forked from OSchip/llvm-project
2759 lines
112 KiB
LLVM
2759 lines
112 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 i32>, <1 x i1>} @llvm.smul.with.overflow.v1i32(<1 x i32>, <1 x i32>)
|
|
declare {<2 x i32>, <2 x i1>} @llvm.smul.with.overflow.v2i32(<2 x i32>, <2 x i32>)
|
|
declare {<3 x i32>, <3 x i1>} @llvm.smul.with.overflow.v3i32(<3 x i32>, <3 x i32>)
|
|
declare {<4 x i32>, <4 x i1>} @llvm.smul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
|
|
declare {<6 x i32>, <6 x i1>} @llvm.smul.with.overflow.v6i32(<6 x i32>, <6 x i32>)
|
|
declare {<8 x i32>, <8 x i1>} @llvm.smul.with.overflow.v8i32(<8 x i32>, <8 x i32>)
|
|
declare {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32>, <16 x i32>)
|
|
|
|
declare {<16 x i8>, <16 x i1>} @llvm.smul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
|
|
declare {<8 x i16>, <8 x i1>} @llvm.smul.with.overflow.v8i16(<8 x i16>, <8 x i16>)
|
|
declare {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64>, <2 x i64>)
|
|
|
|
declare {<4 x i24>, <4 x i1>} @llvm.smul.with.overflow.v4i24(<4 x i24>, <4 x i24>)
|
|
declare {<4 x i1>, <4 x i1>} @llvm.smul.with.overflow.v4i1(<4 x i1>, <4 x i1>)
|
|
declare {<2 x i128>, <2 x i1>} @llvm.smul.with.overflow.v2i128(<2 x i128>, <2 x i128>)
|
|
|
|
define <1 x i32> @smulo_v1i32(<1 x i32> %a0, <1 x i32> %a1, <1 x i32>* %p2) nounwind {
|
|
; SSE-LABEL: smulo_v1i32:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: xorl %eax, %eax
|
|
; SSE-NEXT: imull %esi, %edi
|
|
; SSE-NEXT: seto %al
|
|
; SSE-NEXT: negl %eax
|
|
; SSE-NEXT: movl %edi, (%rdx)
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: smulo_v1i32:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: xorl %eax, %eax
|
|
; AVX-NEXT: imull %esi, %edi
|
|
; AVX-NEXT: seto %al
|
|
; AVX-NEXT: negl %eax
|
|
; AVX-NEXT: movl %edi, (%rdx)
|
|
; AVX-NEXT: retq
|
|
%t = call {<1 x i32>, <1 x i1>} @llvm.smul.with.overflow.v1i32(<1 x i32> %a0, <1 x i32> %a1)
|
|
%val = extractvalue {<1 x i32>, <1 x i1>} %t, 0
|
|
%obit = extractvalue {<1 x i32>, <1 x i1>} %t, 1
|
|
%res = sext <1 x i1> %obit to <1 x i32>
|
|
store <1 x i32> %val, <1 x i32>* %p2
|
|
ret <1 x i32> %res
|
|
}
|
|
|
|
define <2 x i32> @smulo_v2i32(<2 x i32> %a0, <2 x i32> %a1, <2 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v2i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: psllq $32, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[2,3,0,1]
|
|
; SSE2-NEXT: movq %xmm1, %r8
|
|
; SSE2-NEXT: psllq $32, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; SSE2-NEXT: movq %xmm0, %rcx
|
|
; SSE2-NEXT: movq %xmm2, %rdx
|
|
; SSE2-NEXT: movq %xmm1, %rsi
|
|
; SSE2-NEXT: xorl %eax, %eax
|
|
; SSE2-NEXT: imulq %rdx, %rsi
|
|
; SSE2-NEXT: movq $-1, %r9
|
|
; SSE2-NEXT: movl $0, %edx
|
|
; SSE2-NEXT: cmovoq %r9, %rdx
|
|
; SSE2-NEXT: movq %rsi, %xmm1
|
|
; SSE2-NEXT: imulq %r8, %rcx
|
|
; SSE2-NEXT: movq %rcx, %xmm0
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE2-NEXT: psllq $32, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,0,3,2]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; SSE2-NEXT: movq %rdx, %xmm0
|
|
; SSE2-NEXT: cmovoq %r9, %rax
|
|
; SSE2-NEXT: movq %rax, %xmm3
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: movq %xmm1, (%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v2i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: psllq $32, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[2,3,0,1]
|
|
; SSSE3-NEXT: movq %xmm1, %r8
|
|
; SSSE3-NEXT: psllq $32, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
|
; SSSE3-NEXT: movq %xmm0, %rcx
|
|
; SSSE3-NEXT: movq %xmm2, %rdx
|
|
; SSSE3-NEXT: movq %xmm1, %rsi
|
|
; SSSE3-NEXT: xorl %eax, %eax
|
|
; SSSE3-NEXT: imulq %rdx, %rsi
|
|
; SSSE3-NEXT: movq $-1, %r9
|
|
; SSSE3-NEXT: movl $0, %edx
|
|
; SSSE3-NEXT: cmovoq %r9, %rdx
|
|
; SSSE3-NEXT: movq %rsi, %xmm1
|
|
; SSSE3-NEXT: imulq %r8, %rcx
|
|
; SSSE3-NEXT: movq %rcx, %xmm0
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
|
; SSSE3-NEXT: psllq $32, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
|
|
; SSSE3-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,0,3,2]
|
|
; SSSE3-NEXT: pand %xmm2, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm2
|
|
; SSSE3-NEXT: movq %rdx, %xmm0
|
|
; SSSE3-NEXT: cmovoq %r9, %rax
|
|
; SSSE3-NEXT: movq %rax, %xmm3
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
|
; SSSE3-NEXT: por %xmm2, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: movq %xmm1, (%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v2i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE41-NEXT: psllq $32, %xmm2
|
|
; SSE41-NEXT: psrad $31, %xmm2
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
|
|
; SSE41-NEXT: movq %xmm2, %r8
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm1
|
|
; SSE41-NEXT: psllq $32, %xmm1
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
|
|
; SSE41-NEXT: movq %xmm1, %rcx
|
|
; SSE41-NEXT: pextrq $1, %xmm2, %rdx
|
|
; SSE41-NEXT: pextrq $1, %xmm1, %rsi
|
|
; SSE41-NEXT: xorl %eax, %eax
|
|
; SSE41-NEXT: imulq %rdx, %rsi
|
|
; SSE41-NEXT: movq $-1, %r9
|
|
; SSE41-NEXT: movl $0, %edx
|
|
; SSE41-NEXT: cmovoq %r9, %rdx
|
|
; SSE41-NEXT: movq %rsi, %xmm0
|
|
; SSE41-NEXT: imulq %r8, %rcx
|
|
; SSE41-NEXT: movq %rcx, %xmm1
|
|
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE41-NEXT: psllq $32, %xmm0
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
|
|
; SSE41-NEXT: pcmpeqq %xmm1, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSE41-NEXT: pxor %xmm0, %xmm2
|
|
; SSE41-NEXT: movq %rdx, %xmm3
|
|
; SSE41-NEXT: cmovoq %r9, %rax
|
|
; SSE41-NEXT: movq %rax, %xmm0
|
|
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
|
; SSE41-NEXT: por %xmm2, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE41-NEXT: movq %xmm1, (%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v2i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpsllq $32, %xmm1, %xmm2
|
|
; AVX1-NEXT: vpsrad $31, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vmovq %xmm1, %r8
|
|
; AVX1-NEXT: vpsllq $32, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpsrad $31, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vmovq %xmm0, %rcx
|
|
; AVX1-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX1-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX1-NEXT: xorl %eax, %eax
|
|
; AVX1-NEXT: imulq %rdx, %rsi
|
|
; AVX1-NEXT: movq $-1, %r9
|
|
; AVX1-NEXT: movl $0, %edx
|
|
; AVX1-NEXT: cmovoq %r9, %rdx
|
|
; AVX1-NEXT: vmovq %rsi, %xmm0
|
|
; AVX1-NEXT: imulq %r8, %rcx
|
|
; AVX1-NEXT: vmovq %rcx, %xmm1
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
|
; AVX1-NEXT: vpsllq $32, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpsrad $31, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
|
|
; AVX1-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vmovq %rdx, %xmm2
|
|
; AVX1-NEXT: cmovoq %r9, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm3
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm3[0],xmm2[0]
|
|
; AVX1-NEXT: vpor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; AVX1-NEXT: vmovq %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v2i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpsllq $32, %xmm1, %xmm2
|
|
; AVX2-NEXT: vpsrad $31, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3]
|
|
; AVX2-NEXT: vmovq %xmm1, %r8
|
|
; AVX2-NEXT: vpsllq $32, %xmm0, %xmm2
|
|
; AVX2-NEXT: vpsrad $31, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
|
|
; AVX2-NEXT: vmovq %xmm0, %rcx
|
|
; AVX2-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX2-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX2-NEXT: xorl %eax, %eax
|
|
; AVX2-NEXT: imulq %rdx, %rsi
|
|
; AVX2-NEXT: movq $-1, %r9
|
|
; AVX2-NEXT: movl $0, %edx
|
|
; AVX2-NEXT: cmovoq %r9, %rdx
|
|
; AVX2-NEXT: vmovq %rsi, %xmm0
|
|
; AVX2-NEXT: imulq %r8, %rcx
|
|
; AVX2-NEXT: vmovq %rcx, %xmm1
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
|
; AVX2-NEXT: vpsllq $32, %xmm1, %xmm0
|
|
; AVX2-NEXT: vpsrad $31, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3]
|
|
; AVX2-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vmovq %rdx, %xmm2
|
|
; AVX2-NEXT: cmovoq %r9, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm3
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm2 = xmm3[0],xmm2[0]
|
|
; AVX2-NEXT: vpor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; AVX2-NEXT: vmovq %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v2i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpsllq $32, %xmm1, %xmm1
|
|
; AVX512-NEXT: vpsraq $32, %xmm1, %xmm1
|
|
; AVX512-NEXT: vmovq %xmm1, %rax
|
|
; AVX512-NEXT: vpsllq $32, %xmm0, %xmm0
|
|
; AVX512-NEXT: vpsraq $32, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovq %xmm0, %rcx
|
|
; AVX512-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX512-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX512-NEXT: imulq %rdx, %rsi
|
|
; AVX512-NEXT: seto %dl
|
|
; AVX512-NEXT: vmovq %rsi, %xmm0
|
|
; AVX512-NEXT: imulq %rax, %rcx
|
|
; AVX512-NEXT: vmovq %rcx, %xmm1
|
|
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
|
; AVX512-NEXT: vpsllq $32, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpsraq $32, %xmm1, %xmm1
|
|
; AVX512-NEXT: vpcmpneqq %xmm0, %xmm1, %k0
|
|
; AVX512-NEXT: kmovd %edx, %k1
|
|
; AVX512-NEXT: kshiftlw $1, %k1, %k1
|
|
; AVX512-NEXT: seto %al
|
|
; AVX512-NEXT: andl $1, %eax
|
|
; AVX512-NEXT: kmovw %eax, %k2
|
|
; AVX512-NEXT: korw %k1, %k2, %k1
|
|
; AVX512-NEXT: korw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpmovqd %xmm0, (%rdi)
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa64 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: retq
|
|
%t = call {<2 x i32>, <2 x i1>} @llvm.smul.with.overflow.v2i32(<2 x i32> %a0, <2 x i32> %a1)
|
|
%val = extractvalue {<2 x i32>, <2 x i1>} %t, 0
|
|
%obit = extractvalue {<2 x i32>, <2 x i1>} %t, 1
|
|
%res = sext <2 x i1> %obit to <2 x i32>
|
|
store <2 x i32> %val, <2 x i32>* %p2
|
|
ret <2 x i32> %res
|
|
}
|
|
|
|
