32 x i8> %6, %7
|
|
%9 = select <32 x i1> %8, <32 x i8> %6, <32 x i8> %7
|
|
%10 = shufflevector <32 x i8> %9, <32 x i8> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <32 x i8> %9, %10
|
|
%12 = select <32 x i1> %11, <32 x i8> %9, <32 x i8> %10
|
|
%13 = shufflevector <32 x i8> %12, <32 x i8> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%14 = icmp ult <32 x i8> %12, %13
|
|
%15 = select <32 x i1> %14, <32 x i8> %12, <32 x i8> %13
|
|
%16 = extractelement <32 x i8> %15, i32 0
|
|
ret i8 %16
|
|
}
|
|
|
|
;
|
|
; 512-bit Vectors
|
|
;
|
|
|
|
define i64 @test_reduce_v8i64(<8 x i64> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v8i64:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: subl $28, %esp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa_offset 32
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm6, (%esp) ## 16-byte Spill
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm6, %xmm7
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm5, %xmm7
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm5, %xmm6
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[0,0,2,2]
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm6
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm6, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; X86-SSE2-NEXT: movdqa %xmm7, %xmm0
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm6, %xmm0
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm6, %xmm7
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm0[0,0,2,2]
|
|
; X86-SSE2-NEXT: pand %xmm6, %xmm7
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm0[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm7, %xmm6
|
|
; X86-SSE2-NEXT: pand %xmm6, %xmm1
|
|
; X86-SSE2-NEXT: pandn %xmm3, %xmm6
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm6
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm2
|
|
; X86-SSE2-NEXT: pandn (%esp), %xmm5 ## 16-byte Folded Reload
|
|
; X86-SSE2-NEXT: por %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm6, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,0,2,2]
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: pand %xmm0, %xmm5
|
|
; X86-SSE2-NEXT: pandn %xmm6, %xmm0
|
|
; X86-SSE2-NEXT: por %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: movdqa %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pcmpeqd %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,0,2,2]
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3]
|
|
; X86-SSE2-NEXT: por %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: movd %xmm2, %eax
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,2,3]
|
|
; X86-SSE2-NEXT: movd %xmm0, %edx
|
|
; X86-SSE2-NEXT: addl $28, %esp
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v8i64:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm5
|
|
; X86-SSE42-NEXT: movdqa {{.*#+}} xmm4 = [0,2147483648,0,2147483648]
|
|
; X86-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: movdqa %xmm2, %xmm6
|
|
; X86-SSE42-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm0, %xmm6
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm7
|
|
; X86-SSE42-NEXT: pxor %xmm4, %xmm7
|
|
; X86-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm7, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm3
|
|
; X86-SSE42-NEXT: movdqa %xmm6, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm5, %xmm2
|
|
; X86-SSE42-NEXT: movapd %xmm2, %xmm1
|
|
; X86-SSE42-NEXT: xorpd %xmm4, %xmm1
|
|
; X86-SSE42-NEXT: movapd %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: xorpd %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm2, %xmm3
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm3[2,3,0,1]
|
|
; X86-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: pxor %xmm1, %xmm4
|
|
; X86-SSE42-NEXT: pcmpgtq %xmm0, %xmm4
|
|
; X86-SSE42-NEXT: movdqa %xmm4, %xmm0
|
|
; X86-SSE42-NEXT: blendvpd %xmm0, %xmm3, %xmm1
|
|
; X86-SSE42-NEXT: movd %xmm1, %eax
|
|
; X86-SSE42-NEXT: pextrd $1, %xmm1, %edx
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v8i64:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
|
|
; X86-AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [0,2147483648,0,2147483648]
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm2, %xmm2
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm4, %xmm4
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm0, %xmm4
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm5
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm4, %xmm5, %xmm4
|
|
; X86-AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm2
|
|
; X86-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX1-NEXT: vxorpd %xmm3, %xmm0, %xmm2
