forked from OSchip/llvm-project
2130 lines
78 KiB
LLVM
2130 lines
78 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSSE3
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
|
|
|
|
declare <1 x i8> @llvm.ssub.sat.v1i8(<1 x i8>, <1 x i8>)
|
|
declare <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8>, <2 x i8>)
|
|
declare <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8>, <4 x i8>)
|
|
declare <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8>, <8 x i8>)
|
|
declare <12 x i8> @llvm.ssub.sat.v12i8(<12 x i8>, <12 x i8>)
|
|
declare <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8>, <16 x i8>)
|
|
declare <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8>, <32 x i8>)
|
|
declare <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8>, <64 x i8>)
|
|
|
|
declare <1 x i16> @llvm.ssub.sat.v1i16(<1 x i16>, <1 x i16>)
|
|
declare <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16>, <4 x i16>)
|
|
declare <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <12 x i16> @llvm.ssub.sat.v12i16(<12 x i16>, <12 x i16>)
|
|
declare <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16>, <16 x i16>)
|
|
declare <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16>, <32 x i16>)
|
|
|
|
declare <16 x i1> @llvm.ssub.sat.v16i1(<16 x i1>, <16 x i1>)
|
|
declare <16 x i4> @llvm.ssub.sat.v16i4(<16 x i4>, <16 x i4>)
|
|
|
|
declare <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32>, <2 x i32>)
|
|
declare <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32>, <4 x i32>)
|
|
declare <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32>, <8 x i32>)
|
|
declare <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32>, <16 x i32>)
|
|
declare <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64>, <4 x i64>)
|
|
declare <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64>, <8 x i64>)
|
|
|
|
declare <4 x i24> @llvm.ssub.sat.v4i24(<4 x i24>, <4 x i24>)
|
|
declare <2 x i128> @llvm.ssub.sat.v2i128(<2 x i128>, <2 x i128>)
|
|
|
|
; Legal types, depending on architecture.
|
|
|
|
define <16 x i8> @v16i8(<16 x i8> %x, <16 x i8> %y) nounwind {
|
|
; SSE-LABEL: v16i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v16i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%z = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> %x, <16 x i8> %y)
|
|
ret <16 x i8> %z
|
|
}
|
|
|
|
define <32 x i8> @v32i8(<32 x i8> %x, <32 x i8> %y) nounwind {
|
|
; SSE-LABEL: v32i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsb %xmm2, %xmm0
|
|
; SSE-NEXT: psubsb %xmm3, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v32i8:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; AVX1-NEXT: vpsubsb %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v32i8:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsubsb %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v32i8:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsubsb %ymm1, %ymm0, %ymm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> %x, <32 x i8> %y)
|
|
ret <32 x i8> %z
|
|
}
|
|
|
|
define <64 x i8> @v64i8(<64 x i8> %x, <64 x i8> %y) nounwind {
|
|
; SSE-LABEL: v64i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsb %xmm4, %xmm0
|
|
; SSE-NEXT: psubsb %xmm5, %xmm1
|
|
; SSE-NEXT: psubsb %xmm6, %xmm2
|
|
; SSE-NEXT: psubsb %xmm7, %xmm3
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v64i8:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5
|
|
; AVX1-NEXT: vpsubsb %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpsubsb %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vpsubsb %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsubsb %xmm3, %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v64i8:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsubsb %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsubsb %ymm3, %ymm1, %ymm1
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v64i8:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsubsb %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> %x, <64 x i8> %y)
|
|
ret <64 x i8> %z
|
|
}
|
|
|
|
define <8 x i16> @v8i16(<8 x i16> %x, <8 x i16> %y) nounwind {
|
|
; SSE-LABEL: v8i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsw %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v8i16:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpsubsw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%z = call <8 x i16> @llvm.ssub.sat.v8i16(<8 x i16> %x, <8 x i16> %y)
|
|
ret <8 x i16> %z
|
|
}
|
|
|
|
define <16 x i16> @v16i16(<16 x i16> %x, <16 x i16> %y) nounwind {
|
|
; SSE-LABEL: v16i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsw %xmm2, %xmm0
|
|
; SSE-NEXT: psubsw %xmm3, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v16i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; AVX1-NEXT: vpsubsw %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpsubsw %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v16i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsubsw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v16i16:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsubsw %ymm1, %ymm0, %ymm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> %x, <16 x i16> %y)
|
|
ret <16 x i16> %z
|
|
}
|
|
|
|
define <32 x i16> @v32i16(<32 x i16> %x, <32 x i16> %y) nounwind {
|
|
; SSE-LABEL: v32i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsw %xmm4, %xmm0
|
|
; SSE-NEXT: psubsw %xmm5, %xmm1
|
|
; SSE-NEXT: psubsw %xmm6, %xmm2
|
|
; SSE-NEXT: psubsw %xmm7, %xmm3
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v32i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm5
|
|
; AVX1-NEXT: vpsubsw %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpsubsw %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vpsubsw %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsubsw %xmm3, %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v32i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsubsw %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpsubsw %ymm3, %ymm1, %ymm1
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v32i16:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsubsw %zmm1, %zmm0, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> %x, <32 x i16> %y)
|
|
ret <32 x i16> %z
|
|
}
|
|
|
|
; Too narrow vectors, legalized by widening.
|
|
|
|
define void @v8i8(<8 x i8>* %px, <8 x i8>* %py, <8 x i8>* %pz) nounwind {
|
|
; SSE-LABEL: v8i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
|
|
; SSE-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: movq %xmm0, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v8i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vmovq %xmm0, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <8 x i8>, <8 x i8>* %px
|
|
%y = load <8 x i8>, <8 x i8>* %py
|
|
%z = call <8 x i8> @llvm.ssub.sat.v8i8(<8 x i8> %x, <8 x i8> %y)
|
|
store <8 x i8> %z, <8 x i8>* %pz
|
|
ret void
|
|
}
|
|
|
|
define void @v4i8(<4 x i8>* %px, <4 x i8>* %py, <4 x i8>* %pz) nounwind {
|
|
; SSE-LABEL: v4i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: movd %xmm0, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v4i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vmovd %xmm0, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <4 x i8>, <4 x i8>* %px
|
|
%y = load <4 x i8>, <4 x i8>* %py
|
|
%z = call <4 x i8> @llvm.ssub.sat.v4i8(<4 x i8> %x, <4 x i8> %y)
|
|
store <4 x i8> %z, <4 x i8>* %pz
|
|
ret void
|
|
}
|
|
|
|
define void @v2i8(<2 x i8>* %px, <2 x i8>* %py, <2 x i8>* %pz) nounwind {
|
|
; SSE2-LABEL: v2i8:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movzwl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm0
|
|
; SSE2-NEXT: movzwl (%rsi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm1
|
|
; SSE2-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rdx)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v2i8:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movzwl (%rdi), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm0
|
|
; SSSE3-NEXT: movzwl (%rsi), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm1
|
|
; SSSE3-NEXT: psubsb %xmm1, %xmm0
|
|
; SSSE3-NEXT: movd %xmm0, %eax
|
|
; SSSE3-NEXT: movw %ax, (%rdx)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v2i8:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movzwl (%rdi), %eax
|
|
; SSE41-NEXT: movd %eax, %xmm0
|
|
; SSE41-NEXT: movzwl (%rsi), %eax
|
|
; SSE41-NEXT: movd %eax, %xmm1
|
|
; SSE41-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE41-NEXT: pextrw $0, %xmm0, (%rdx)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v2i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: movzwl (%rdi), %eax
|
|
; AVX-NEXT: vmovd %eax, %xmm0
|
|
; AVX-NEXT: movzwl (%rsi), %eax
|
|
; AVX-NEXT: vmovd %eax, %xmm1
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpextrw $0, %xmm0, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <2 x i8>, <2 x i8>* %px
|
|
%y = load <2 x i8>, <2 x i8>* %py
|
|
%z = call <2 x i8> @llvm.ssub.sat.v2i8(<2 x i8> %x, <2 x i8> %y)
|
|