define <3 x i32> @smulo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v3i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSE2-NEXT: pand %xmm0, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSE2-NEXT: pand %xmm1, %xmm2
|
|
; SSE2-NEXT: paddd %xmm3, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSE2-NEXT: psubd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSE2-NEXT: movq %xmm0, (%rdi)
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: psrad $31, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE2-NEXT: pxor %xmm2, %xmm0
|
|
; SSE2-NEXT: movd %xmm1, 8(%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v3i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSSE3-NEXT: pand %xmm0, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSSE3-NEXT: pand %xmm1, %xmm2
|
|
; SSSE3-NEXT: paddd %xmm3, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSSE3-NEXT: psubd %xmm2, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSSE3-NEXT: movq %xmm0, (%rdi)
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm2
|
|
; SSSE3-NEXT: psrad $31, %xmm2
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSSE3-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm0
|
|
; SSSE3-NEXT: movd %xmm1, 8(%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v3i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pmuldq %xmm1, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5],xmm3[6,7]
|
|
; SSE41-NEXT: pmulld %xmm1, %xmm0
|
|
; SSE41-NEXT: pextrd $2, %xmm0, 8(%rdi)
|
|
; SSE41-NEXT: movq %xmm0, (%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE41-NEXT: pxor %xmm1, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v3i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3],xmm3[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpextrd $2, %xmm1, 8(%rdi)
|
|
; AVX1-NEXT: vmovq %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v3i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX2-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3]
|
|
; AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpextrd $2, %xmm1, 8(%rdi)
|
|
; AVX2-NEXT: vmovq %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v3i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmuldq %xmm1, %xmm0, %xmm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
|
; AVX512-NEXT: vpmuldq %xmm3, %xmm4, %xmm3
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} xmm4 = [1,5,3,7]
|
|
; AVX512-NEXT: vpermi2d %xmm3, %xmm2, %xmm4
|
|
; AVX512-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpcmpneqd %xmm0, %xmm4, %k1
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: vpextrd $2, %xmm1, 8(%rdi)
|
|
; AVX512-NEXT: vmovq %xmm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<3 x i32>, <3 x i1>} @llvm.smul.with.overflow.v3i32(<3 x i32> %a0, <3 x i32> %a1)
|
|
%val = extractvalue {<3 x i32>, <3 x i1>} %t, 0
|
|
%obit = extractvalue {<3 x i32>, <3 x i1>} %t, 1
|
|
%res = sext <3 x i1> %obit to <3 x i32>
|
|
store <3 x i32> %val, <3 x i32>* %p2
|
|
ret <3 x i32> %res
|
|
}
|
|
|
|
define <4 x i32> @smulo_v4i32(<4 x i32> %a0, <4 x i32> %a1, <4 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v4i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSE2-NEXT: pand %xmm0, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSE2-NEXT: pand %xmm1, %xmm2
|
|
; SSE2-NEXT: paddd %xmm3, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSE2-NEXT: psubd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSE2-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v4i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSSE3-NEXT: pand %xmm0, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSSE3-NEXT: pand %xmm1, %xmm2
|
|
; SSSE3-NEXT: paddd %xmm3, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSSE3-NEXT: psubd %xmm2, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSSE3-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm1
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm1, %xmm0
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v4i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pmuldq %xmm1, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5],xmm3[6,7]
|
|
; SSE41-NEXT: pmulld %xmm1, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE41-NEXT: pxor %xmm1, %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v4i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3],xmm3[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v4i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX2-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3]
|
|
; AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v4i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmuldq %xmm1, %xmm0, %xmm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
|
; AVX512-NEXT: vpmuldq %xmm3, %xmm4, %xmm3
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} xmm4 = [1,5,3,7]
|
|
; AVX512-NEXT: vpermi2d %xmm3, %xmm2, %xmm4
|
|
; AVX512-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpcmpneqd %xmm0, %xmm4, %k1
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<4 x i32>, <4 x i1>} @llvm.smul.with.overflow.v4i32(<4 x i32> %a0, <4 x i32> %a1)
|
|
%val = extractvalue {<4 x i32>, <4 x i1>} %t, 0
|
|
%obit = extractvalue {<4 x i32>, <4 x i1>} %t, 1
|
|
%res = sext <4 x i1> %obit to <4 x i32>
|
|
store <4 x i32> %val, <4 x i32>* %p2
|
|
ret <4 x i32> %res
|
|
}
|
|
|
|
define <6 x i32> @smulo_v6i32(<6 x i32> %a0, <6 x i32> %a1, <6 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v6i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movq %rdi, %rax
|
|
; SSE2-NEXT: movd %r8d, %xmm9
|
|
; SSE2-NEXT: movd %ecx, %xmm0
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm9[0],xmm0[1],xmm9[1]
|
|
; SSE2-NEXT: movd %edx, %xmm6
|
|
; SSE2-NEXT: movd %esi, %xmm5
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm0[0]
|
|
; SSE2-NEXT: movd {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1]
|
|
; SSE2-NEXT: movd {{.*#+}} xmm7 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm7[0],xmm3[1],xmm7[1]
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
|
; SSE2-NEXT: movd %r9d, %xmm12
|
|
; SSE2-NEXT: movd {{.*#+}} xmm11 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm12 = xmm12[0],xmm11[0],xmm12[1],xmm11[1]
|
|
; SSE2-NEXT: movd {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm8[0],xmm2[1],xmm8[1]
|
|
; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rcx
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pxor %xmm0, %xmm0
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSE2-NEXT: pand %xmm5, %xmm0
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm1
|
|
; SSE2-NEXT: pand %xmm3, %xmm1
|
|
; SSE2-NEXT: paddd %xmm0, %xmm1
|
|
; SSE2-NEXT: pmuludq %xmm5, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm10[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm9[0,0]
|
|
; SSE2-NEXT: pmuludq %xmm7, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1]
|
|
; SSE2-NEXT: psubd %xmm1, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm3[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm0[0],xmm7[1],xmm0[1]
|
|
; SSE2-NEXT: movdqa %xmm7, (%rcx)
|
|
; SSE2-NEXT: psrad $31, %xmm7
|
|
; SSE2-NEXT: pcmpeqd %xmm5, %xmm7
|
|
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE2-NEXT: pxor %xmm0, %xmm7
|
|
; SSE2-NEXT: pxor %xmm1, %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSE2-NEXT: pand %xmm12, %xmm1
|
|
; SSE2-NEXT: pcmpgtd %xmm12, %xmm4
|
|
; SSE2-NEXT: pand %xmm2, %xmm4
|
|
; SSE2-NEXT: paddd %xmm1, %xmm4
|
|
; SSE2-NEXT: pmuludq %xmm12, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
|
|
; SSE2-NEXT: pmuludq %xmm8, %xmm11
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm11[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
|
; SSE2-NEXT: psubd %xmm4, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm11[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
|
; SSE2-NEXT: movq %xmm2, 16(%rcx)
|
|
; SSE2-NEXT: psrad $31, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE2-NEXT: pxor %xmm0, %xmm2
|
|
; SSE2-NEXT: movq %xmm2, 16(%rdi)
|
|
; SSE2-NEXT: movdqa %xmm7, (%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v6i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movq %rdi, %rax
|
|
; SSSE3-NEXT: movd %r8d, %xmm9
|
|
; SSSE3-NEXT: movd %ecx, %xmm0
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm9[0],xmm0[1],xmm9[1]
|
|
; SSSE3-NEXT: movd %edx, %xmm6
|
|
; SSSE3-NEXT: movd %esi, %xmm5
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm0[0]
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1]
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm7 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm7[0],xmm3[1],xmm7[1]
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
|
; SSSE3-NEXT: movd %r9d, %xmm12
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm11 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm12 = xmm12[0],xmm11[0],xmm12[1],xmm11[1]
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm8[0],xmm2[1],xmm8[1]
|
|
; SSSE3-NEXT: movq {{[0-9]+}}(%rsp), %rcx
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm0
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm0
|
|
; SSSE3-NEXT: pand %xmm5, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm1, %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm1
|
|
; SSSE3-NEXT: pand %xmm3, %xmm1
|
|
; SSSE3-NEXT: paddd %xmm0, %xmm1
|
|
; SSSE3-NEXT: pmuludq %xmm5, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSSE3-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm10[0,0]
|
|
; SSSE3-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm9[0,0]
|
|
; SSSE3-NEXT: pmuludq %xmm7, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm6[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1]
|
|
; SSSE3-NEXT: psubd %xmm1, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm3[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm0[0],xmm7[1],xmm0[1]
|
|
; SSSE3-NEXT: movdqa %xmm7, (%rcx)
|
|
; SSSE3-NEXT: psrad $31, %xmm7
|
|
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm7
|
|
; SSSE3-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm7
|
|
; SSSE3-NEXT: pxor %xmm1, %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm1
|
|