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm4
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm4, %xmm0, %xmm4
|
|
; X86-AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; X86-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vxorpd %xmm3, %xmm0, %xmm2
|
|
; X86-AVX1-NEXT: vxorpd %xmm3, %xmm1, %xmm4
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; X86-AVX1-NEXT: vpxor %xmm3, %xmm4, %xmm3
|
|
; X86-AVX1-NEXT: vpcmpgtq %xmm3, %xmm0, %xmm3
|
|
; X86-AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
|
|
; X86-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: vpextrd $1, %xmm0, %edx
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v8i64:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2147483648,0,2147483648,0,2147483648,0,2147483648]
|
|
; X86-AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm3
|
|
; X86-AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm4
|
|
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X86-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm4
|
|
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X86-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
|
|
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
|
|
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v8i64:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm9 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm5
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm6, %xmm7
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm5, %xmm7
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm8 = xmm7[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm5, %xmm6
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm8, %xmm6
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm6, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm7
|
|
; X64-SSE2-NEXT: movdqa %xmm7, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm6, %xmm4
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm8 = xmm4[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm6, %xmm7
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm8, %xmm7
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm7, %xmm6
|
|
; X64-SSE2-NEXT: pand %xmm6, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm3, %xmm6
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm6
|
|
; X64-SSE2-NEXT: pand %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm2, %xmm5
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm6, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm0
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pand %xmm1, %xmm5
|
|
; X64-SSE2-NEXT: pandn %xmm6, %xmm1
|
|
; X64-SSE2-NEXT: por %xmm5, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm9, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm9
|
|
; X64-SSE2-NEXT: movdqa %xmm9, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[0,0,2,2]
|
|
; X64-SSE2-NEXT: pcmpeqd %xmm2, %xmm9
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm9[1,1,3,3]
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; X64-SSE2-NEXT: por %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: movq %xmm3, %rax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v8i64:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm5
|
|
; X64-SSE42-NEXT: movdqa {{.*#+}} xmm4 = [9223372036854775808,9223372036854775808]
|
|
; X64-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: movdqa %xmm2, %xmm6
|
|
; X64-SSE42-NEXT: pxor %xmm4, %xmm6
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm0, %xmm6
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm7
|
|
; X64-SSE42-NEXT: pxor %xmm4, %xmm7
|
|
; X64-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm7, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm1, %xmm3
|
|
; X64-SSE42-NEXT: movdqa %xmm6, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm5, %xmm2
|
|
; X64-SSE42-NEXT: movapd %xmm2, %xmm1
|
|
; X64-SSE42-NEXT: xorpd %xmm4, %xmm1
|
|
; X64-SSE42-NEXT: movapd %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: xorpd %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm2, %xmm3
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm3[2,3,0,1]
|
|
; X64-SSE42-NEXT: movdqa %xmm3, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: pxor %xmm1, %xmm4
|
|
; X64-SSE42-NEXT: pcmpgtq %xmm0, %xmm4
|
|
; X64-SSE42-NEXT: movdqa %xmm4, %xmm0
|
|
; X64-SSE42-NEXT: blendvpd %xmm0, %xmm3, %xmm1
|
|
; X64-SSE42-NEXT: movq %xmm1, %rax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v8i64:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
|
|
; X64-AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [9223372036854775808,9223372036854775808]
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm2, %xmm2