store <2 x i8> %z, <2 x i8>* %pz
|
|
ret void
|
|
}
|
|
|
|
define void @v4i16(<4 x i16>* %px, <4 x i16>* %py, <4 x i16>* %pz) nounwind {
|
|
; SSE-LABEL: v4i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
|
|
; SSE-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
|
|
; SSE-NEXT: psubsw %xmm1, %xmm0
|
|
; SSE-NEXT: movq %xmm0, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v4i16:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX-NEXT: vpsubsw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vmovq %xmm0, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <4 x i16>, <4 x i16>* %px
|
|
%y = load <4 x i16>, <4 x i16>* %py
|
|
%z = call <4 x i16> @llvm.ssub.sat.v4i16(<4 x i16> %x, <4 x i16> %y)
|
|
store <4 x i16> %z, <4 x i16>* %pz
|
|
ret void
|
|
}
|
|
|
|
define void @v2i16(<2 x i16>* %px, <2 x i16>* %py, <2 x i16>* %pz) nounwind {
|
|
; SSE-LABEL: v2i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: psubsw %xmm1, %xmm0
|
|
; SSE-NEXT: movd %xmm0, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v2i16:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vpsubsw %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vmovd %xmm0, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <2 x i16>, <2 x i16>* %px
|
|
%y = load <2 x i16>, <2 x i16>* %py
|
|
%z = call <2 x i16> @llvm.ssub.sat.v2i16(<2 x i16> %x, <2 x i16> %y)
|
|
store <2 x i16> %z, <2 x i16>* %pz
|
|
ret void
|
|
}
|
|
|
|
define <12 x i8> @v12i8(<12 x i8> %x, <12 x i8> %y) nounwind {
|
|
; SSE-LABEL: v12i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v12i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%z = call <12 x i8> @llvm.ssub.sat.v12i8(<12 x i8> %x, <12 x i8> %y)
|
|
ret <12 x i8> %z
|
|
}
|
|
|
|
define void @v12i16(<12 x i16>* %px, <12 x i16>* %py, <12 x i16>* %pz) nounwind {
|
|
; SSE-LABEL: v12i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE-NEXT: movdqa 16(%rdi), %xmm1
|
|
; SSE-NEXT: psubsw (%rsi), %xmm0
|
|
; SSE-NEXT: psubsw 16(%rsi), %xmm1
|
|
; SSE-NEXT: movq %xmm1, 16(%rdx)
|
|
; SSE-NEXT: movdqa %xmm0, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v12i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX1-NEXT: vmovdqa 16(%rdi), %xmm1
|
|
; AVX1-NEXT: vpsubsw 16(%rsi), %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsubsw (%rsi), %xmm0, %xmm0
|
|
; AVX1-NEXT: vmovdqa %xmm0, (%rdx)
|
|
; AVX1-NEXT: vmovq %xmm1, 16(%rdx)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v12i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
|
|
; AVX2-NEXT: vpsubsw (%rsi), %ymm0, %ymm0
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vmovq %xmm1, 16(%rdx)
|
|
; AVX2-NEXT: vmovdqa %xmm0, (%rdx)
|
|
; AVX2-NEXT: vzeroupper
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v12i16:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vmovdqa (%rdi), %ymm0
|
|
; AVX512-NEXT: vpsubsw (%rsi), %ymm0, %ymm0
|
|
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX512-NEXT: vmovq %xmm1, 16(%rdx)
|
|
; AVX512-NEXT: vmovdqa %xmm0, (%rdx)
|
|
; AVX512-NEXT: vzeroupper
|
|
; AVX512-NEXT: retq
|
|
%x = load <12 x i16>, <12 x i16>* %px
|
|
%y = load <12 x i16>, <12 x i16>* %py
|
|
%z = call <12 x i16> @llvm.ssub.sat.v12i16(<12 x i16> %x, <12 x i16> %y)
|
|
store <12 x i16> %z, <12 x i16>* %pz
|
|
ret void
|
|
}
|
|
|
|
; Scalarization
|
|
|
|
define void @v1i8(<1 x i8>* %px, <1 x i8>* %py, <1 x i8>* %pz) nounwind {
|
|
; SSE-LABEL: v1i8:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movb (%rdi), %al
|
|
; SSE-NEXT: movb (%rsi), %cl
|
|
; SSE-NEXT: xorl %esi, %esi
|
|
; SSE-NEXT: cmpb %cl, %al
|
|
; SSE-NEXT: setns %sil
|
|
; SSE-NEXT: addl $127, %esi
|
|
; SSE-NEXT: subb %cl, %al
|
|
; SSE-NEXT: movzbl %al, %eax
|
|
; SSE-NEXT: cmovol %esi, %eax
|
|
; SSE-NEXT: movb %al, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v1i8:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: movb (%rdi), %al
|
|
; AVX-NEXT: movb (%rsi), %cl
|
|
; AVX-NEXT: xorl %esi, %esi
|
|
; AVX-NEXT: cmpb %cl, %al
|
|
; AVX-NEXT: setns %sil
|
|
; AVX-NEXT: addl $127, %esi
|
|
; AVX-NEXT: subb %cl, %al
|
|
; AVX-NEXT: movzbl %al, %eax
|
|
; AVX-NEXT: cmovol %esi, %eax
|
|
; AVX-NEXT: movb %al, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <1 x i8>, <1 x i8>* %px
|
|
%y = load <1 x i8>, <1 x i8>* %py
|
|
%z = call <1 x i8> @llvm.ssub.sat.v1i8(<1 x i8> %x, <1 x i8> %y)
|
|
store <1 x i8> %z, <1 x i8>* %pz
|
|
ret void
|
|
}
|
|
|
|
define void @v1i16(<1 x i16>* %px, <1 x i16>* %py, <1 x i16>* %pz) nounwind {
|
|
; SSE-LABEL: v1i16:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movzwl (%rdi), %eax
|
|
; SSE-NEXT: movzwl (%rsi), %ecx
|
|
; SSE-NEXT: xorl %esi, %esi
|
|
; SSE-NEXT: cmpw %cx, %ax
|
|
; SSE-NEXT: setns %sil
|
|
; SSE-NEXT: addl $32767, %esi # imm = 0x7FFF
|
|
; SSE-NEXT: subw %cx, %ax
|
|
; SSE-NEXT: cmovol %esi, %eax
|
|
; SSE-NEXT: movw %ax, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v1i16:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: movzwl (%rdi), %eax
|
|
; AVX-NEXT: movzwl (%rsi), %ecx
|
|
; AVX-NEXT: xorl %esi, %esi
|
|
; AVX-NEXT: cmpw %cx, %ax
|
|
; AVX-NEXT: setns %sil
|
|
; AVX-NEXT: addl $32767, %esi # imm = 0x7FFF
|
|
; AVX-NEXT: subw %cx, %ax
|
|
; AVX-NEXT: cmovol %esi, %eax
|
|
; AVX-NEXT: movw %ax, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%x = load <1 x i16>, <1 x i16>* %px
|
|
%y = load <1 x i16>, <1 x i16>* %py
|
|
%z = call <1 x i16> @llvm.ssub.sat.v1i16(<1 x i16> %x, <1 x i16> %y)
|
|
store <1 x i16> %z, <1 x i16>* %pz
|
|
ret void
|
|
}
|
|
|
|
; Promotion
|
|
|
|
define <16 x i4> @v16i4(<16 x i4> %x, <16 x i4> %y) nounwind {
|
|
; SSE-LABEL: v16i4:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psllw $4, %xmm1
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; SSE-NEXT: pand %xmm2, %xmm1
|
|
; SSE-NEXT: psllw $4, %xmm0
|
|
; SSE-NEXT: pand %xmm2, %xmm0
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: psrlw $4, %xmm0
|
|
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; SSE-NEXT: pxor %xmm1, %xmm0
|
|
; SSE-NEXT: psubb %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v16i4:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vpsllw $4, %xmm1, %xmm1
|
|
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
|
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
|
|
; AVX-NEXT: vpsllw $4, %xmm0, %xmm0
|
|
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
|
|
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm0
|
|
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
|
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
|
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%z = call <16 x i4> @llvm.ssub.sat.v16i4(<16 x i4> %x, <16 x i4> %y)
|
|
ret <16 x i4> %z
|
|
}
|
|
|
|
define <16 x i1> @v16i1(<16 x i1> %x, <16 x i1> %y) nounwind {
|
|
; SSE-LABEL: v16i1:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: psllw $7, %xmm1
|
|
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128]
|
|
; SSE-NEXT: pand %xmm2, %xmm1
|
|
; SSE-NEXT: psllw $7, %xmm0
|
|
; SSE-NEXT: pand %xmm2, %xmm0
|
|
; SSE-NEXT: psubsb %xmm1, %xmm0
|
|
; SSE-NEXT: pxor %xmm1, %xmm1
|
|
; SSE-NEXT: pcmpgtb %xmm0, %xmm1
|
|
; SSE-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v16i1:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpsllw $7, %xmm1, %xmm1
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128]
|
|
; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v16i1:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsllw $7, %xmm1, %xmm1
|
|
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128]
|
|
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpsllw $7, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v16i1:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsllw $7, %xmm0, %xmm0
|
|
; AVX512-NEXT: vpmovb2m %xmm0, %k0
|
|
; AVX512-NEXT: vpsllw $7, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpmovb2m %xmm0, %k1
|
|
; AVX512-NEXT: kandnw %k0, %k1, %k0
|
|
; AVX512-NEXT: vpmovm2b %k0, %xmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <16 x i1> @llvm.ssub.sat.v16i1(<16 x i1> %x, <16 x i1> %y)
|
|
ret <16 x i1> %z
|
|
}
|
|
|
|
; Expanded
|
|
|
|
define <2 x i32> @v2i32(<2 x i32> %x, <2 x i32> %y) nounwind {
|
|
; SSE2-LABEL: v2i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; SSE2-NEXT: psubd %xmm1, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; SSE2-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSE2-NEXT: psrld $1, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm1
|
|
; SSE2-NEXT: pand %xmm0, %xmm1
|
|
; SSE2-NEXT: pandn %xmm3, %xmm0
|
|
; SSE2-NEXT: por %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v2i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm3
|
|
; SSSE3-NEXT: psubd %xmm1, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm1, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm1
|
|
; SSSE3-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSSE3-NEXT: psrld $1, %xmm2
|
|
; SSSE3-NEXT: por %xmm2, %xmm1
|
|
; SSSE3-NEXT: pand %xmm0, %xmm1
|
|
; SSSE3-NEXT: pandn %xmm3, %xmm0