; SSSE3-NEXT: pand %xmm12, %xmm1
|
|
; SSSE3-NEXT: pcmpgtd %xmm12, %xmm4
|
|
; SSSE3-NEXT: pand %xmm2, %xmm4
|
|
; SSSE3-NEXT: paddd %xmm1, %xmm4
|
|
; SSSE3-NEXT: pmuludq %xmm12, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
|
|
; SSSE3-NEXT: pmuludq %xmm8, %xmm11
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm11[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
|
; SSSE3-NEXT: psubd %xmm4, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm11[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
|
|
; SSSE3-NEXT: movq %xmm2, 16(%rcx)
|
|
; SSSE3-NEXT: psrad $31, %xmm2
|
|
; SSSE3-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm2
|
|
; SSSE3-NEXT: movq %xmm2, 16(%rdi)
|
|
; SSSE3-NEXT: movdqa %xmm7, (%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v6i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movq %rdi, %rax
|
|
; SSE41-NEXT: movd %esi, %xmm3
|
|
; SSE41-NEXT: pinsrd $1, %edx, %xmm3
|
|
; SSE41-NEXT: pinsrd $2, %ecx, %xmm3
|
|
; SSE41-NEXT: pinsrd $3, %r8d, %xmm3
|
|
; SSE41-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrd $1, {{[0-9]+}}(%rsp), %xmm0
|
|
; SSE41-NEXT: movd %r9d, %xmm1
|
|
; SSE41-NEXT: pinsrd $1, {{[0-9]+}}(%rsp), %xmm1
|
|
; SSE41-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrd $1, {{[0-9]+}}(%rsp), %xmm2
|
|
; SSE41-NEXT: pinsrd $2, {{[0-9]+}}(%rsp), %xmm2
|
|
; SSE41-NEXT: pinsrd $3, {{[0-9]+}}(%rsp), %xmm2
|
|
; SSE41-NEXT: movq {{[0-9]+}}(%rsp), %rcx
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm3, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm2, (%rcx)
|
|
; SSE41-NEXT: psrad $31, %xmm2
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSE41-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSE41-NEXT: pxor %xmm3, %xmm2
|
|
; SSE41-NEXT: movd {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: movd {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm0, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm0, %xmm1
|
|
; SSE41-NEXT: movq %xmm1, 16(%rcx)
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE41-NEXT: pxor %xmm3, %xmm1
|
|
; SSE41-NEXT: movq %xmm1, 16(%rdi)
|
|
; SSE41-NEXT: movdqa %xmm2, (%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v6i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm2[1,1,3,3]
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm4[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm3, %xmm5, %xmm3
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm4, %xmm5
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm5[0,1],xmm3[2,3],xmm5[4,5],xmm3[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsrad $31, %xmm2, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm5, %xmm6, %xmm5
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm5 = xmm6[0,1],xmm5[2,3],xmm6[4,5],xmm5[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm5, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
|
; AVX1-NEXT: vmovq %xmm2, 16(%rdi)
|
|
; AVX1-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v6i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm1[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpmuldq %ymm2, %ymm3, %ymm2
|
|
; AVX2-NEXT: vpmuldq %ymm1, %ymm0, %ymm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3],ymm3[4],ymm2[5],ymm3[6],ymm2[7]
|
|
; AVX2-NEXT: vpmulld %ymm1, %ymm0, %ymm1
|
|
; AVX2-NEXT: vpsrad $31, %ymm1, %ymm0
|
|
; AVX2-NEXT: vpcmpeqd %ymm0, %ymm2, %ymm0
|
|
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm2, %ymm2
|
|
; AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
|
|
; AVX2-NEXT: vmovq %xmm2, 16(%rdi)
|
|
; AVX2-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v6i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmuldq %ymm1, %ymm0, %ymm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} ymm3 = ymm1[1,1,3,3,5,5,7,7]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} ymm4 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX512-NEXT: vpmuldq %ymm3, %ymm4, %ymm3
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} ymm4 = [1,9,3,11,5,13,7,15]
|
|
; AVX512-NEXT: vpermi2d %ymm3, %ymm2, %ymm4
|
|
; AVX512-NEXT: vpmulld %ymm1, %ymm0, %ymm1
|
|
; AVX512-NEXT: vpsrad $31, %ymm1, %ymm0
|
|
; AVX512-NEXT: vpcmpneqd %ymm0, %ymm4, %k1
|
|
; AVX512-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
|
|
; AVX512-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
|
|
; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2
|
|
; AVX512-NEXT: vmovq %xmm2, 16(%rdi)
|
|
; AVX512-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<6 x i32>, <6 x i1>} @llvm.smul.with.overflow.v6i32(<6 x i32> %a0, <6 x i32> %a1)
|
|
%val = extractvalue {<6 x i32>, <6 x i1>} %t, 0
|
|
%obit = extractvalue {<6 x i32>, <6 x i1>} %t, 1
|
|
%res = sext <6 x i1> %obit to <6 x i32>
|
|
store <6 x i32> %val, <6 x i32>* %p2
|
|
ret <6 x i32> %res
|
|
}
|
|
|
|
define <8 x i32> @smulo_v8i32(<8 x i32> %a0, <8 x i32> %a1, <8 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v8i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pxor %xmm5, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
|
|
; SSE2-NEXT: pand %xmm0, %xmm5
|
|
; SSE2-NEXT: pxor %xmm6, %xmm6
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm6
|
|
; SSE2-NEXT: pand %xmm2, %xmm6
|
|
; SSE2-NEXT: paddd %xmm5, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm2, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm7, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm7 = xmm2[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
|
|
; SSE2-NEXT: psubd %xmm6, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm5, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm2, %xmm0
|
|
; SSE2-NEXT: pxor %xmm5, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm5
|
|
; SSE2-NEXT: pand %xmm1, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; SSE2-NEXT: pand %xmm3, %xmm4
|
|
; SSE2-NEXT: paddd %xmm5, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm5, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm5[0],xmm6[1],xmm5[1]
|
|
; SSE2-NEXT: psubd %xmm4, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
|
; SSE2-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm6, %xmm1
|
|
; SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v8i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
|
|
; SSSE3-NEXT: pand %xmm0, %xmm5
|
|
; SSSE3-NEXT: pxor %xmm6, %xmm6
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm6
|
|
; SSSE3-NEXT: pand %xmm2, %xmm6
|
|
; SSSE3-NEXT: paddd %xmm5, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm2, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm7, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm7 = xmm2[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
|
|
; SSSE3-NEXT: psubd %xmm6, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSSE3-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm5
|
|
; SSSE3-NEXT: pand %xmm1, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; SSSE3-NEXT: pand %xmm3, %xmm4
|
|
; SSSE3-NEXT: paddd %xmm5, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm5, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm5[0],xmm6[1],xmm5[1]
|
|
; SSSE3-NEXT: psubd %xmm4, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
|
; SSSE3-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm6, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm1
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v8i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm2, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSE41-NEXT: pxor %xmm2, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm3, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm3, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE41-NEXT: pxor %xmm2, %xmm1
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v8i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm2[1,1,3,3]
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm4[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm3, %xmm5, %xmm3
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm4, %xmm5
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm5[0,1],xmm3[2,3],xmm5[4,5],xmm3[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm2, %xmm4, %xmm2
|
|
; AVX1-NEXT: vpsrad $31, %xmm2, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm5, %xmm6, %xmm5
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm5 = xmm6[0,1],xmm5[2,3],xmm6[4,5],xmm5[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm5, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
|
; AVX1-NEXT: vmovdqa %xmm2, 16(%rdi)
|
|
; AVX1-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v8i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm2 = ymm1[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpmuldq %ymm2, %ymm3, %ymm2
|
|
; AVX2-NEXT: vpmuldq %ymm1, %ymm0, %ymm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3],ymm3[4],ymm2[5],ymm3[6],ymm2[7]
|
|
; AVX2-NEXT: vpmulld %ymm1, %ymm0, %ymm1
|
|
; AVX2-NEXT: vpsrad $31, %ymm1, %ymm0
|
|
; AVX2-NEXT: vpcmpeqd %ymm0, %ymm2, %ymm0
|
|
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm2, %ymm2
|
|
; AVX2-NEXT: vpxor %ymm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: vmovdqa %ymm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v8i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmuldq %ymm1, %ymm0, %ymm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} ymm3 = ymm1[1,1,3,3,5,5,7,7]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} ymm4 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX512-NEXT: vpmuldq %ymm3, %ymm4, %ymm3
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} ymm4 = [1,9,3,11,5,13,7,15]
|
|
; AVX512-NEXT: vpermi2d %ymm3, %ymm2, %ymm4
|
|
; AVX512-NEXT: vpmulld %ymm1, %ymm0, %ymm1
|
|
; AVX512-NEXT: vpsrad $31, %ymm1, %ymm0
|
|
; AVX512-NEXT: vpcmpneqd %ymm0, %ymm4, %k1
|
|
; AVX512-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
|
|
; AVX512-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
|
|
; AVX512-NEXT: vmovdqa %ymm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<8 x i32>, <8 x i1>} @llvm.smul.with.overflow.v8i32(<8 x i32> %a0, <8 x i32> %a1)
|
|