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm4, %xmm4
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm0, %xmm4
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm5
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm4, %xmm5, %xmm4
|
|
; X64-AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm2
|
|
; X64-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX1-NEXT: vxorpd %xmm3, %xmm0, %xmm2
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm1, %xmm4
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm4, %xmm0, %xmm4
|
|
; X64-AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; X64-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vxorpd %xmm3, %xmm0, %xmm2
|
|
; X64-AVX1-NEXT: vxorpd %xmm3, %xmm1, %xmm4
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm2
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; X64-AVX1-NEXT: vpxor %xmm3, %xmm4, %xmm3
|
|
; X64-AVX1-NEXT: vpcmpgtq %xmm3, %xmm0, %xmm3
|
|
; X64-AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
|
|
; X64-AVX1-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX1-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v8i64:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vpbroadcastq {{.*#+}} ymm2 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; X64-AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm3
|
|
; X64-AVX2-NEXT: vpxor %ymm2, %ymm1, %ymm4
|
|
; X64-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X64-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm4
|
|
; X64-AVX2-NEXT: vpcmpgtq %ymm3, %ymm4, %ymm3
|
|
; X64-AVX2-NEXT: vblendvpd %ymm3, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
|
|
; X64-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
|
|
; X64-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
|
|
; X64-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
|
|
; X64-AVX2-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v8i64:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; X64-AVX512-NEXT: vpminuq %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminuq %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminuq %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vmovq %xmm0, %rax
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <8 x i64> %a0, <8 x i64> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <8 x i64> %a0, %1
|
|
%3 = select <8 x i1> %2, <8 x i64> %a0, <8 x i64> %1
|
|
%4 = shufflevector <8 x i64> %3, <8 x i64> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <8 x i64> %3, %4
|
|
%6 = select <8 x i1> %5, <8 x i64> %3, <8 x i64> %4
|
|
%7 = shufflevector <8 x i64> %6, <8 x i64> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <8 x i64> %6, %7
|
|
%9 = select <8 x i1> %8, <8 x i64> %6, <8 x i64> %7
|
|
%10 = extractelement <8 x i64> %9, i32 0
|
|
ret i64 %10
|
|
}
|
|
|
|
define i32 @test_reduce_v16i32(<16 x i32> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v16i32:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm6, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm6, %xmm7
|
|
; X86-SSE2-NEXT: pand %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: pandn %xmm3, %xmm7
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm7
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pand %xmm1, %xmm5
|
|
; X86-SSE2-NEXT: pandn %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: por %xmm5, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X86-SSE2-NEXT: movd %xmm4, %eax
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v16i32:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminud %xmm3, %xmm1
|
|
; X86-SSE42-NEXT: pminud %xmm2, %xmm0
|
|
; X86-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v16i32:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X86-AVX1-NEXT: vpminud %xmm2, %xmm3, %xmm2
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpminud %xmm2, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v16i32:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v16i32:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm6, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm6, %xmm7
|
|
; X64-SSE2-NEXT: pand %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm3, %xmm7
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm7
|
|
; X64-SSE2-NEXT: pand %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm2, %xmm5
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pand %xmm1, %xmm5
|
|
; X64-SSE2-NEXT: pandn %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: por %xmm5, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm4
|
|
; X64-SSE2-NEXT: movd %xmm4, %eax
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v16i32:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminud %xmm3, %xmm1