|
|
; SSSE3-NEXT: por %xmm1, %xmm0
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v2i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pxor %xmm0, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm3
|
|
; SSE41-NEXT: psubd %xmm1, %xmm3
|
|
; SSE41-NEXT: pcmpgtd %xmm0, %xmm1
|
|
; SSE41-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSE41-NEXT: pxor %xmm1, %xmm2
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm1 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, {{.*}}(%rip), %xmm1
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm1, %xmm3
|
|
; SSE41-NEXT: movaps %xmm3, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v2i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm2
|
|
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vmovaps {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX1-NEXT: vblendvps %xmm1, {{.*}}(%rip), %xmm2, %xmm2
|
|
; AVX1-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v2i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm2
|
|
; AVX2-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm2 = [2147483647,2147483647,2147483647,2147483647]
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX2-NEXT: vblendvps %xmm1, %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v2i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtd %xmm2, %xmm1, %k0
|
|
; AVX512-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpcmpgtd %xmm1, %xmm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtd %xmm1, %xmm2, %k2
|
|
; AVX512-NEXT: vpbroadcastd {{.*#+}} xmm0 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX512-NEXT: vpbroadcastd {{.*}}(%rip), %xmm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa %xmm1, %xmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <2 x i32> @llvm.ssub.sat.v2i32(<2 x i32> %x, <2 x i32> %y)
|
|
ret <2 x i32> %z
|
|
}
|
|
|
|
define <4 x i32> @v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
|
|
; SSE2-LABEL: v4i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; SSE2-NEXT: psubd %xmm1, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; SSE2-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSE2-NEXT: psrld $1, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm1
|
|
; SSE2-NEXT: pand %xmm0, %xmm1
|
|
; SSE2-NEXT: pandn %xmm3, %xmm0
|
|
; SSE2-NEXT: por %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v4i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm3
|
|
; SSSE3-NEXT: psubd %xmm1, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm1, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm1
|
|
; SSSE3-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSSE3-NEXT: psrld $1, %xmm2
|
|
; SSSE3-NEXT: por %xmm2, %xmm1
|
|
; SSSE3-NEXT: pand %xmm0, %xmm1
|
|
; SSSE3-NEXT: pandn %xmm3, %xmm0
|
|
; SSSE3-NEXT: por %xmm1, %xmm0
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v4i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pxor %xmm0, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm3
|
|
; SSE41-NEXT: psubd %xmm1, %xmm3
|
|
; SSE41-NEXT: pcmpgtd %xmm0, %xmm1
|
|
; SSE41-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSE41-NEXT: pxor %xmm1, %xmm2
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm1 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, {{.*}}(%rip), %xmm1
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm1, %xmm3
|
|
; SSE41-NEXT: movaps %xmm3, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v4i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm2
|
|
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vmovaps {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX1-NEXT: vblendvps %xmm1, {{.*}}(%rip), %xmm2, %xmm2
|
|
; AVX1-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v4i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm2
|
|
; AVX2-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm2 = [2147483647,2147483647,2147483647,2147483647]
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX2-NEXT: vblendvps %xmm1, %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v4i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtd %xmm2, %xmm1, %k0
|
|
; AVX512-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpcmpgtd %xmm1, %xmm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtd %xmm1, %xmm2, %k2
|
|
; AVX512-NEXT: vpbroadcastd {{.*#+}} xmm0 = [2147483648,2147483648,2147483648,2147483648]
|
|
; AVX512-NEXT: vpbroadcastd {{.*}}(%rip), %xmm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa %xmm1, %xmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> %x, <4 x i32> %y)
|
|
ret <4 x i32> %z
|
|
}
|
|
|
|
define <8 x i32> @v8i32(<8 x i32> %x, <8 x i32> %y) nounwind {
|
|
; SSE2-LABEL: v8i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
|
; SSE2-NEXT: psubd %xmm2, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm2
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm0
|
|
; SSE2-NEXT: pxor %xmm2, %xmm0
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm6
|
|
; SSE2-NEXT: pandn %xmm2, %xmm6
|
|
; SSE2-NEXT: pxor %xmm7, %xmm7
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm7
|
|
; SSE2-NEXT: psrld $1, %xmm7
|
|
; SSE2-NEXT: por %xmm7, %xmm6
|
|
; SSE2-NEXT: pand %xmm0, %xmm6
|
|
; SSE2-NEXT: pandn %xmm5, %xmm0
|
|
; SSE2-NEXT: por %xmm6, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm5
|
|
; SSE2-NEXT: psubd %xmm3, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm1
|
|
; SSE2-NEXT: pxor %xmm3, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm3
|
|
; SSE2-NEXT: pandn %xmm2, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm4
|
|
; SSE2-NEXT: psrld $1, %xmm4
|
|
; SSE2-NEXT: por %xmm4, %xmm3
|
|
; SSE2-NEXT: pand %xmm1, %xmm3
|
|
; SSE2-NEXT: pandn %xmm5, %xmm1
|
|
; SSE2-NEXT: por %xmm3, %xmm1
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v8i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm5
|
|
; SSSE3-NEXT: psubd %xmm2, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm2
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm0
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSSE3-NEXT: movdqa %xmm5, %xmm6
|
|
; SSSE3-NEXT: pandn %xmm2, %xmm6
|
|
; SSSE3-NEXT: pxor %xmm7, %xmm7
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm7
|
|
; SSSE3-NEXT: psrld $1, %xmm7
|
|
; SSSE3-NEXT: por %xmm7, %xmm6
|
|
; SSSE3-NEXT: pand %xmm0, %xmm6
|
|
; SSSE3-NEXT: pandn %xmm5, %xmm0
|
|
; SSSE3-NEXT: por %xmm6, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm5
|
|
; SSSE3-NEXT: psubd %xmm3, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm5, %xmm3
|
|
; SSSE3-NEXT: pandn %xmm2, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm4
|
|
; SSSE3-NEXT: psrld $1, %xmm4
|
|
; SSSE3-NEXT: por %xmm4, %xmm3
|
|
; SSSE3-NEXT: pand %xmm1, %xmm3
|
|
; SSSE3-NEXT: pandn %xmm5, %xmm1
|
|
; SSSE3-NEXT: por %xmm3, %xmm1
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v8i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm4
|
|
; SSE41-NEXT: pxor %xmm8, %xmm8
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm5
|
|
; SSE41-NEXT: psubd %xmm2, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm8, %xmm2
|
|
; SSE41-NEXT: pcmpgtd %xmm5, %xmm4
|
|
; SSE41-NEXT: pxor %xmm2, %xmm4
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm7 = [2147483647,2147483647,2147483647,2147483647]
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm6 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE41-NEXT: movaps %xmm6, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm7, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm2, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE41-NEXT: psubd %xmm3, %xmm2
|
|
; SSE41-NEXT: pcmpgtd %xmm8, %xmm3
|
|
; SSE41-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSE41-NEXT: pxor %xmm3, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm7, %xmm6
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm6, %xmm2
|
|
; SSE41-NEXT: movaps %xmm5, %xmm0
|
|
; SSE41-NEXT: movaps %xmm2, %xmm1
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v8i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm2, %xmm4
|
|
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm3
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: vxorps %ymm0, %ymm3, %ymm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
|
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX1-NEXT: vblendvps %ymm1, {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX1-NEXT: vblendvps %ymm0, %ymm2, %ymm1, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v8i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpgtd %ymm2, %ymm1, %ymm2
|
|
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm1
|
|
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpxor %ymm0, %ymm2, %ymm0
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm2 = [2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647]
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX2-NEXT: vblendvps %ymm1, %ymm2, %ymm3, %ymm2
|
|
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm1, %ymm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v8i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtd %ymm2, %ymm1, %k0