%val = extractvalue {<8 x i32>, <8 x i1>} %t, 0
|
|
%obit = extractvalue {<8 x i32>, <8 x i1>} %t, 1
|
|
%res = sext <8 x i1> %obit to <8 x i32>
|
|
store <8 x i32> %val, <8 x i32>* %p2
|
|
ret <8 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @smulo_v16i32(<16 x i32> %a0, <16 x i32> %a1, <16 x i32>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v16i32:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pxor %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpgtd %xmm4, %xmm9
|
|
; SSE2-NEXT: pand %xmm0, %xmm9
|
|
; SSE2-NEXT: pxor %xmm10, %xmm10
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm10
|
|
; SSE2-NEXT: pand %xmm4, %xmm10
|
|
; SSE2-NEXT: paddd %xmm9, %xmm10
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm9 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm4[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm11, %xmm12
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm12[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm4[0],xmm9[1],xmm4[1]
|
|
; SSE2-NEXT: psubd %xmm10, %xmm9
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm12[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
|
|
; SSE2-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm9
|
|
; SSE2-NEXT: pxor %xmm9, %xmm0
|
|
; SSE2-NEXT: pxor %xmm10, %xmm10
|
|
; SSE2-NEXT: pcmpgtd %xmm5, %xmm10
|
|
; SSE2-NEXT: pand %xmm1, %xmm10
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; SSE2-NEXT: pand %xmm5, %xmm4
|
|
; SSE2-NEXT: paddd %xmm10, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm5, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm12 = xmm5[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm10, %xmm12
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm12[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm11 = xmm11[0],xmm5[0],xmm11[1],xmm5[1]
|
|
; SSE2-NEXT: psubd %xmm4, %xmm11
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm12[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
|
|
; SSE2-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm11, %xmm1
|
|
; SSE2-NEXT: pxor %xmm9, %xmm1
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm6, %xmm4
|
|
; SSE2-NEXT: pand %xmm2, %xmm4
|
|
; SSE2-NEXT: pxor %xmm5, %xmm5
|
|
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
|
|
; SSE2-NEXT: pand %xmm6, %xmm5
|
|
; SSE2-NEXT: paddd %xmm4, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm10 = xmm2[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm6, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm2[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm11 = xmm6[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm10, %xmm11
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm11[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
|
|
; SSE2-NEXT: psubd %xmm5, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm11[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
|
|
; SSE2-NEXT: movdqa %xmm2, 32(%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSE2-NEXT: pxor %xmm9, %xmm2
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm7, %xmm4
|
|
; SSE2-NEXT: pand %xmm3, %xmm4
|
|
; SSE2-NEXT: pcmpgtd %xmm3, %xmm8
|
|
; SSE2-NEXT: pand %xmm7, %xmm8
|
|
; SSE2-NEXT: paddd %xmm4, %xmm8
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm7, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm7[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm4, %xmm6
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm6[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1]
|
|
; SSE2-NEXT: psubd %xmm8, %xmm5
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm6[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
|
; SSE2-NEXT: movdqa %xmm3, 48(%rdi)
|
|
; SSE2-NEXT: psrad $31, %xmm3
|
|
; SSE2-NEXT: pcmpeqd %xmm5, %xmm3
|
|
; SSE2-NEXT: pxor %xmm9, %xmm3
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v16i32:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pxor %xmm8, %xmm8
|
|
; SSSE3-NEXT: pxor %xmm9, %xmm9
|
|
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm9
|
|
; SSSE3-NEXT: pand %xmm0, %xmm9
|
|
; SSSE3-NEXT: pxor %xmm10, %xmm10
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm10
|
|
; SSSE3-NEXT: pand %xmm4, %xmm10
|
|
; SSSE3-NEXT: paddd %xmm9, %xmm10
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm11 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm4, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm9 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm4[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm11, %xmm12
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm12[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm9 = xmm9[0],xmm4[0],xmm9[1],xmm4[1]
|
|
; SSSE3-NEXT: psubd %xmm10, %xmm9
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm12[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
|
|
; SSSE3-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm9, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm9, %xmm9
|
|
; SSSE3-NEXT: pxor %xmm9, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm10, %xmm10
|
|
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm10
|
|
; SSSE3-NEXT: pand %xmm1, %xmm10
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm4
|
|
; SSSE3-NEXT: pand %xmm5, %xmm4
|
|
; SSSE3-NEXT: paddd %xmm10, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm10 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm5, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm11 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm12 = xmm5[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm10, %xmm12
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm12[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm11 = xmm11[0],xmm5[0],xmm11[1],xmm5[1]
|
|
; SSSE3-NEXT: psubd %xmm4, %xmm11
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm12[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
|
|
; SSSE3-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm11, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm9, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm4
|
|
; SSSE3-NEXT: pand %xmm2, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm5, %xmm5
|
|
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
|
|
; SSSE3-NEXT: pand %xmm6, %xmm5
|
|
; SSSE3-NEXT: paddd %xmm4, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm10 = xmm2[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm6, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm2[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm11 = xmm6[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm10, %xmm11
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm11[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
|
|
; SSSE3-NEXT: psubd %xmm5, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm11[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
|
|
; SSSE3-NEXT: movdqa %xmm2, 32(%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm2
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm9, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm4
|
|
; SSSE3-NEXT: pand %xmm3, %xmm4
|
|
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm8
|
|
; SSSE3-NEXT: pand %xmm7, %xmm8
|
|
; SSSE3-NEXT: paddd %xmm4, %xmm8
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm7, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm7[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm4, %xmm6
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm6[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1]
|
|
; SSSE3-NEXT: psubd %xmm8, %xmm5
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm6[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
|
; SSSE3-NEXT: movdqa %xmm3, 48(%rdi)
|
|
; SSSE3-NEXT: psrad $31, %xmm3
|
|
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm3
|
|
; SSSE3-NEXT: pxor %xmm9, %xmm3
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v16i32:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm8 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm9 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm8, %xmm9
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm8
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm8
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm8 = xmm8[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm8 = xmm8[0,1],xmm9[2,3],xmm8[4,5],xmm9[6,7]
|
|
; SSE41-NEXT: pmulld %xmm4, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm8, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm8, %xmm8
|
|
; SSE41-NEXT: pxor %xmm8, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm9 = xmm5[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm10 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm9, %xmm10
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm5, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm10[2,3],xmm4[4,5],xmm10[6,7]
|
|
; SSE41-NEXT: pmulld %xmm5, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, 16(%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE41-NEXT: pxor %xmm8, %xmm1
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm6[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm2, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm6, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm6, %xmm2
|
|
; SSE41-NEXT: movdqa %xmm2, 32(%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm2
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm2
|
|
; SSE41-NEXT: pxor %xmm8, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm7[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm4, %xmm5
|
|
; SSE41-NEXT: movdqa %xmm3, %xmm4
|
|
; SSE41-NEXT: pmuldq %xmm7, %xmm4
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3],xmm4[4,5],xmm5[6,7]
|
|
; SSE41-NEXT: pmulld %xmm7, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm3, 48(%rdi)
|
|
; SSE41-NEXT: psrad $31, %xmm3
|
|
; SSE41-NEXT: pcmpeqd %xmm4, %xmm3
|
|
; SSE41-NEXT: pxor %xmm8, %xmm3
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v16i32:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm4[1,1,3,3]
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm6