|
|
; X64-SSE42-NEXT: pminud %xmm2, %xmm0
|
|
; X64-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminud %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminud %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v16i32:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X64-AVX1-NEXT: vpminud %xmm2, %xmm3, %xmm2
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpminud %xmm2, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX1-NEXT: vpminud %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v16i32:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX2-NEXT: vpminud %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v16i32:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; X64-AVX512-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX512-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <16 x i32> %a0, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <16 x i32> %a0, %1
|
|
%3 = select <16 x i1> %2, <16 x i32> %a0, <16 x i32> %1
|
|
%4 = shufflevector <16 x i32> %3, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <16 x i32> %3, %4
|
|
%6 = select <16 x i1> %5, <16 x i32> %3, <16 x i32> %4
|
|
%7 = shufflevector <16 x i32> %6, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <16 x i32> %6, %7
|
|
%9 = select <16 x i1> %8, <16 x i32> %6, <16 x i32> %7
|
|
%10 = shufflevector <16 x i32> %9, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <16 x i32> %9, %10
|
|
%12 = select <16 x i1> %11, <16 x i32> %9, <16 x i32> %10
|
|
%13 = extractelement <16 x i32> %12, i32 0
|
|
ret i32 %13
|
|
}
|
|
|
|
define i16 @test_reduce_v32i16(<32 x i16> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v32i16:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: movdqa {{.*#+}} xmm4 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm6, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm6, %xmm7
|
|
; X86-SSE2-NEXT: pand %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: pandn %xmm3, %xmm7
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm7
|
|
; X86-SSE2-NEXT: pand %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pandn %xmm2, %xmm5
|
|
; X86-SSE2-NEXT: por %xmm0, %xmm5
|
|
; X86-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pand %xmm1, %xmm5
|
|
; X86-SSE2-NEXT: pandn %xmm7, %xmm1
|
|
; X86-SSE2-NEXT: por %xmm5, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm3
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pand %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X86-SSE2-NEXT: por %xmm1, %xmm3
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X86-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm1, %xmm2
|
|
; X86-SSE2-NEXT: pand %xmm2, %xmm3
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X86-SSE2-NEXT: por %xmm3, %xmm2
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm0
|
|
; X86-SSE2-NEXT: psrld $16, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm2, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X86-SSE2-NEXT: pxor %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: pcmpgtw %xmm1, %xmm4
|
|
; X86-SSE2-NEXT: pand %xmm4, %xmm2
|
|
; X86-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X86-SSE2-NEXT: por %xmm2, %xmm4
|
|
; X86-SSE2-NEXT: movd %xmm4, %eax
|
|
; X86-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v32i16:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminuw %xmm3, %xmm1
|
|
; X86-SSE42-NEXT: pminuw %xmm2, %xmm0
|
|
; X86-SSE42-NEXT: pminuw %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X86-SSE42-NEXT: movd %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v32i16:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X86-AVX1-NEXT: vpminuw %xmm2, %xmm3, %xmm2
|
|
; X86-AVX1-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpminuw %xmm2, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX1-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v32i16:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vpminuw %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X86-AVX2-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X86-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X86-AVX2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v32i16:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: movdqa {{.*#+}} xmm4 = [32768,32768,32768,32768,32768,32768,32768,32768]
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm6, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm6
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm6
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm7
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm6, %xmm7
|
|