|
|
; AVX512-NEXT: vpsubd %ymm1, %ymm0, %ymm1
|
|
; AVX512-NEXT: vpcmpgtd %ymm1, %ymm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtd %ymm1, %ymm2, %k2
|
|
; AVX512-NEXT: vpbroadcastd {{.*#+}} ymm0 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX512-NEXT: vpbroadcastd {{.*}}(%rip), %ymm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa32 %ymm0, %ymm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa %ymm1, %ymm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <8 x i32> @llvm.ssub.sat.v8i32(<8 x i32> %x, <8 x i32> %y)
|
|
ret <8 x i32> %z
|
|
}
|
|
|
|
define <16 x i32> @v16i32(<16 x i32> %x, <16 x i32> %y) nounwind {
|
|
; SSE2-LABEL: v16i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm9
|
|
; SSE2-NEXT: psubd %xmm4, %xmm9
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm9, %xmm0
|
|
; SSE2-NEXT: pxor %xmm4, %xmm0
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm10 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE2-NEXT: movdqa %xmm9, %xmm11
|
|
; SSE2-NEXT: pandn %xmm10, %xmm11
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm9, %xmm4
|
|
; SSE2-NEXT: psrld $1, %xmm4
|
|
; SSE2-NEXT: por %xmm4, %xmm11
|
|
; SSE2-NEXT: pand %xmm0, %xmm11
|
|
; SSE2-NEXT: pandn %xmm9, %xmm0
|
|
; SSE2-NEXT: por %xmm11, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm9
|
|
; SSE2-NEXT: psubd %xmm5, %xmm9
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm9, %xmm1
|
|
; SSE2-NEXT: pxor %xmm5, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm9, %xmm5
|
|
; SSE2-NEXT: pandn %xmm10, %xmm5
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm9, %xmm4
|
|
; SSE2-NEXT: psrld $1, %xmm4
|
|
; SSE2-NEXT: por %xmm4, %xmm5
|
|
; SSE2-NEXT: pand %xmm1, %xmm5
|
|
; SSE2-NEXT: pandn %xmm9, %xmm1
|
|
; SSE2-NEXT: por %xmm5, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm4
|
|
; SSE2-NEXT: psubd %xmm6, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm2
|
|
; SSE2-NEXT: pxor %xmm6, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
; SSE2-NEXT: pandn %xmm10, %xmm5
|
|
; SSE2-NEXT: pxor %xmm6, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm6
|
|
; SSE2-NEXT: psrld $1, %xmm6
|
|
; SSE2-NEXT: por %xmm6, %xmm5
|
|
; SSE2-NEXT: pand %xmm2, %xmm5
|
|
; SSE2-NEXT: pandn %xmm4, %xmm2
|
|
; SSE2-NEXT: por %xmm5, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm4
|
|
; SSE2-NEXT: psubd %xmm7, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm7
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm3
|
|
; SSE2-NEXT: pxor %xmm7, %xmm3
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
; SSE2-NEXT: pandn %xmm10, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm8
|
|
; SSE2-NEXT: psrld $1, %xmm8
|
|
; SSE2-NEXT: por %xmm8, %xmm5
|
|
; SSE2-NEXT: pand %xmm3, %xmm5
|
|
; SSE2-NEXT: pandn %xmm4, %xmm3
|
|
; SSE2-NEXT: por %xmm5, %xmm3
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v16i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm8
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm9
|
|
; SSSE3-NEXT: psubd %xmm4, %xmm9
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm9, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm0
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm10 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSSE3-NEXT: movdqa %xmm9, %xmm11
|
|
; SSSE3-NEXT: pandn %xmm10, %xmm11
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm9, %xmm4
|
|
; SSSE3-NEXT: psrld $1, %xmm4
|
|
; SSSE3-NEXT: por %xmm4, %xmm11
|
|
; SSSE3-NEXT: pand %xmm0, %xmm11
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm0
|
|
; SSSE3-NEXT: por %xmm11, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm9
|
|
; SSSE3-NEXT: psubd %xmm5, %xmm9
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm9, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm9, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm10, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm9, %xmm4
|
|
; SSSE3-NEXT: psrld $1, %xmm4
|
|
; SSSE3-NEXT: por %xmm4, %xmm5
|
|
; SSSE3-NEXT: pand %xmm1, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm1
|
|
; SSSE3-NEXT: por %xmm5, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm4
|
|
; SSSE3-NEXT: psubd %xmm6, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm6, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm10, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm6, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm6
|
|
; SSSE3-NEXT: psrld $1, %xmm6
|
|
; SSSE3-NEXT: por %xmm6, %xmm5
|
|
; SSSE3-NEXT: pand %xmm2, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm4, %xmm2
|
|
; SSSE3-NEXT: por %xmm5, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm4
|
|
; SSSE3-NEXT: psubd %xmm7, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm7
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm3
|
|
; SSSE3-NEXT: pxor %xmm7, %xmm3
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm10, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm8
|
|
; SSSE3-NEXT: psrld $1, %xmm8
|
|
; SSSE3-NEXT: por %xmm8, %xmm5
|
|
; SSSE3-NEXT: pand %xmm3, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm4, %xmm3
|
|
; SSSE3-NEXT: por %xmm5, %xmm3
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v16i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm8
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm3
|
|
; SSE41-NEXT: pxor %xmm10, %xmm10
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm9
|
|
; SSE41-NEXT: psubd %xmm4, %xmm9
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm4
|
|
; SSE41-NEXT: pcmpgtd %xmm9, %xmm3
|
|
; SSE41-NEXT: pxor %xmm4, %xmm3
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm12 = [2147483647,2147483647,2147483647,2147483647]
|
|
; SSE41-NEXT: movaps {{.*#+}} xmm11 = [2147483648,2147483648,2147483648,2147483648]
|
|
; SSE41-NEXT: movaps %xmm11, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm9, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm12, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm4, %xmm9
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE41-NEXT: psubd %xmm5, %xmm4
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm4, %xmm1
|
|
; SSE41-NEXT: pxor %xmm5, %xmm1
|
|
; SSE41-NEXT: movaps %xmm11, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm12, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm3, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm3
|
|
; SSE41-NEXT: psubd %xmm6, %xmm3
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm6
|
|
; SSE41-NEXT: pcmpgtd %xmm3, %xmm2
|
|
; SSE41-NEXT: pxor %xmm6, %xmm2
|
|
; SSE41-NEXT: movaps %xmm11, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm12, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm1, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm8, %xmm5
|
|
; SSE41-NEXT: psubd %xmm7, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm7
|
|
; SSE41-NEXT: pcmpgtd %xmm5, %xmm8
|
|
; SSE41-NEXT: pxor %xmm7, %xmm8
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm12, %xmm11
|
|
; SSE41-NEXT: movdqa %xmm8, %xmm0
|
|
; SSE41-NEXT: blendvps %xmm0, %xmm11, %xmm5
|
|
; SSE41-NEXT: movaps %xmm9, %xmm0
|
|
; SSE41-NEXT: movaps %xmm4, %xmm1
|
|
; SSE41-NEXT: movaps %xmm3, %xmm2
|
|
; SSE41-NEXT: movaps %xmm5, %xmm3
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v16i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpgtd %xmm5, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpcmpgtd %xmm5, %xmm2, %xmm7
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm7, %ymm6
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm7
|
|
; AVX1-NEXT: vpsubd %xmm4, %xmm7, %xmm4
|
|
; AVX1-NEXT: vpcmpgtd %xmm4, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm0
|
|
; AVX1-NEXT: vxorps %ymm0, %ymm6, %ymm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: vmovaps {{.*#+}} ymm4 = [2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647]
|
|
; AVX1-NEXT: vmovaps {{.*#+}} ymm6 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX1-NEXT: vblendvps %ymm2, %ymm4, %ymm6, %ymm7
|
|
; AVX1-NEXT: vblendvps %ymm0, %ymm7, %ymm2, %ymm0
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm5, %xmm2, %xmm7
|
|
; AVX1-NEXT: vpcmpgtd %xmm5, %xmm3, %xmm5
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm5, %ymm5
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm7
|
|
; AVX1-NEXT: vpsubd %xmm2, %xmm7, %xmm2
|
|
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpsubd %xmm3, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm1, %ymm1
|
|
; AVX1-NEXT: vxorps %ymm1, %ymm5, %ymm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
|
; AVX1-NEXT: vblendvps %ymm2, %ymm4, %ymm6, %ymm3
|
|
; AVX1-NEXT: vblendvps %ymm1, %ymm3, %ymm2, %ymm1
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v16i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpgtd %ymm4, %ymm2, %ymm5
|
|
; AVX2-NEXT: vpsubd %ymm2, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpcmpgtd %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpxor %ymm0, %ymm5, %ymm0