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm6[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm5, %xmm7, %xmm5
|
|
; AVX1-NEXT: vpmuldq %xmm4, %xmm6, %xmm7
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm5 = xmm7[0,1],xmm5[2,3],xmm7[4,5],xmm5[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm4, %xmm6, %xmm8
|
|
; AVX1-NEXT: vpsrad $31, %xmm8, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm5, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm7, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpmuldq %xmm3, %xmm1, %xmm7
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm4 = xmm7[0,1],xmm4[2,3],xmm7[4,5],xmm4[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm3, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpsrad $31, %xmm3, %xmm1
|
|
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm4, %xmm1
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpackssdw %xmm6, %xmm1, %xmm9
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm4[1,1,3,3]
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm7
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm7[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm6, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpmuldq %xmm4, %xmm7, %xmm6
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm6[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm6[0,1],xmm1[2,3],xmm6[4,5],xmm1[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm4, %xmm7, %xmm4
|
|
; AVX1-NEXT: vpsrad $31, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm6 = xmm2[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm6, %xmm7, %xmm6
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm0, %xmm7
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm7 = xmm7[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm6 = xmm7[0,1],xmm6[2,3],xmm7[4,5],xmm6[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm2, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpsrad $31, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm6, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpacksswb %xmm9, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpmovsxbd %xmm1, %xmm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[1,1,2,3]
|
|
; AVX1-NEXT: vpmovsxbd %xmm5, %xmm5
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[2,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbd %xmm5, %xmm5
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbd %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm5, %ymm1
|
|
; AVX1-NEXT: vmovdqa %xmm8, 48(%rdi)
|
|
; AVX1-NEXT: vmovdqa %xmm3, 32(%rdi)
|
|
; AVX1-NEXT: vmovdqa %xmm4, 16(%rdi)
|
|
; AVX1-NEXT: vmovdqa %xmm2, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v16i32:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm4 = ymm3[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm5 = ymm1[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpmuldq %ymm4, %ymm5, %ymm4
|
|
; AVX2-NEXT: vpmuldq %ymm3, %ymm1, %ymm5
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm5 = ymm5[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm4 = ymm5[0],ymm4[1],ymm5[2],ymm4[3],ymm5[4],ymm4[5],ymm5[6],ymm4[7]
|
|
; AVX2-NEXT: vpmulld %ymm3, %ymm1, %ymm3
|
|
; AVX2-NEXT: vpsrad $31, %ymm3, %ymm1
|
|
; AVX2-NEXT: vpcmpeqd %ymm1, %ymm4, %ymm1
|
|
; AVX2-NEXT: vpcmpeqd %ymm4, %ymm4, %ymm4
|
|
; AVX2-NEXT: vpxor %ymm4, %ymm1, %ymm1
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm5 = ymm2[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm6 = ymm0[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpmuldq %ymm5, %ymm6, %ymm5
|
|
; AVX2-NEXT: vpmuldq %ymm2, %ymm0, %ymm6
|
|
; AVX2-NEXT: vpshufd {{.*#+}} ymm6 = ymm6[1,1,3,3,5,5,7,7]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm5 = ymm6[0],ymm5[1],ymm6[2],ymm5[3],ymm6[4],ymm5[5],ymm6[6],ymm5[7]
|
|
; AVX2-NEXT: vpmulld %ymm2, %ymm0, %ymm2
|
|
; AVX2-NEXT: vpsrad $31, %ymm2, %ymm0
|
|
; AVX2-NEXT: vpcmpeqd %ymm0, %ymm5, %ymm0
|
|
; AVX2-NEXT: vpxor %ymm4, %ymm0, %ymm0
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpmovsxbd %xmm1, %ymm0
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
; AVX2-NEXT: vpmovsxbd %xmm1, %ymm1
|
|
; AVX2-NEXT: vmovdqa %ymm3, 32(%rdi)
|
|
; AVX2-NEXT: vmovdqa %ymm2, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v16i32:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmuldq %zmm1, %zmm0, %zmm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} zmm3 = zmm1[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} zmm4 = zmm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
|
|
; AVX512-NEXT: vpmuldq %zmm3, %zmm4, %zmm3
|
|
; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm4 = [1,17,3,19,5,21,7,23,9,25,11,27,13,29,15,31]
|
|
; AVX512-NEXT: vpermi2d %zmm3, %zmm2, %zmm4
|
|
; AVX512-NEXT: vpmulld %zmm1, %zmm0, %zmm1
|
|
; AVX512-NEXT: vpsrad $31, %zmm1, %zmm0
|
|
; AVX512-NEXT: vpcmpneqd %zmm0, %zmm4, %k1
|
|
; AVX512-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
|
|
; AVX512-NEXT: vmovdqa64 %zmm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32> %a0, <16 x i32> %a1)
|
|
%val = extractvalue {<16 x i32>, <16 x i1>} %t, 0
|
|
%obit = extractvalue {<16 x i32>, <16 x i1>} %t, 1
|
|
%res = sext <16 x i1> %obit to <16 x i32>
|
|
store <16 x i32> %val, <16 x i32>* %p2
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @smulo_v16i8(<16 x i8> %a0, <16 x i8> %a1, <16 x i8>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v16i8:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1],xmm5[2],xmm1[2],xmm5[3],xmm1[3],xmm5[4],xmm1[4],xmm5[5],xmm1[5],xmm5[6],xmm1[6],xmm5[7],xmm1[7]
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm4
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8],xmm0[8],xmm6[9],xmm0[9],xmm6[10],xmm0[10],xmm6[11],xmm0[11],xmm6[12],xmm0[12],xmm6[13],xmm0[13],xmm6[14],xmm0[14],xmm6[15],xmm0[15]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm0[0],xmm7[1],xmm0[1],xmm7[2],xmm0[2],xmm7[3],xmm0[3],xmm7[4],xmm0[4],xmm7[5],xmm0[5],xmm7[6],xmm0[6],xmm7[7],xmm0[7]
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
; SSE2-NEXT: pmullw %xmm1, %xmm0
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
|
|
; SSE2-NEXT: pmullw %xmm2, %xmm4
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm1, %xmm0
|
|
; SSE2-NEXT: pand %xmm1, %xmm4
|
|
; SSE2-NEXT: packuswb %xmm0, %xmm4
|
|
; SSE2-NEXT: pxor %xmm0, %xmm0
|
|
; SSE2-NEXT: pcmpgtb %xmm4, %xmm0
|
|
; SSE2-NEXT: psraw $8, %xmm3
|
|
; SSE2-NEXT: psraw $8, %xmm6
|
|
; SSE2-NEXT: pmullw %xmm3, %xmm6
|
|
; SSE2-NEXT: psrlw $8, %xmm6
|
|
; SSE2-NEXT: psraw $8, %xmm5
|
|
; SSE2-NEXT: psraw $8, %xmm7
|
|
; SSE2-NEXT: pmullw %xmm5, %xmm7
|
|
; SSE2-NEXT: psrlw $8, %xmm7
|
|
; SSE2-NEXT: packuswb %xmm6, %xmm7
|
|
; SSE2-NEXT: pcmpeqb %xmm0, %xmm7
|
|
; SSE2-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSE2-NEXT: pxor %xmm7, %xmm3
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm1
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
|
; SSE2-NEXT: pslld $31, %xmm0
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSE2-NEXT: pslld $31, %xmm1
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm0[8],xmm3[9],xmm0[9],xmm3[10],xmm0[10],xmm3[11],xmm0[11],xmm3[12],xmm0[12],xmm3[13],xmm0[13],xmm3[14],xmm0[14],xmm3[15],xmm0[15]
|
|
; SSE2-NEXT: movdqa %xmm3, %xmm2
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
|
|
; SSE2-NEXT: pslld $31, %xmm2
|
|
; SSE2-NEXT: psrad $31, %xmm2
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
|
|
; SSE2-NEXT: pslld $31, %xmm3
|
|
; SSE2-NEXT: psrad $31, %xmm3
|
|
; SSE2-NEXT: movdqa %xmm4, (%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v16i8:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm2
|
|
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1],xmm5[2],xmm1[2],xmm5[3],xmm1[3],xmm5[4],xmm1[4],xmm5[5],xmm1[5],xmm5[6],xmm1[6],xmm5[7],xmm1[7]
|
|
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm4
|
|
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm6 = xmm6[8],xmm0[8],xmm6[9],xmm0[9],xmm6[10],xmm0[10],xmm6[11],xmm0[11],xmm6[12],xmm0[12],xmm6[13],xmm0[13],xmm6[14],xmm0[14],xmm6[15],xmm0[15]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm0[0],xmm7[1],xmm0[1],xmm7[2],xmm0[2],xmm7[3],xmm0[3],xmm7[4],xmm0[4],xmm7[5],xmm0[5],xmm7[6],xmm0[6],xmm7[7],xmm0[7]
|
|
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
; SSSE3-NEXT: pmullw %xmm1, %xmm0
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3],xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
|
|
; SSSE3-NEXT: pmullw %xmm2, %xmm4
|
|
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
|
|
; SSSE3-NEXT: pand %xmm1, %xmm0
|
|
; SSSE3-NEXT: pand %xmm1, %xmm4
|
|
; SSSE3-NEXT: packuswb %xmm0, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm0
|
|
; SSSE3-NEXT: pcmpgtb %xmm4, %xmm0
|
|
; SSSE3-NEXT: psraw $8, %xmm3
|
|
; SSSE3-NEXT: psraw $8, %xmm6
|
|
; SSSE3-NEXT: pmullw %xmm3, %xmm6
|
|
; SSSE3-NEXT: psrlw $8, %xmm6
|
|
; SSSE3-NEXT: psraw $8, %xmm5
|
|
; SSSE3-NEXT: psraw $8, %xmm7
|
|
; SSSE3-NEXT: pmullw %xmm5, %xmm7
|
|
; SSSE3-NEXT: psrlw $8, %xmm7
|
|
; SSSE3-NEXT: packuswb %xmm6, %xmm7
|
|
; SSSE3-NEXT: pcmpeqb %xmm0, %xmm7
|
|
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSSE3-NEXT: pxor %xmm7, %xmm3
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm1
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
|
; SSSE3-NEXT: pslld $31, %xmm0
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSSE3-NEXT: pslld $31, %xmm1
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm0[8],xmm3[9],xmm0[9],xmm3[10],xmm0[10],xmm3[11],xmm0[11],xmm3[12],xmm0[12],xmm3[13],xmm0[13],xmm3[14],xmm0[14],xmm3[15],xmm0[15]
|
|
; SSSE3-NEXT: movdqa %xmm3, %xmm2
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
|
|
; SSSE3-NEXT: pslld $31, %xmm2
|
|
; SSSE3-NEXT: psrad $31, %xmm2
|
|
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
|
|
; SSSE3-NEXT: pslld $31, %xmm3
|
|
; SSSE3-NEXT: psrad $31, %xmm3
|
|
; SSSE3-NEXT: movdqa %xmm4, (%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v16i8:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
|
; SSE41-NEXT: pmovsxbw %xmm1, %xmm3
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm5 = xmm1[2,3,0,1]