; X64-SSE2-NEXT: pand %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm3, %xmm7
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm7
|
|
; X64-SSE2-NEXT: pand %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pandn %xmm2, %xmm5
|
|
; X64-SSE2-NEXT: por %xmm0, %xmm5
|
|
; X64-SSE2-NEXT: movdqa %xmm5, %xmm0
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pand %xmm1, %xmm5
|
|
; X64-SSE2-NEXT: pandn %xmm7, %xmm1
|
|
; X64-SSE2-NEXT: por %xmm5, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm3
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pand %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm3
|
|
; X64-SSE2-NEXT: por %xmm1, %xmm3
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[1,1,2,3]
|
|
; X64-SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm1, %xmm2
|
|
; X64-SSE2-NEXT: pand %xmm2, %xmm3
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; X64-SSE2-NEXT: por %xmm3, %xmm2
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm0
|
|
; X64-SSE2-NEXT: psrld $16, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm2, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm4, %xmm1
|
|
; X64-SSE2-NEXT: pxor %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: pcmpgtw %xmm1, %xmm4
|
|
; X64-SSE2-NEXT: pand %xmm4, %xmm2
|
|
; X64-SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; X64-SSE2-NEXT: por %xmm2, %xmm4
|
|
; X64-SSE2-NEXT: movd %xmm4, %eax
|
|
; X64-SSE2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v32i16:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminuw %xmm3, %xmm1
|
|
; X64-SSE42-NEXT: pminuw %xmm2, %xmm0
|
|
; X64-SSE42-NEXT: pminuw %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: phminposuw %xmm0, %xmm0
|
|
; X64-SSE42-NEXT: movd %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v32i16:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X64-AVX1-NEXT: vpminuw %xmm2, %xmm3, %xmm2
|
|
; X64-AVX1-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpminuw %xmm2, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX1-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v32i16:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vpminuw %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX2-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX2-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX2-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v32i16:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; X64-AVX512-NEXT: vpminuw %ymm1, %ymm0, %ymm0
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminuw %xmm1, %xmm0, %xmm0
|
|
; X64-AVX512-NEXT: vphminposuw %xmm0, %xmm0
|
|
; X64-AVX512-NEXT: vmovd %xmm0, %eax
|
|
; X64-AVX512-NEXT: ## kill: %ax<def> %ax<kill> %eax<kill>
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <32 x i16> %a0, <32 x i16> undef, <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <32 x i16> %a0, %1
|
|
%3 = select <32 x i1> %2, <32 x i16> %a0, <32 x i16> %1
|
|
%4 = shufflevector <32 x i16> %3, <32 x i16> undef, <32 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <32 x i16> %3, %4
|
|
%6 = select <32 x i1> %5, <32 x i16> %3, <32 x i16> %4
|
|
%7 = shufflevector <32 x i16> %6, <32 x i16> undef, <32 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <32 x i16> %6, %7
|
|
%9 = select <32 x i1> %8, <32 x i16> %6, <32 x i16> %7
|
|
%10 = shufflevector <32 x i16> %9, <32 x i16> undef, <32 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <32 x i16> %9, %10
|
|
%12 = select <32 x i1> %11, <32 x i16> %9, <32 x i16> %10
|
|
%13 = shufflevector <32 x i16> %12, <32 x i16> undef, <32 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%14 = icmp ult <32 x i16> %12, %13
|
|
%15 = select <32 x i1> %14, <32 x i16> %12, <32 x i16> %13
|
|
%16 = extractelement <32 x i16> %15, i32 0
|
|
ret i16 %16
|
|
}
|
|
|
|
define i8 @test_reduce_v64i8(<64 x i8> %a0) {
|
|
; X86-SSE2-LABEL: test_reduce_v64i8:
|
|
; X86-SSE2: ## %bb.0:
|
|
; X86-SSE2-NEXT: pminub %xmm3, %xmm1
|
|
; X86-SSE2-NEXT: pminub %xmm2, %xmm0
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: psrld $16, %xmm1
|
|
; X86-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE2-NEXT: movd %xmm0, %eax
|
|
; X86-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-SSE42-LABEL: test_reduce_v64i8:
|
|
; X86-SSE42: ## %bb.0:
|
|
; X86-SSE42-NEXT: pminub %xmm3, %xmm1
|
|
; X86-SSE42-NEXT: pminub %xmm2, %xmm0
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: psrld $16, %xmm1
|
|
; X86-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X86-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X86-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X86-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X86-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-SSE42-NEXT: retl