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm5 = [2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647,2147483647]
|
|
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX2-NEXT: vblendvps %ymm2, %ymm5, %ymm6, %ymm7
|
|
; AVX2-NEXT: vblendvps %ymm0, %ymm7, %ymm2, %ymm0
|
|
; AVX2-NEXT: vpcmpgtd %ymm4, %ymm3, %ymm2
|
|
; AVX2-NEXT: vpsubd %ymm3, %ymm1, %ymm3
|
|
; AVX2-NEXT: vpcmpgtd %ymm3, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpxor %ymm1, %ymm2, %ymm1
|
|
; AVX2-NEXT: vblendvps %ymm3, %ymm5, %ymm6, %ymm2
|
|
; AVX2-NEXT: vblendvps %ymm1, %ymm2, %ymm3, %ymm1
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtd %zmm2, %zmm1, %k0
|
|
; AVX512-NEXT: vpsubd %zmm1, %zmm0, %zmm1
|
|
; AVX512-NEXT: vpcmpgtd %zmm1, %zmm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtd %zmm1, %zmm2, %k2
|
|
; AVX512-NEXT: vpbroadcastd {{.*#+}} zmm0 = [2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648,2147483648]
|
|
; AVX512-NEXT: vpbroadcastd {{.*}}(%rip), %zmm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa32 %zmm0, %zmm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <16 x i32> @llvm.ssub.sat.v16i32(<16 x i32> %x, <16 x i32> %y)
|
|
ret <16 x i32> %z
|
|
}
|
|
|
|
define <2 x i64> @v2i64(<2 x i64> %x, <2 x i64> %y) nounwind {
|
|
; SSE2-LABEL: v2i64:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; SSE2-NEXT: pxor %xmm2, %xmm3
|
|
; SSE2-NEXT: psubq %xmm1, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm4
|
|
; SSE2-NEXT: pxor %xmm2, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm6, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm3, %xmm4
|
|
; SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm5, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm1, %xmm2
|
|
; SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; SSE2-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm3
|
|
; SSE2-NEXT: por %xmm3, %xmm1
|
|
; SSE2-NEXT: pand %xmm2, %xmm1
|
|
; SSE2-NEXT: pandn %xmm0, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v2i64:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm3
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm3
|
|
; SSSE3-NEXT: psubq %xmm1, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm6, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm3, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm3[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm5, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm1, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm1
|
|
; SSSE3-NEXT: pandn {{.*}}(%rip), %xmm1
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSSE3-NEXT: pand {{.*}}(%rip), %xmm3
|
|
; SSSE3-NEXT: por %xmm3, %xmm1
|
|
; SSSE3-NEXT: pand %xmm2, %xmm1
|
|
; SSSE3-NEXT: pandn %xmm0, %xmm2
|
|
; SSSE3-NEXT: por %xmm2, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v2i64:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [2147483648,2147483648]
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm3
|
|
; SSE41-NEXT: pxor %xmm0, %xmm3
|
|
; SSE41-NEXT: psubq %xmm1, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm4
|
|
; SSE41-NEXT: pxor %xmm0, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm5
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm4, %xmm3
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm3[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm5, %xmm4
|
|
; SSE41-NEXT: por %xmm3, %xmm4
|
|
; SSE41-NEXT: pxor %xmm0, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm5
|
|
; SSE41-NEXT: pcmpeqd %xmm0, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm0, %xmm1
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm1[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm5, %xmm3
|
|
; SSE41-NEXT: por %xmm1, %xmm3
|
|
; SSE41-NEXT: pxor %xmm4, %xmm3
|
|
; SSE41-NEXT: movapd {{.*#+}} xmm1 = [9223372036854775808,9223372036854775808]
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, {{.*}}(%rip), %xmm1
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm1, %xmm2
|
|
; SSE41-NEXT: movapd %xmm2, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v2i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm1, %xmm2
|
|
; AVX1-NEXT: vpsubq %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vmovapd {{.*#+}} xmm2 = [9223372036854775808,9223372036854775808]
|
|
; AVX1-NEXT: vblendvpd %xmm1, {{.*}}(%rip), %xmm2, %xmm2
|
|
; AVX1-NEXT: vblendvpd %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v2i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpgtq %xmm2, %xmm1, %xmm2
|
|
; AVX2-NEXT: vpsubq %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vmovapd {{.*#+}} xmm2 = [9223372036854775808,9223372036854775808]
|
|
; AVX2-NEXT: vblendvpd %xmm1, {{.*}}(%rip), %xmm2, %xmm2
|
|
; AVX2-NEXT: vblendvpd %xmm0, %xmm2, %xmm1, %xmm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v2i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtq %xmm2, %xmm1, %k0
|
|
; AVX512-NEXT: vpsubq %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpcmpgtq %xmm1, %xmm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtq %xmm1, %xmm2, %k2
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} xmm0 = [9223372036854775808,9223372036854775808]
|
|
; AVX512-NEXT: vmovdqa64 {{.*}}(%rip), %xmm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa64 %xmm0, %xmm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa %xmm1, %xmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <2 x i64> @llvm.ssub.sat.v2i64(<2 x i64> %x, <2 x i64> %y)
|
|
ret <2 x i64> %z
|
|
}
|
|
|
|
define <4 x i64> @v4i64(<4 x i64> %x, <4 x i64> %y) nounwind {
|
|
; SSE2-LABEL: v4i64:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
|
; SSE2-NEXT: pxor %xmm8, %xmm5
|
|
; SSE2-NEXT: psubq %xmm2, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm6
|
|
; SSE2-NEXT: pxor %xmm8, %xmm6
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm7
|
|
; SSE2-NEXT: pcmpgtd %xmm6, %xmm7
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm7[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm5, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm4, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm5, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm6, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm2, %xmm7
|
|
; SSE2-NEXT: pxor %xmm4, %xmm7
|
|
; SSE2-NEXT: movdqa %xmm7, %xmm4
|
|
; SSE2-NEXT: pandn %xmm0, %xmm4
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm9 = [9223372036854775808,9223372036854775808]
|
|
; SSE2-NEXT: pxor %xmm5, %xmm5
|
|
; SSE2-NEXT: pxor %xmm6, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm6
|
|
; SSE2-NEXT: pandn %xmm9, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm10 = [9223372036854775807,9223372036854775807]
|
|
; SSE2-NEXT: pand %xmm10, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: pand %xmm7, %xmm0
|
|
; SSE2-NEXT: por %xmm4, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE2-NEXT: pxor %xmm8, %xmm2
|
|
; SSE2-NEXT: psubq %xmm3, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm7
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm7
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm7[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm6, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm2, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm3
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm2
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm2[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm6, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm3, %xmm2
|
|
; SSE2-NEXT: pxor %xmm4, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm3
|
|
; SSE2-NEXT: pandn %xmm1, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm5
|
|
; SSE2-NEXT: pandn %xmm9, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm10, %xmm4
|
|
; SSE2-NEXT: por %xmm4, %xmm1
|
|
; SSE2-NEXT: pand %xmm2, %xmm1
|
|
; SSE2-NEXT: por %xmm3, %xmm1
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v4i64:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm5
|
|
; SSSE3-NEXT: psubq %xmm2, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm6
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm6
|
|
; SSSE3-NEXT: movdqa %xmm5, %xmm7
|
|
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm7
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm7[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm4, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm5, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm6, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm2, %xmm7
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm7
|
|
; SSSE3-NEXT: movdqa %xmm7, %xmm4
|
|
; SSSE3-NEXT: pandn %xmm0, %xmm4
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm9 = [9223372036854775808,9223372036854775808]
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm6, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm6
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm10 = [9223372036854775807,9223372036854775807]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm2
|
|
; SSSE3-NEXT: por %xmm2, %xmm0