|
|
; SSE41-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
|
|
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm4 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; SSE41-NEXT: pmovsxbw %xmm0, %xmm6
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm7 = xmm0[2,3,0,1]
|
|
; SSE41-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
; SSE41-NEXT: pmullw %xmm1, %xmm0
|
|
; SSE41-NEXT: pmullw %xmm2, %xmm4
|
|
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
|
|
; SSE41-NEXT: pand %xmm1, %xmm0
|
|
; SSE41-NEXT: pand %xmm1, %xmm4
|
|
; SSE41-NEXT: packuswb %xmm0, %xmm4
|
|
; SSE41-NEXT: pxor %xmm0, %xmm0
|
|
; SSE41-NEXT: pcmpgtb %xmm4, %xmm0
|
|
; SSE41-NEXT: pmullw %xmm3, %xmm6
|
|
; SSE41-NEXT: psrlw $8, %xmm6
|
|
; SSE41-NEXT: pmovsxbw %xmm5, %xmm1
|
|
; SSE41-NEXT: pmovsxbw %xmm7, %xmm2
|
|
; SSE41-NEXT: pmullw %xmm1, %xmm2
|
|
; SSE41-NEXT: psrlw $8, %xmm2
|
|
; SSE41-NEXT: packuswb %xmm2, %xmm6
|
|
; SSE41-NEXT: pcmpeqb %xmm0, %xmm6
|
|
; SSE41-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSE41-NEXT: pxor %xmm6, %xmm3
|
|
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm0 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero
|
|
; SSE41-NEXT: pslld $31, %xmm0
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm3[1,1,2,3]
|
|
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero
|
|
; SSE41-NEXT: pslld $31, %xmm1
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm3[2,3,0,1]
|
|
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero
|
|
; SSE41-NEXT: pslld $31, %xmm2
|
|
; SSE41-NEXT: psrad $31, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
|
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero
|
|
; SSE41-NEXT: pslld $31, %xmm3
|
|
; SSE41-NEXT: psrad $31, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm4, (%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v16i8:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm1[8],xmm0[8],xmm1[9],xmm0[9],xmm1[10],xmm0[10],xmm1[11],xmm0[11],xmm1[12],xmm0[12],xmm1[13],xmm0[13],xmm1[14],xmm0[14],xmm1[15],xmm0[15]
|
|
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm3 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
|
; AVX1-NEXT: vpmullw %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
|
; AVX1-NEXT: vpand %xmm3, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm4 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
|
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
|
|
; AVX1-NEXT: vpmullw %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpand %xmm3, %xmm4, %xmm3
|
|
; AVX1-NEXT: vpackuswb %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpgtb %xmm2, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpmovsxbw %xmm1, %xmm4
|
|
; AVX1-NEXT: vpmovsxbw %xmm0, %xmm5
|
|
; AVX1-NEXT: vpmullw %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpsrlw $8, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbw %xmm1, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbw %xmm0, %xmm0
|
|
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpackuswb %xmm0, %xmm4, %xmm0
|
|
; AVX1-NEXT: vpcmpeqb %xmm3, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpmovsxbd %xmm1, %xmm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
|
|
; AVX1-NEXT: vpmovsxbd %xmm3, %xmm3
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[2,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbd %xmm3, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,3,0,1]
|
|
; AVX1-NEXT: vpmovsxbd %xmm1, %xmm1
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
|
|
; AVX1-NEXT: vmovdqa %xmm2, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v16i8:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpmovsxbw %xmm1, %ymm2
|
|
; AVX2-NEXT: vpmovsxbw %xmm0, %ymm3
|
|
; AVX2-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
; AVX2-NEXT: vpsrlw $8, %ymm2, %ymm2
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3
|
|
; AVX2-NEXT: vpackuswb %xmm3, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
|
|
; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
|
|
; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpcmpgtb %xmm3, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpcmpeqb %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpmovsxbd %xmm1, %ymm0
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
|
|
; AVX2-NEXT: vpmovsxbd %xmm1, %ymm1
|
|
; AVX2-NEXT: vmovdqa %xmm3, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v16i8:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
|
|
; AVX512-NEXT: vpmovzxbw {{.*#+}} ymm3 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
|
|
; AVX512-NEXT: vpmullw %ymm2, %ymm3, %ymm2
|
|
; AVX512-NEXT: vpmovwb %ymm2, %xmm2
|
|
; AVX512-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
|
; AVX512-NEXT: vpcmpgtb %xmm2, %xmm3, %xmm3
|
|
; AVX512-NEXT: vpmovsxbw %xmm1, %ymm1
|
|
; AVX512-NEXT: vpmovsxbw %xmm0, %ymm0
|
|
; AVX512-NEXT: vpmullw %ymm1, %ymm0, %ymm0
|
|
; AVX512-NEXT: vpsrlw $8, %ymm0, %ymm0
|
|
; AVX512-NEXT: vpmovwb %ymm0, %xmm0
|
|
; AVX512-NEXT: vpcmpneqb %xmm3, %xmm0, %k1
|
|
; AVX512-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
|
|
; AVX512-NEXT: vmovdqa %xmm2, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<16 x i8>, <16 x i1>} @llvm.smul.with.overflow.v16i8(<16 x i8> %a0, <16 x i8> %a1)
|
|
%val = extractvalue {<16 x i8>, <16 x i1>} %t, 0
|
|
%obit = extractvalue {<16 x i8>, <16 x i1>} %t, 1
|
|
%res = sext <16 x i1> %obit to <16 x i32>
|
|
store <16 x i8> %val, <16 x i8>* %p2
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <8 x i32> @smulo_v8i16(<8 x i16> %a0, <8 x i16> %a1, <8 x i16>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v8i16:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE2-NEXT: pmulhw %xmm1, %xmm2
|
|
; SSE2-NEXT: pmullw %xmm1, %xmm0
|
|
; SSE2-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE2-NEXT: psraw $15, %xmm0
|
|
; SSE2-NEXT: pcmpeqw %xmm2, %xmm0
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE2-NEXT: pxor %xmm0, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
|
; SSE2-NEXT: pslld $31, %xmm0
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSE2-NEXT: pslld $31, %xmm1
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v8i16:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm2
|
|
; SSSE3-NEXT: pmulhw %xmm1, %xmm2
|
|
; SSSE3-NEXT: pmullw %xmm1, %xmm0
|
|
; SSSE3-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSSE3-NEXT: psraw $15, %xmm0
|
|
; SSSE3-NEXT: pcmpeqw %xmm2, %xmm0
|
|
; SSSE3-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm0, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
|
; SSSE3-NEXT: pslld $31, %xmm0
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSSE3-NEXT: pslld $31, %xmm1
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v8i16:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pmulhw %xmm1, %xmm2
|
|
; SSE41-NEXT: pmullw %xmm1, %xmm0
|
|
; SSE41-NEXT: movdqa %xmm0, (%rdi)
|
|
; SSE41-NEXT: psraw $15, %xmm0
|
|
; SSE41-NEXT: pcmpeqw %xmm2, %xmm0
|
|
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE41-NEXT: pxor %xmm0, %xmm1
|
|
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
|
; SSE41-NEXT: pslld $31, %xmm0
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
|
; SSE41-NEXT: pslld $31, %xmm1
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v8i16:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpmulhw %xmm1, %xmm0, %xmm2
|
|
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsraw $15, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqw %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpmovsxwd %xmm0, %xmm2
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
|
; AVX1-NEXT: vpmovsxwd %xmm0, %xmm0
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
|
|
; AVX1-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v8i16:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpmulhw %xmm1, %xmm0, %xmm2
|
|
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpsraw $15, %xmm1, %xmm0
|
|
; AVX2-NEXT: vpcmpeqw %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpmovsxwd %xmm0, %ymm0
|
|
; AVX2-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v8i16:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpmulhw %xmm1, %xmm0, %xmm2
|
|
; AVX512-NEXT: vpmullw %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpsraw $15, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpcmpneqw %xmm0, %xmm2, %k1
|
|
; AVX512-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
|
|
; AVX512-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
|
|
; AVX512-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<8 x i16>, <8 x i1>} @llvm.smul.with.overflow.v8i16(<8 x i16> %a0, <8 x i16> %a1)
|
|
%val = extractvalue {<8 x i16>, <8 x i1>} %t, 0
|
|
%obit = extractvalue {<8 x i16>, <8 x i1>} %t, 1
|
|
%res = sext <8 x i1> %obit to <8 x i32>
|
|
store <8 x i16> %val, <8 x i16>* %p2
|
|
ret <8 x i32> %res
|
|
}
|
|
|
|
define <2 x i32> @smulo_v2i64(<2 x i64> %a0, <2 x i64> %a1, <2 x i64>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v2i64:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; SSE2-NEXT: movq %xmm2, %r8
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
|
|
; SSE2-NEXT: movq %xmm2, %rcx
|
|
; SSE2-NEXT: movq %xmm1, %rdx
|
|
; SSE2-NEXT: movq %xmm0, %rsi
|
|
; SSE2-NEXT: xorl %eax, %eax
|
|
; SSE2-NEXT: imulq %rdx, %rsi
|
|
; SSE2-NEXT: movq $-1, %r9
|
|
; SSE2-NEXT: movl $0, %edx
|
|
; SSE2-NEXT: cmovoq %r9, %rdx
|
|
; SSE2-NEXT: movq %rdx, %xmm0
|
|
; SSE2-NEXT: imulq %r8, %rcx
|
|
; SSE2-NEXT: cmovoq %r9, %rax
|
|
; SSE2-NEXT: movq %rax, %xmm1
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSE2-NEXT: movq %rsi, %xmm1
|
|
; SSE2-NEXT: movq %rcx, %xmm2
|
|
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; SSE2-NEXT: movdqa %xmm1, (%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v2i64:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
|
|
; SSSE3-NEXT: movq %xmm2, %r8
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
|
|
; SSSE3-NEXT: movq %xmm2, %rcx
|
|
; SSSE3-NEXT: movq %xmm1, %rdx
|
|
; SSSE3-NEXT: movq %xmm0, %rsi