|
|
;
|
|
; X86-AVX1-LABEL: test_reduce_v64i8:
|
|
; X86-AVX1: ## %bb.0:
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X86-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X86-AVX1-NEXT: vpminub %xmm2, %xmm3, %xmm2
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpminub %xmm2, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X86-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X86-AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X86-AVX1-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-AVX1-NEXT: vzeroupper
|
|
; X86-AVX1-NEXT: retl
|
|
;
|
|
; X86-AVX2-LABEL: test_reduce_v64i8:
|
|
; X86-AVX2: ## %bb.0:
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X86-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X86-AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X86-AVX2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X86-AVX2-NEXT: vzeroupper
|
|
; X86-AVX2-NEXT: retl
|
|
;
|
|
; X64-SSE2-LABEL: test_reduce_v64i8:
|
|
; X64-SSE2: ## %bb.0:
|
|
; X64-SSE2-NEXT: pminub %xmm3, %xmm1
|
|
; X64-SSE2-NEXT: pminub %xmm2, %xmm0
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: psrld $16, %xmm1
|
|
; X64-SSE2-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE2-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE2-NEXT: movd %xmm0, %eax
|
|
; X64-SSE2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE2-NEXT: retq
|
|
;
|
|
; X64-SSE42-LABEL: test_reduce_v64i8:
|
|
; X64-SSE42: ## %bb.0:
|
|
; X64-SSE42-NEXT: pminub %xmm3, %xmm1
|
|
; X64-SSE42-NEXT: pminub %xmm2, %xmm0
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: movdqa %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: psrld $16, %xmm1
|
|
; X64-SSE42-NEXT: pminub %xmm0, %xmm1
|
|
; X64-SSE42-NEXT: movdqa %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: psrlw $8, %xmm0
|
|
; X64-SSE42-NEXT: pminub %xmm1, %xmm0
|
|
; X64-SSE42-NEXT: pextrb $0, %xmm0, %eax
|
|
; X64-SSE42-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-SSE42-NEXT: retq
|
|
;
|
|
; X64-AVX1-LABEL: test_reduce_v64i8:
|
|
; X64-AVX1: ## %bb.0:
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X64-AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; X64-AVX1-NEXT: vpminub %xmm2, %xmm3, %xmm2
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpminub %xmm2, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX1-NEXT: vpminub %xmm1, %xmm0, %xmm0
|
|
; X64-AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX1-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX1-NEXT: vzeroupper
|
|
; X64-AVX1-NEXT: retq
|
|
;
|
|
; X64-AVX2-LABEL: test_reduce_v64i8:
|
|
; X64-AVX2: ## %bb.0:
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX2-NEXT: vpminub %ymm1, %ymm0, %ymm0
|
|
; X64-AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX2-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX2-NEXT: vzeroupper
|
|
; X64-AVX2-NEXT: retq
|
|
;
|
|
; X64-AVX512-LABEL: test_reduce_v64i8:
|
|
; X64-AVX512: ## %bb.0:
|
|
; X64-AVX512-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpsrld $16, %xmm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpsrlw $8, %xmm0, %xmm1
|
|
; X64-AVX512-NEXT: vpminub %zmm1, %zmm0, %zmm0
|
|
; X64-AVX512-NEXT: vpextrb $0, %xmm0, %eax
|
|
; X64-AVX512-NEXT: ## kill: %al<def> %al<kill> %eax<kill>
|
|
; X64-AVX512-NEXT: vzeroupper
|
|
; X64-AVX512-NEXT: retq
|
|
%1 = shufflevector <64 x i8> %a0, <64 x i8> undef, <64 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%2 = icmp ult <64 x i8> %a0, %1
|
|
%3 = select <64 x i1> %2, <64 x i8> %a0, <64 x i8> %1
|
|
%4 = shufflevector <64 x i8> %3, <64 x i8> undef, <64 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%5 = icmp ult <64 x i8> %3, %4
|
|
%6 = select <64 x i1> %5, <64 x i8> %3, <64 x i8> %4
|
|
%7 = shufflevector <64 x i8> %6, <64 x i8> undef, <64 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%8 = icmp ult <64 x i8> %6, %7
|
|
%9 = select <64 x i1> %8, <64 x i8> %6, <64 x i8> %7
|
|
%10 = shufflevector <64 x i8> %9, <64 x i8> undef, <64 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%11 = icmp ult <64 x i8> %9, %10
|
|
%12 = select <64 x i1> %11, <64 x i8> %9, <64 x i8> %10
|
|
%13 = shufflevector <64 x i8> %12, <64 x i8> undef, <64 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%14 = icmp ult <64 x i8> %12, %13
|
|
%15 = select <64 x i1> %14, <64 x i8> %12, <64 x i8> %13
|
|
%16 = shufflevector <64 x i8> %15, <64 x i8> undef, <64 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%17 = icmp ult <64 x i8> %15, %16
|
|
%18 = select <64 x i1> %17, <64 x i8> %15, <64 x i8> %16
|
|
%19 = extractelement <64 x i8> %18, i32 0
|
|
ret i8 %19
|
|
}
|