|
|
; SSSE3-NEXT: pand %xmm7, %xmm0
|
|
; SSSE3-NEXT: por %xmm4, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm2
|
|
; SSSE3-NEXT: psubq %xmm3, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm7
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm7
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm7[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm2, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm6, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm2, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm3
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm2
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm2[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm6, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm3, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm3
|
|
; SSSE3-NEXT: pandn %xmm1, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm4
|
|
; SSSE3-NEXT: por %xmm4, %xmm1
|
|
; SSSE3-NEXT: pand %xmm2, %xmm1
|
|
; SSSE3-NEXT: por %xmm3, %xmm1
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v4i64:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm4
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm9 = [2147483648,2147483648]
|
|
; SSE41-NEXT: pxor %xmm9, %xmm0
|
|
; SSE41-NEXT: psubq %xmm2, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm5
|
|
; SSE41-NEXT: pxor %xmm9, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm7
|
|
; SSE41-NEXT: pcmpeqd %xmm5, %xmm7
|
|
; SSE41-NEXT: pcmpgtd %xmm5, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm7, %xmm6
|
|
; SSE41-NEXT: por %xmm0, %xmm6
|
|
; SSE41-NEXT: pxor %xmm9, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm9, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm9, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm2[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm5
|
|
; SSE41-NEXT: por %xmm2, %xmm5
|
|
; SSE41-NEXT: pxor %xmm6, %xmm5
|
|
; SSE41-NEXT: movapd {{.*#+}} xmm8 = [9223372036854775807,9223372036854775807]
|
|
; SSE41-NEXT: movapd {{.*#+}} xmm7 = [9223372036854775808,9223372036854775808]
|
|
; SSE41-NEXT: movapd %xmm7, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm8, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm2, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: pxor %xmm9, %xmm0
|
|
; SSE41-NEXT: psubq %xmm3, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE41-NEXT: pxor %xmm9, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm5
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm2, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm5, %xmm6
|
|
; SSE41-NEXT: por %xmm0, %xmm6
|
|
; SSE41-NEXT: pxor %xmm9, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm9, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm9, %xmm3
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm2
|
|
; SSE41-NEXT: por %xmm3, %xmm2
|
|
; SSE41-NEXT: pxor %xmm6, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm8, %xmm7
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm7, %xmm1
|
|
; SSE41-NEXT: movapd %xmm4, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v4i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm4
|
|
; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm3
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vpsubq %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpsubq %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: vxorpd %ymm0, %ymm3, %ymm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
|
; AVX1-NEXT: vmovapd {{.*#+}} ymm2 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX1-NEXT: vblendvpd %ymm1, {{.*}}(%rip), %ymm2, %ymm2
|
|
; AVX1-NEXT: vblendvpd %ymm0, %ymm2, %ymm1, %ymm0
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v4i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpgtq %ymm2, %ymm1, %ymm2
|
|
; AVX2-NEXT: vpsubq %ymm1, %ymm0, %ymm1
|
|
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpxor %ymm0, %ymm2, %ymm0
|
|
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm2 = [9223372036854775807,9223372036854775807,9223372036854775807,9223372036854775807]
|
|
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX2-NEXT: vblendvpd %ymm1, %ymm2, %ymm3, %ymm2
|
|
; AVX2-NEXT: vblendvpd %ymm0, %ymm2, %ymm1, %ymm0
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v4i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtq %ymm2, %ymm1, %k0
|
|
; AVX512-NEXT: vpsubq %ymm1, %ymm0, %ymm1
|
|
; AVX512-NEXT: vpcmpgtq %ymm1, %ymm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtq %ymm1, %ymm2, %k2
|
|
; AVX512-NEXT: vpbroadcastq {{.*#+}} ymm0 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX512-NEXT: vpbroadcastq {{.*}}(%rip), %ymm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa64 %ymm0, %ymm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa %ymm1, %ymm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <4 x i64> @llvm.ssub.sat.v4i64(<4 x i64> %x, <4 x i64> %y)
|
|
ret <4 x i64> %z
|
|
}
|
|
|
|
define <8 x i64> @v8i64(<8 x i64> %x, <8 x i64> %y) nounwind {
|
|
; SSE2-LABEL: v8i64:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm9
|
|
; SSE2-NEXT: pxor %xmm8, %xmm9
|
|
; SSE2-NEXT: psubq %xmm4, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm10
|
|
; SSE2-NEXT: pxor %xmm8, %xmm10
|
|
; SSE2-NEXT: movdqa %xmm9, %xmm11
|
|
; SSE2-NEXT: pcmpgtd %xmm10, %xmm11
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm11[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm10
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm10[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm12, %xmm9
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm11[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm9, %xmm10
|
|
; SSE2-NEXT: pxor %xmm8, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm9
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm9
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm9[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm11, %xmm12
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm9[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm12, %xmm4
|
|
; SSE2-NEXT: pxor %xmm10, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm12
|
|
; SSE2-NEXT: pandn %xmm0, %xmm12
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm9 = [9223372036854775808,9223372036854775808]
|
|
; SSE2-NEXT: pxor %xmm11, %xmm11
|
|
; SSE2-NEXT: pxor %xmm10, %xmm10
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm10
|
|
; SSE2-NEXT: pandn %xmm9, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm10[1,1,3,3]
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm10 = [9223372036854775807,9223372036854775807]
|
|
; SSE2-NEXT: pand %xmm10, %xmm13
|
|
; SSE2-NEXT: por %xmm13, %xmm0
|
|
; SSE2-NEXT: pand %xmm4, %xmm0
|
|
; SSE2-NEXT: por %xmm12, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm12
|
|
; SSE2-NEXT: pxor %xmm8, %xmm12
|
|
; SSE2-NEXT: psubq %xmm5, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm12, %xmm13
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm13
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm14 = xmm13[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm12, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm14, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm13[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm4, %xmm12
|
|
; SSE2-NEXT: pxor %xmm8, %xmm5
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm4[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm13, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm5, %xmm4
|
|
; SSE2-NEXT: pxor %xmm12, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm12
|
|
; SSE2-NEXT: pandn %xmm1, %xmm12
|
|
; SSE2-NEXT: pxor %xmm5, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm5
|
|
; SSE2-NEXT: pandn %xmm9, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm10, %xmm5
|
|
; SSE2-NEXT: por %xmm5, %xmm1
|
|
; SSE2-NEXT: pand %xmm4, %xmm1
|
|
; SSE2-NEXT: por %xmm12, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm12
|
|
; SSE2-NEXT: pxor %xmm8, %xmm12
|
|
; SSE2-NEXT: psubq %xmm6, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm2, %xmm5
|
|
; SSE2-NEXT: pxor %xmm8, %xmm5
|
|
; SSE2-NEXT: movdqa %xmm12, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm13 = xmm4[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm12, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm13, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm5, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm6
|
|
; SSE2-NEXT: movdqa %xmm6, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm5[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm12, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm6, %xmm5
|
|
; SSE2-NEXT: pxor %xmm4, %xmm5
|
|
; SSE2-NEXT: movdqa %xmm5, %xmm4
|
|
; SSE2-NEXT: pandn %xmm2, %xmm4
|
|
; SSE2-NEXT: pxor %xmm6, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm6
|
|
; SSE2-NEXT: pandn %xmm9, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm10, %xmm6
|
|
; SSE2-NEXT: por %xmm6, %xmm2
|
|
; SSE2-NEXT: pand %xmm5, %xmm2
|
|