|
|
; SSSE3-NEXT: xorl %eax, %eax
|
|
; SSSE3-NEXT: imulq %rdx, %rsi
|
|
; SSSE3-NEXT: movq $-1, %r9
|
|
; SSSE3-NEXT: movl $0, %edx
|
|
; SSSE3-NEXT: cmovoq %r9, %rdx
|
|
; SSSE3-NEXT: movq %rdx, %xmm0
|
|
; SSSE3-NEXT: imulq %r8, %rcx
|
|
; SSSE3-NEXT: cmovoq %r9, %rax
|
|
; SSSE3-NEXT: movq %rax, %xmm1
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSSE3-NEXT: movq %rsi, %xmm1
|
|
; SSSE3-NEXT: movq %rcx, %xmm2
|
|
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
|
; SSSE3-NEXT: movdqa %xmm1, (%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v2i64:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: movq %xmm1, %r8
|
|
; SSE41-NEXT: movq %xmm0, %rcx
|
|
; SSE41-NEXT: pextrq $1, %xmm1, %rdx
|
|
; SSE41-NEXT: pextrq $1, %xmm0, %rsi
|
|
; SSE41-NEXT: xorl %eax, %eax
|
|
; SSE41-NEXT: imulq %rdx, %rsi
|
|
; SSE41-NEXT: movq $-1, %r9
|
|
; SSE41-NEXT: movl $0, %edx
|
|
; SSE41-NEXT: cmovoq %r9, %rdx
|
|
; SSE41-NEXT: movq %rdx, %xmm1
|
|
; SSE41-NEXT: imulq %r8, %rcx
|
|
; SSE41-NEXT: cmovoq %r9, %rax
|
|
; SSE41-NEXT: movq %rax, %xmm0
|
|
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSE41-NEXT: movq %rsi, %xmm1
|
|
; SSE41-NEXT: movq %rcx, %xmm2
|
|
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
|
|
; SSE41-NEXT: movdqa %xmm2, (%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v2i64:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vmovq %xmm1, %r8
|
|
; AVX1-NEXT: vmovq %xmm0, %rcx
|
|
; AVX1-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX1-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX1-NEXT: xorl %eax, %eax
|
|
; AVX1-NEXT: imulq %rdx, %rsi
|
|
; AVX1-NEXT: movq $-1, %r9
|
|
; AVX1-NEXT: movl $0, %edx
|
|
; AVX1-NEXT: cmovoq %r9, %rdx
|
|
; AVX1-NEXT: vmovq %rdx, %xmm0
|
|
; AVX1-NEXT: imulq %r8, %rcx
|
|
; AVX1-NEXT: cmovoq %r9, %rax
|
|
; AVX1-NEXT: vmovq %rax, %xmm1
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
|
; AVX1-NEXT: vmovq %rsi, %xmm1
|
|
; AVX1-NEXT: vmovq %rcx, %xmm2
|
|
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
|
; AVX1-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v2i64:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vmovq %xmm1, %r8
|
|
; AVX2-NEXT: vmovq %xmm0, %rcx
|
|
; AVX2-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX2-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX2-NEXT: xorl %eax, %eax
|
|
; AVX2-NEXT: imulq %rdx, %rsi
|
|
; AVX2-NEXT: movq $-1, %r9
|
|
; AVX2-NEXT: movl $0, %edx
|
|
; AVX2-NEXT: cmovoq %r9, %rdx
|
|
; AVX2-NEXT: vmovq %rdx, %xmm0
|
|
; AVX2-NEXT: imulq %r8, %rcx
|
|
; AVX2-NEXT: cmovoq %r9, %rax
|
|
; AVX2-NEXT: vmovq %rax, %xmm1
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
|
; AVX2-NEXT: vmovq %rsi, %xmm1
|
|
; AVX2-NEXT: vmovq %rcx, %xmm2
|
|
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
|
; AVX2-NEXT: vmovdqa %xmm1, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v2i64:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vmovq %xmm1, %rax
|
|
; AVX512-NEXT: vmovq %xmm0, %rcx
|
|
; AVX512-NEXT: vpextrq $1, %xmm1, %rdx
|
|
; AVX512-NEXT: vpextrq $1, %xmm0, %rsi
|
|
; AVX512-NEXT: imulq %rdx, %rsi
|
|
; AVX512-NEXT: seto %dl
|
|
; AVX512-NEXT: kmovd %edx, %k0
|
|
; AVX512-NEXT: kshiftlw $1, %k0, %k0
|
|
; AVX512-NEXT: imulq %rax, %rcx
|
|
; AVX512-NEXT: seto %al
|
|
; AVX512-NEXT: andl $1, %eax
|
|
; AVX512-NEXT: kmovw %eax, %k1
|
|
; AVX512-NEXT: korw %k0, %k1, %k1
|
|
; AVX512-NEXT: vmovq %rsi, %xmm0
|
|
; AVX512-NEXT: vmovq %rcx, %xmm1
|
|
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
|
; AVX512-NEXT: vmovdqa %xmm0, (%rdi)
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa64 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: retq
|
|
%t = call {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64> %a0, <2 x i64> %a1)
|
|
%val = extractvalue {<2 x i64>, <2 x i1>} %t, 0
|
|
%obit = extractvalue {<2 x i64>, <2 x i1>} %t, 1
|
|
%res = sext <2 x i1> %obit to <2 x i32>
|
|
store <2 x i64> %val, <2 x i64>* %p2
|
|
ret <2 x i32> %res
|
|
}
|
|
|
|
define <4 x i32> @smulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v4i24:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pslld $8, %xmm0
|
|
; SSE2-NEXT: psrad $8, %xmm0
|
|
; SSE2-NEXT: pslld $8, %xmm1
|
|
; SSE2-NEXT: psrad $8, %xmm1
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; SSE2-NEXT: pand %xmm0, %xmm2
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm4
|
|
; SSE2-NEXT: pand %xmm1, %xmm4
|
|
; SSE2-NEXT: paddd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm5, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
|
|
; SSE2-NEXT: psubd %xmm4, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
|
|
; SSE2-NEXT: movdqa %xmm4, %xmm1
|
|
; SSE2-NEXT: pslld $8, %xmm1
|
|
; SSE2-NEXT: psrad $8, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1]
|
|
; SSE2-NEXT: psrad $31, %xmm4
|
|
; SSE2-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; SSE2-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSE2-NEXT: pxor %xmm3, %xmm4
|
|
; SSE2-NEXT: pxor %xmm3, %xmm1
|
|
; SSE2-NEXT: por %xmm4, %xmm1
|
|
; SSE2-NEXT: movd %xmm0, %eax
|
|
; SSE2-NEXT: movw %ax, (%rdi)
|
|
; SSE2-NEXT: movd %xmm2, %ecx
|
|
; SSE2-NEXT: movw %cx, 3(%rdi)
|
|
; SSE2-NEXT: shrl $16, %eax
|
|
; SSE2-NEXT: movb %al, 2(%rdi)
|
|
; SSE2-NEXT: shrl $16, %ecx
|
|
; SSE2-NEXT: movb %cl, 5(%rdi)
|
|
; SSE2-NEXT: movd %xmm5, %eax
|
|
; SSE2-NEXT: movw %ax, 9(%rdi)
|
|
; SSE2-NEXT: movd %xmm6, %ecx
|
|
; SSE2-NEXT: movw %cx, 6(%rdi)
|
|
; SSE2-NEXT: shrl $16, %eax
|
|
; SSE2-NEXT: movb %al, 11(%rdi)
|
|
; SSE2-NEXT: shrl $16, %ecx
|
|
; SSE2-NEXT: movb %cl, 8(%rdi)
|
|
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v4i24:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pslld $8, %xmm0
|
|
; SSSE3-NEXT: psrad $8, %xmm0
|
|
; SSSE3-NEXT: pslld $8, %xmm1
|
|
; SSSE3-NEXT: psrad $8, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm4, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm2
|
|
; SSSE3-NEXT: pand %xmm0, %xmm2
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm4
|
|
; SSSE3-NEXT: pand %xmm1, %xmm4
|
|
; SSSE3-NEXT: paddd %xmm2, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm5, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
|
|
; SSSE3-NEXT: psubd %xmm4, %xmm3
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
|
|
; SSSE3-NEXT: movdqa %xmm4, %xmm1
|
|
; SSSE3-NEXT: pslld $8, %xmm1
|
|
; SSSE3-NEXT: psrad $8, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1]
|
|
; SSSE3-NEXT: psrad $31, %xmm4
|
|
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm4
|
|
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm3
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm4
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm1
|
|
; SSSE3-NEXT: por %xmm4, %xmm1
|
|
; SSSE3-NEXT: movd %xmm0, %eax
|
|
; SSSE3-NEXT: movw %ax, (%rdi)
|
|
; SSSE3-NEXT: movd %xmm2, %ecx
|
|
; SSSE3-NEXT: movw %cx, 3(%rdi)
|
|
; SSSE3-NEXT: shrl $16, %eax
|
|
; SSSE3-NEXT: movb %al, 2(%rdi)
|
|
; SSSE3-NEXT: shrl $16, %ecx
|
|
; SSSE3-NEXT: movb %cl, 5(%rdi)
|
|
; SSSE3-NEXT: movd %xmm5, %eax
|
|
; SSSE3-NEXT: movw %ax, 9(%rdi)
|
|
; SSSE3-NEXT: movd %xmm6, %ecx
|
|
; SSSE3-NEXT: movw %cx, 6(%rdi)
|
|
; SSSE3-NEXT: shrl $16, %eax
|
|
; SSSE3-NEXT: movb %al, 11(%rdi)
|
|
; SSSE3-NEXT: shrl $16, %ecx
|
|
; SSSE3-NEXT: movb %cl, 8(%rdi)
|
|
; SSSE3-NEXT: movdqa %xmm1, %xmm0
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v4i24:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pslld $8, %xmm0
|
|
; SSE41-NEXT: psrad $8, %xmm0
|
|
; SSE41-NEXT: pslld $8, %xmm1
|
|
; SSE41-NEXT: psrad $8, %xmm1
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pmuldq %xmm1, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5],xmm3[6,7]
|
|
; SSE41-NEXT: pmulld %xmm0, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm3
|
|
; SSE41-NEXT: pslld $8, %xmm3
|
|
; SSE41-NEXT: psrad $8, %xmm3
|
|
; SSE41-NEXT: pcmpeqd %xmm1, %xmm3
|
|
; SSE41-NEXT: pextrd $3, %xmm1, %eax
|
|
; SSE41-NEXT: pextrd $2, %xmm1, %ecx
|
|
; SSE41-NEXT: pextrd $1, %xmm1, %edx
|
|
; SSE41-NEXT: movd %xmm1, %esi
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSE41-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE41-NEXT: pxor %xmm0, %xmm1
|
|
; SSE41-NEXT: pxor %xmm3, %xmm0
|
|
; SSE41-NEXT: por %xmm1, %xmm0
|
|
; SSE41-NEXT: movw %ax, 9(%rdi)
|
|
; SSE41-NEXT: movw %cx, 6(%rdi)
|
|
; SSE41-NEXT: movw %dx, 3(%rdi)
|
|
; SSE41-NEXT: movw %si, (%rdi)
|
|
; SSE41-NEXT: shrl $16, %eax
|
|
; SSE41-NEXT: movb %al, 11(%rdi)
|
|
; SSE41-NEXT: shrl $16, %ecx
|
|
; SSE41-NEXT: movb %cl, 8(%rdi)
|
|
; SSE41-NEXT: shrl $16, %edx
|
|
; SSE41-NEXT: movb %dl, 5(%rdi)
|
|
; SSE41-NEXT: shrl $16, %esi
|
|
; SSE41-NEXT: movb %sil, 2(%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v4i24:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpslld $8, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrad $8, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpslld $8, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsrad $8, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3],xmm3[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpslld $8, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpsrad $8, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpor %xmm0, %xmm2, %xmm0
|
|
; AVX1-NEXT: vpextrd $3, %xmm1, %eax
|
|
; AVX1-NEXT: movw %ax, 9(%rdi)
|
|
; AVX1-NEXT: vpextrd $2, %xmm1, %ecx
|
|
; AVX1-NEXT: movw %cx, 6(%rdi)
|
|
; AVX1-NEXT: vpextrd $1, %xmm1, %edx
|
|
; AVX1-NEXT: movw %dx, 3(%rdi)
|
|
; AVX1-NEXT: vmovd %xmm1, %esi
|
|
; AVX1-NEXT: movw %si, (%rdi)
|
|
; AVX1-NEXT: shrl $16, %eax
|
|
; AVX1-NEXT: movb %al, 11(%rdi)
|
|
; AVX1-NEXT: shrl $16, %ecx
|
|
; AVX1-NEXT: movb %cl, 8(%rdi)
|
|
; AVX1-NEXT: shrl $16, %edx
|
|
; AVX1-NEXT: movb %dl, 5(%rdi)
|
|
; AVX1-NEXT: shrl $16, %esi
|
|
; AVX1-NEXT: movb %sil, 2(%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v4i24:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpslld $8, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpsrad $8, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpslld $8, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpsrad $8, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX2-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3]