; SSE2-NEXT: por %xmm4, %xmm2
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm4
|
|
; SSE2-NEXT: pxor %xmm8, %xmm4
|
|
; SSE2-NEXT: psubq %xmm7, %xmm3
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm5
|
|
; SSE2-NEXT: pxor %xmm8, %xmm5
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm6[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm12, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm4, %xmm5
|
|
; SSE2-NEXT: pxor %xmm8, %xmm7
|
|
; SSE2-NEXT: movdqa %xmm7, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[0,0,2,2]
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm7
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm6, %xmm7
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: por %xmm7, %xmm4
|
|
; SSE2-NEXT: pxor %xmm5, %xmm4
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm5
|
|
; SSE2-NEXT: pandn %xmm3, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm11
|
|
; SSE2-NEXT: pandn %xmm9, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm11[1,1,3,3]
|
|
; SSE2-NEXT: pand %xmm10, %xmm6
|
|
; SSE2-NEXT: por %xmm6, %xmm3
|
|
; SSE2-NEXT: pand %xmm4, %xmm3
|
|
; SSE2-NEXT: por %xmm5, %xmm3
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: v8i64:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm8 = [2147483648,2147483648]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm9
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm9
|
|
; SSSE3-NEXT: psubq %xmm4, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm10
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm10
|
|
; SSSE3-NEXT: movdqa %xmm9, %xmm11
|
|
; SSSE3-NEXT: pcmpgtd %xmm10, %xmm11
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm11[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm9, %xmm10
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm9 = xmm10[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm12, %xmm9
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm10 = xmm11[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm9, %xmm10
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm9
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm9
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm11 = xmm9[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm11, %xmm12
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm9[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm12, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm10, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm12
|
|
; SSSE3-NEXT: pandn %xmm0, %xmm12
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm9 = [9223372036854775808,9223372036854775808]
|
|
; SSSE3-NEXT: pxor %xmm11, %xmm11
|
|
; SSSE3-NEXT: pxor %xmm10, %xmm10
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm10
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm13 = xmm10[1,1,3,3]
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm10 = [9223372036854775807,9223372036854775807]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm13
|
|
; SSSE3-NEXT: por %xmm13, %xmm0
|
|
; SSSE3-NEXT: pand %xmm4, %xmm0
|
|
; SSSE3-NEXT: por %xmm12, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm12
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm12
|
|
; SSSE3-NEXT: psubq %xmm5, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm12, %xmm13
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm13
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm14 = xmm13[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm12, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm14, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm13[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm4, %xmm12
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm5
|
|
; SSSE3-NEXT: movdqa %xmm5, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm13 = xmm4[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm13, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm5, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm12, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm12
|
|
; SSSE3-NEXT: pandn %xmm1, %xmm12
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm5
|
|
; SSSE3-NEXT: por %xmm5, %xmm1
|
|
; SSSE3-NEXT: pand %xmm4, %xmm1
|
|
; SSSE3-NEXT: por %xmm12, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm12
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm12
|
|
; SSSE3-NEXT: psubq %xmm6, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm2, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm5
|
|
; SSSE3-NEXT: movdqa %xmm12, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm13 = xmm4[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm12, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm13, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm5, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm6
|
|
; SSSE3-NEXT: movdqa %xmm6, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm5[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm12, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm6, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm5
|
|
; SSSE3-NEXT: movdqa %xmm5, %xmm4
|
|
; SSSE3-NEXT: pandn %xmm2, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm6, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm6
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm6
|
|
; SSSE3-NEXT: por %xmm6, %xmm2
|
|
; SSSE3-NEXT: pand %xmm5, %xmm2
|
|
; SSSE3-NEXT: por %xmm4, %xmm2
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm4
|
|
; SSSE3-NEXT: psubq %xmm7, %xmm3
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm5
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm6[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm12, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm4, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm7
|
|
; SSSE3-NEXT: movdqa %xmm7, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm8, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm4[0,0,2,2]
|
|
; SSSE3-NEXT: pcmpeqd %xmm8, %xmm7
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm6, %xmm7
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: por %xmm7, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm4
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm5
|
|
; SSSE3-NEXT: pandn %xmm3, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm11
|
|
; SSSE3-NEXT: pandn %xmm9, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm11[1,1,3,3]
|
|
; SSSE3-NEXT: pand %xmm10, %xmm6
|
|
; SSSE3-NEXT: por %xmm6, %xmm3
|
|
; SSSE3-NEXT: pand %xmm4, %xmm3
|
|
; SSSE3-NEXT: por %xmm5, %xmm3
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: v8i64:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm8
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm10 = [2147483648,2147483648]
|
|
; SSE41-NEXT: pxor %xmm10, %xmm0
|
|
; SSE41-NEXT: psubq %xmm4, %xmm8
|
|
; SSE41-NEXT: movdqa %xmm8, %xmm9
|
|
; SSE41-NEXT: pxor %xmm10, %xmm9
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm11
|
|
; SSE41-NEXT: pcmpeqd %xmm9, %xmm11
|
|
; SSE41-NEXT: pcmpgtd %xmm9, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm12 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm11, %xmm12
|
|
; SSE41-NEXT: por %xmm0, %xmm12
|
|
; SSE41-NEXT: pxor %xmm10, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm10, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm9 = xmm4[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm9
|
|
; SSE41-NEXT: por %xmm4, %xmm9
|
|
; SSE41-NEXT: pxor %xmm12, %xmm9
|
|
; SSE41-NEXT: movapd {{.*#+}} xmm12 = [9223372036854775807,9223372036854775807]
|
|
; SSE41-NEXT: movapd {{.*#+}} xmm11 = [9223372036854775808,9223372036854775808]
|
|
; SSE41-NEXT: movapd %xmm11, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm8, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm12, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm9, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm4, %xmm8
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: pxor %xmm10, %xmm0
|
|
; SSE41-NEXT: psubq %xmm5, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE41-NEXT: pxor %xmm10, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm9
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm9
|
|
; SSE41-NEXT: pcmpgtd %xmm4, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm13 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm9, %xmm13
|
|
; SSE41-NEXT: por %xmm0, %xmm13
|
|
; SSE41-NEXT: pxor %xmm10, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm5, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm10, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm5
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm5[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm4
|
|
; SSE41-NEXT: por %xmm5, %xmm4
|
|
; SSE41-NEXT: pxor %xmm13, %xmm4
|
|
; SSE41-NEXT: movapd %xmm11, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm12, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm5, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: pxor %xmm10, %xmm0
|
|
; SSE41-NEXT: psubq %xmm6, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm4
|
|
; SSE41-NEXT: pxor %xmm10, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm9
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm9
|
|
; SSE41-NEXT: pcmpgtd %xmm4, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm9, %xmm5
|
|
; SSE41-NEXT: por %xmm0, %xmm5
|
|
; SSE41-NEXT: pxor %xmm10, %xmm6
|
|
; SSE41-NEXT: movdqa %xmm6, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm10, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm6
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm6[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm4
|
|
; SSE41-NEXT: por %xmm6, %xmm4
|
|
; SSE41-NEXT: pxor %xmm5, %xmm4
|
|
; SSE41-NEXT: movapd %xmm11, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm12, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm5, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: pxor %xmm10, %xmm0
|
|
; SSE41-NEXT: psubq %xmm7, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm4
|
|
; SSE41-NEXT: pxor %xmm10, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm5
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm5
|
|
; SSE41-NEXT: pcmpgtd %xmm4, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm6 = xmm0[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm5, %xmm6
|
|
; SSE41-NEXT: por %xmm0, %xmm6
|
|
; SSE41-NEXT: pxor %xmm10, %xmm7
|
|
; SSE41-NEXT: movdqa %xmm7, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm10, %xmm0
|
|
; SSE41-NEXT: pcmpgtd %xmm10, %xmm7
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm7[0,0,2,2]
|
|
; SSE41-NEXT: pand %xmm0, %xmm4
|
|
; SSE41-NEXT: por %xmm7, %xmm4
|
|
; SSE41-NEXT: pxor %xmm6, %xmm4
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm12, %xmm11
|
|
; SSE41-NEXT: movdqa %xmm4, %xmm0
|
|
; SSE41-NEXT: blendvpd %xmm0, %xmm11, %xmm3
|
|
; SSE41-NEXT: movapd %xmm8, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: v8i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpgtq %xmm5, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpcmpgtq %xmm5, %xmm2, %xmm7
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm7, %ymm6
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm7
|
|
; AVX1-NEXT: vpsubq %xmm4, %xmm7, %xmm4
|
|
; AVX1-NEXT: vpcmpgtq %xmm4, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpsubq %xmm2, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm0
|
|
; AVX1-NEXT: vxorpd %ymm0, %ymm6, %ymm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: vmovapd {{.*#+}} ymm4 = [9223372036854775807,9223372036854775807,9223372036854775807,9223372036854775807]
|
|
; AVX1-NEXT: vmovapd {{.*#+}} ymm6 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX1-NEXT: vblendvpd %ymm2, %ymm4, %ymm6, %ymm7
|
|
; AVX1-NEXT: vblendvpd %ymm0, %ymm7, %ymm2, %ymm0
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm2
|
|
; AVX1-NEXT: vpcmpgtq %xmm5, %xmm2, %xmm7
|
|
; AVX1-NEXT: vpcmpgtq %xmm5, %xmm3, %xmm5
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm5, %ymm5
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm7
|
|
; AVX1-NEXT: vpsubq %xmm2, %xmm7, %xmm2
|
|
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpsubq %xmm3, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm1, %ymm1
|
|
; AVX1-NEXT: vxorpd %ymm1, %ymm5, %ymm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
|
; AVX1-NEXT: vblendvpd %ymm2, %ymm4, %ymm6, %ymm3
|
|
; AVX1-NEXT: vblendvpd %ymm1, %ymm3, %ymm2, %ymm1
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: v8i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm2, %ymm5
|
|
; AVX2-NEXT: vpsubq %ymm2, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpcmpgtq %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpxor %ymm0, %ymm5, %ymm0
|
|
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm5 = [9223372036854775807,9223372036854775807,9223372036854775807,9223372036854775807]
|
|
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX2-NEXT: vblendvpd %ymm2, %ymm5, %ymm6, %ymm7
|
|
; AVX2-NEXT: vblendvpd %ymm0, %ymm7, %ymm2, %ymm0
|
|
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm3, %ymm2
|
|
; AVX2-NEXT: vpsubq %ymm3, %ymm1, %ymm3
|
|
; AVX2-NEXT: vpcmpgtq %ymm3, %ymm1, %ymm1
|
|
; AVX2-NEXT: vpxor %ymm1, %ymm2, %ymm1
|
|
; AVX2-NEXT: vblendvpd %ymm3, %ymm5, %ymm6, %ymm2
|
|
; AVX2-NEXT: vblendvpd %ymm1, %ymm2, %ymm3, %ymm1
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v8i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512-NEXT: vpcmpgtq %zmm2, %zmm1, %k0
|
|
; AVX512-NEXT: vpsubq %zmm1, %zmm0, %zmm1
|
|
; AVX512-NEXT: vpcmpgtq %zmm1, %zmm0, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpgtq %zmm1, %zmm2, %k2
|
|
; AVX512-NEXT: vpbroadcastq {{.*#+}} zmm0 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
|
|
; AVX512-NEXT: vpbroadcastq {{.*}}(%rip), %zmm0 {%k2}
|
|
; AVX512-NEXT: vmovdqa64 %zmm0, %zmm1 {%k1}
|
|
; AVX512-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; AVX512-NEXT: retq
|
|
%z = call <8 x i64> @llvm.ssub.sat.v8i64(<8 x i64> %x, <8 x i64> %y)
|
|
ret <8 x i64> %z
|
|
}
|
|
|
|
define <2 x i128> @v2i128(<2 x i128> %x, <2 x i128> %y) nounwind {
|
|
; SSE-LABEL: v2i128:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: pushq %r15
|
|
; SSE-NEXT: pushq %r14
|
|
; SSE-NEXT: pushq %r13
|
|
; SSE-NEXT: pushq %r12
|
|
; SSE-NEXT: pushq %rbx
|
|
; SSE-NEXT: movq %rdi, %rax
|
|
; SSE-NEXT: movq {{[0-9]+}}(%rsp), %r11
|
|
; SSE-NEXT: movq {{[0-9]+}}(%rsp), %r14
|
|
; SSE-NEXT: subq {{[0-9]+}}(%rsp), %rcx
|
|
; SSE-NEXT: movq %r8, %r13
|
|
; SSE-NEXT: sbbq %r14, %r13
|
|
; SSE-NEXT: movq %r13, %r10
|
|
; SSE-NEXT: sarq $63, %r10
|
|
; SSE-NEXT: xorl %edi, %edi
|
|
; SSE-NEXT: testq %r13, %r13
|
|
; SSE-NEXT: setns %dil
|
|
; SSE-NEXT: movabsq $9223372036854775807, %r12 # imm = 0x7FFFFFFFFFFFFFFF
|
|
; SSE-NEXT: leaq (%rdi,%r12), %r15
|
|
; SSE-NEXT: testq %r8, %r8
|
|
; SSE-NEXT: setns %r8b
|
|
; SSE-NEXT: cmpb %dil, %r8b
|
|
; SSE-NEXT: setne %dil
|
|
; SSE-NEXT: testq %r14, %r14
|
|
; SSE-NEXT: setns %bl
|
|
; SSE-NEXT: cmpb %bl, %r8b
|
|
; SSE-NEXT: setne %bl
|
|
; SSE-NEXT: testb %dil, %bl
|
|
; SSE-NEXT: cmoveq %r13, %r15
|
|
; SSE-NEXT: cmoveq %rcx, %r10
|
|
; SSE-NEXT: subq %r9, %rsi
|
|
; SSE-NEXT: movq %rdx, %rdi
|
|
; SSE-NEXT: sbbq %r11, %rdi
|
|
; SSE-NEXT: setns %bl
|
|
; SSE-NEXT: movzbl %bl, %ebx
|
|
; SSE-NEXT: addq %rbx, %r12
|
|
; SSE-NEXT: movq %rdi, %rcx
|
|
; SSE-NEXT: sarq $63, %rcx
|
|
; SSE-NEXT: testq %r11, %r11
|
|
; SSE-NEXT: setns %r8b
|
|
; SSE-NEXT: testq %rdx, %rdx
|
|
; SSE-NEXT: setns %dl
|
|
; SSE-NEXT: cmpb %r8b, %dl
|
|
; SSE-NEXT: setne %r8b
|
|
; SSE-NEXT: cmpb %bl, %dl
|
|
; SSE-NEXT: setne %dl
|
|
; SSE-NEXT: testb %dl, %r8b
|
|
; SSE-NEXT: cmoveq %rsi, %rcx
|
|
; SSE-NEXT: cmoveq %rdi, %r12
|
|
; SSE-NEXT: movq %r15, 24(%rax)
|
|
; SSE-NEXT: movq %r10, 16(%rax)
|
|
; SSE-NEXT: movq %r12, 8(%rax)
|
|
; SSE-NEXT: movq %rcx, (%rax)
|
|
; SSE-NEXT: popq %rbx
|
|
; SSE-NEXT: popq %r12
|
|
; SSE-NEXT: popq %r13
|
|
; SSE-NEXT: popq %r14
|
|
; SSE-NEXT: popq %r15
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: v2i128:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: pushq %r15
|
|
; AVX-NEXT: pushq %r14
|
|
; AVX-NEXT: pushq %r13
|
|
; AVX-NEXT: pushq %r12
|
|
; AVX-NEXT: pushq %rbx
|
|
; AVX-NEXT: movq %rdi, %rax
|
|
; AVX-NEXT: movq {{[0-9]+}}(%rsp), %r11
|
|
; AVX-NEXT: movq {{[0-9]+}}(%rsp), %r14
|
|
; AVX-NEXT: subq {{[0-9]+}}(%rsp), %rcx
|
|
; AVX-NEXT: movq %r8, %r13
|
|
; AVX-NEXT: sbbq %r14, %r13
|
|
; AVX-NEXT: movq %r13, %r10
|
|
; AVX-NEXT: sarq $63, %r10
|
|
; AVX-NEXT: xorl %edi, %edi
|
|
; AVX-NEXT: testq %r13, %r13
|
|
; AVX-NEXT: setns %dil
|
|
; AVX-NEXT: movabsq $9223372036854775807, %r12 # imm = 0x7FFFFFFFFFFFFFFF
|
|
; AVX-NEXT: leaq (%rdi,%r12), %r15
|
|
; AVX-NEXT: testq %r8, %r8
|
|
; AVX-NEXT: setns %r8b
|
|
; AVX-NEXT: cmpb %dil, %r8b
|
|
; AVX-NEXT: setne %dil
|
|
; AVX-NEXT: testq %r14, %r14
|
|
; AVX-NEXT: setns %bl
|
|
; AVX-NEXT: cmpb %bl, %r8b
|
|
; AVX-NEXT: setne %bl
|
|
; AVX-NEXT: testb %dil, %bl
|
|
; AVX-NEXT: cmoveq %r13, %r15
|
|
; AVX-NEXT: cmoveq %rcx, %r10
|
|
; AVX-NEXT: subq %r9, %rsi
|
|
; AVX-NEXT: movq %rdx, %rdi
|
|
; AVX-NEXT: sbbq %r11, %rdi
|
|
; AVX-NEXT: setns %bl
|
|
; AVX-NEXT: movzbl %bl, %ebx
|
|
; AVX-NEXT: addq %rbx, %r12
|
|
; AVX-NEXT: movq %rdi, %rcx
|
|
; AVX-NEXT: sarq $63, %rcx
|
|
; AVX-NEXT: testq %r11, %r11
|
|
; AVX-NEXT: setns %r8b
|
|
; AVX-NEXT: testq %rdx, %rdx
|
|
; AVX-NEXT: setns %dl
|
|
; AVX-NEXT: cmpb %r8b, %dl
|
|
; AVX-NEXT: setne %r8b
|
|
; AVX-NEXT: cmpb %bl, %dl
|
|
; AVX-NEXT: setne %dl
|
|
; AVX-NEXT: testb %dl, %r8b
|
|
; AVX-NEXT: cmoveq %rsi, %rcx
|
|
; AVX-NEXT: cmoveq %rdi, %r12
|
|
; AVX-NEXT: movq %r15, 24(%rax)
|
|
; AVX-NEXT: movq %r10, 16(%rax)
|
|
; AVX-NEXT: movq %r12, 8(%rax)
|
|
; AVX-NEXT: movq %rcx, (%rax)
|
|
; AVX-NEXT: popq %rbx
|
|
; AVX-NEXT: popq %r12
|
|
; AVX-NEXT: popq %r13
|
|
; AVX-NEXT: popq %r14
|
|
; AVX-NEXT: popq %r15
|
|
; AVX-NEXT: retq
|
|
%z = call <2 x i128> @llvm.ssub.sat.v2i128(<2 x i128> %x, <2 x i128> %y)
|
|
ret <2 x i128> %z
|
|
}
|