|
|
; AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpslld $8, %xmm1, %xmm3
|
|
; AVX2-NEXT: vpsrad $8, %xmm3, %xmm3
|
|
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm3, %xmm3
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
|
|
; AVX2-NEXT: vpextrd $3, %xmm1, %eax
|
|
; AVX2-NEXT: movw %ax, 9(%rdi)
|
|
; AVX2-NEXT: vpextrd $2, %xmm1, %ecx
|
|
; AVX2-NEXT: movw %cx, 6(%rdi)
|
|
; AVX2-NEXT: vpextrd $1, %xmm1, %edx
|
|
; AVX2-NEXT: movw %dx, 3(%rdi)
|
|
; AVX2-NEXT: vmovd %xmm1, %esi
|
|
; AVX2-NEXT: movw %si, (%rdi)
|
|
; AVX2-NEXT: shrl $16, %eax
|
|
; AVX2-NEXT: movb %al, 11(%rdi)
|
|
; AVX2-NEXT: shrl $16, %ecx
|
|
; AVX2-NEXT: movb %cl, 8(%rdi)
|
|
; AVX2-NEXT: shrl $16, %edx
|
|
; AVX2-NEXT: movb %dl, 5(%rdi)
|
|
; AVX2-NEXT: shrl $16, %esi
|
|
; AVX2-NEXT: movb %sil, 2(%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v4i24:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: vpslld $8, %xmm1, %xmm1
|
|
; AVX512-NEXT: vpsrad $8, %xmm1, %xmm1
|
|
; AVX512-NEXT: vpslld $8, %xmm0, %xmm0
|
|
; AVX512-NEXT: vpsrad $8, %xmm0, %xmm0
|
|
; AVX512-NEXT: vpmuldq %xmm1, %xmm0, %xmm2
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
|
; AVX512-NEXT: vpshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
|
; AVX512-NEXT: vpmuldq %xmm3, %xmm4, %xmm3
|
|
; AVX512-NEXT: vmovdqa {{.*#+}} xmm4 = [1,5,3,7]
|
|
; AVX512-NEXT: vpermi2d %xmm3, %xmm2, %xmm4
|
|
; AVX512-NEXT: vpmulld %xmm1, %xmm0, %xmm1
|
|
; AVX512-NEXT: vpsrad $31, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpcmpneqd %xmm0, %xmm4, %k0
|
|
; AVX512-NEXT: vpslld $8, %xmm1, %xmm0
|
|
; AVX512-NEXT: vpsrad $8, %xmm0, %xmm0
|
|
; AVX512-NEXT: vpcmpneqd %xmm1, %xmm0, %k1
|
|
; AVX512-NEXT: korw %k0, %k1, %k1
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: vpextrd $3, %xmm1, %eax
|
|
; AVX512-NEXT: movw %ax, 9(%rdi)
|
|
; AVX512-NEXT: vpextrd $2, %xmm1, %ecx
|
|
; AVX512-NEXT: movw %cx, 6(%rdi)
|
|
; AVX512-NEXT: vpextrd $1, %xmm1, %edx
|
|
; AVX512-NEXT: movw %dx, 3(%rdi)
|
|
; AVX512-NEXT: vmovd %xmm1, %esi
|
|
; AVX512-NEXT: movw %si, (%rdi)
|
|
; AVX512-NEXT: shrl $16, %eax
|
|
; AVX512-NEXT: movb %al, 11(%rdi)
|
|
; AVX512-NEXT: shrl $16, %ecx
|
|
; AVX512-NEXT: movb %cl, 8(%rdi)
|
|
; AVX512-NEXT: shrl $16, %edx
|
|
; AVX512-NEXT: movb %dl, 5(%rdi)
|
|
; AVX512-NEXT: shrl $16, %esi
|
|
; AVX512-NEXT: movb %sil, 2(%rdi)
|
|
; AVX512-NEXT: retq
|
|
%t = call {<4 x i24>, <4 x i1>} @llvm.smul.with.overflow.v4i24(<4 x i24> %a0, <4 x i24> %a1)
|
|
%val = extractvalue {<4 x i24>, <4 x i1>} %t, 0
|
|
%obit = extractvalue {<4 x i24>, <4 x i1>} %t, 1
|
|
%res = sext <4 x i1> %obit to <4 x i32>
|
|
store <4 x i24> %val, <4 x i24>* %p2
|
|
ret <4 x i32> %res
|
|
}
|
|
|
|
define <4 x i32> @smulo_v4i1(<4 x i1> %a0, <4 x i1> %a1, <4 x i1>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v4i1:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pslld $31, %xmm0
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pslld $31, %xmm1
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm3, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSE2-NEXT: pand %xmm0, %xmm3
|
|
; SSE2-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSE2-NEXT: pand %xmm1, %xmm2
|
|
; SSE2-NEXT: paddd %xmm3, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSE2-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSE2-NEXT: psubd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm1
|
|
; SSE2-NEXT: psrad $31, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSE2-NEXT: pxor %xmm2, %xmm1
|
|
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
|
; SSE2-NEXT: pslld $31, %xmm3
|
|
; SSE2-NEXT: psrad $31, %xmm3
|
|
; SSE2-NEXT: pcmpeqd %xmm3, %xmm0
|
|
; SSE2-NEXT: pxor %xmm2, %xmm0
|
|
; SSE2-NEXT: por %xmm1, %xmm0
|
|
; SSE2-NEXT: movmskps %xmm3, %eax
|
|
; SSE2-NEXT: movb %al, (%rdi)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v4i1:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pslld $31, %xmm0
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pslld $31, %xmm1
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm3, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm3
|
|
; SSSE3-NEXT: pand %xmm0, %xmm3
|
|
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm2
|
|
; SSSE3-NEXT: pand %xmm1, %xmm2
|
|
; SSSE3-NEXT: paddd %xmm3, %xmm2
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm1, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,3,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
|
; SSSE3-NEXT: pmuludq %xmm3, %xmm1
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
|
; SSSE3-NEXT: psubd %xmm2, %xmm4
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm1
|
|
; SSSE3-NEXT: psrad $31, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1
|
|
; SSSE3-NEXT: pcmpeqd %xmm2, %xmm2
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm1
|
|
; SSSE3-NEXT: movdqa %xmm0, %xmm3
|
|
; SSSE3-NEXT: pslld $31, %xmm3
|
|
; SSSE3-NEXT: psrad $31, %xmm3
|
|
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm0
|
|
; SSSE3-NEXT: pxor %xmm2, %xmm0
|
|
; SSSE3-NEXT: por %xmm1, %xmm0
|
|
; SSSE3-NEXT: movmskps %xmm3, %eax
|
|
; SSSE3-NEXT: movb %al, (%rdi)
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v4i1:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pslld $31, %xmm0
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pslld $31, %xmm1
|
|
; SSE41-NEXT: psrad $31, %xmm1
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: pmuldq %xmm2, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm0, %xmm2
|
|
; SSE41-NEXT: pmuldq %xmm1, %xmm2
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1],xmm3[2,3],xmm2[4,5],xmm3[6,7]
|
|
; SSE41-NEXT: pmulld %xmm0, %xmm1
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm3
|
|
; SSE41-NEXT: psrad $31, %xmm3
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm3
|
|
; SSE41-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE41-NEXT: pxor %xmm0, %xmm3
|
|
; SSE41-NEXT: movdqa %xmm1, %xmm2
|
|
; SSE41-NEXT: pslld $31, %xmm2
|
|
; SSE41-NEXT: psrad $31, %xmm2
|
|
; SSE41-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSE41-NEXT: pxor %xmm1, %xmm0
|
|
; SSE41-NEXT: por %xmm3, %xmm0
|
|
; SSE41-NEXT: movmskps %xmm2, %eax
|
|
; SSE41-NEXT: movb %al, (%rdi)
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v4i1:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: vpslld $31, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrad $31, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpslld $31, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX1-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX1-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm3[0,1],xmm2[2,3],xmm3[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpsrad $31, %xmm0, %xmm1
|
|
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm2, %xmm1
|
|
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpslld $31, %xmm0, %xmm3
|
|
; AVX1-NEXT: vpsrad $31, %xmm3, %xmm3
|
|
; AVX1-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
|
; AVX1-NEXT: vmovmskps %xmm3, %eax
|
|
; AVX1-NEXT: movb %al, (%rdi)
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v4i1:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpsrad $31, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpslld $31, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpsrad $31, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
|
|
; AVX2-NEXT: vpmuldq %xmm2, %xmm3, %xmm2
|
|
; AVX2-NEXT: vpmuldq %xmm1, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3]
|
|
; AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpsrad $31, %xmm0, %xmm1
|
|
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm2, %xmm1
|
|
; AVX2-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpslld $31, %xmm0, %xmm3
|
|
; AVX2-NEXT: vpsrad $31, %xmm3, %xmm3
|
|
; AVX2-NEXT: vpcmpeqd %xmm0, %xmm3, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
|
; AVX2-NEXT: vmovmskps %xmm3, %eax
|
|
; AVX2-NEXT: movb %al, (%rdi)
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v4i1:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: pushq %rbx
|
|
; AVX512-NEXT: vpslld $31, %xmm1, %xmm1
|
|
; AVX512-NEXT: vptestmd %xmm1, %xmm1, %k0
|
|
; AVX512-NEXT: kshiftrw $3, %k0, %k1
|
|
; AVX512-NEXT: kmovd %k1, %r9d
|
|
; AVX512-NEXT: andb $1, %r9b
|
|
; AVX512-NEXT: negb %r9b
|
|
; AVX512-NEXT: vpslld $31, %xmm0, %xmm0
|
|
; AVX512-NEXT: vptestmd %xmm0, %xmm0, %k1
|
|
; AVX512-NEXT: kshiftrw $3, %k1, %k2
|
|
; AVX512-NEXT: kmovd %k2, %r10d
|
|
; AVX512-NEXT: andb $1, %r10b
|
|
; AVX512-NEXT: negb %r10b
|
|
; AVX512-NEXT: kshiftrw $2, %k1, %k2
|
|
; AVX512-NEXT: kmovd %k2, %r11d
|
|
; AVX512-NEXT: andb $1, %r11b
|
|
; AVX512-NEXT: negb %r11b
|
|
; AVX512-NEXT: kshiftrw $2, %k0, %k2
|
|
; AVX512-NEXT: kmovd %k2, %ebx
|
|
; AVX512-NEXT: andb $1, %bl
|
|
; AVX512-NEXT: negb %bl
|
|
; AVX512-NEXT: kshiftrw $1, %k0, %k2
|
|
; AVX512-NEXT: kmovd %k2, %esi
|
|
; AVX512-NEXT: andb $1, %sil
|
|
; AVX512-NEXT: negb %sil
|
|
; AVX512-NEXT: kshiftrw $1, %k1, %k2
|
|
; AVX512-NEXT: kmovd %k2, %edx
|
|
; AVX512-NEXT: andb $1, %dl
|
|
; AVX512-NEXT: negb %dl
|
|
; AVX512-NEXT: kmovd %k1, %eax
|
|
; AVX512-NEXT: andb $1, %al
|
|
; AVX512-NEXT: negb %al
|
|
; AVX512-NEXT: kmovd %k0, %ecx
|
|
; AVX512-NEXT: andb $1, %cl
|
|
; AVX512-NEXT: negb %cl
|
|
; AVX512-NEXT: # kill: def $al killed $al killed $eax
|
|
; AVX512-NEXT: imulb %cl
|
|
; AVX512-NEXT: movl %eax, %r8d
|
|
; AVX512-NEXT: seto %al
|
|
; AVX512-NEXT: movl %r8d, %ecx
|
|
; AVX512-NEXT: andb $1, %cl
|
|
; AVX512-NEXT: negb %cl
|
|
; AVX512-NEXT: cmpb %r8b, %cl
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: orb %al, %cl
|
|
; AVX512-NEXT: setne %al
|
|
; AVX512-NEXT: kmovd %eax, %k0
|
|
; AVX512-NEXT: kshiftrw $1, %k0, %k1
|
|
; AVX512-NEXT: movl %edx, %eax
|
|
; AVX512-NEXT: imulb %sil
|
|
; AVX512-NEXT: movl %eax, %edx
|
|
; AVX512-NEXT: seto %al
|
|
; AVX512-NEXT: movl %edx, %ecx
|
|
; AVX512-NEXT: andb $1, %cl
|
|
; AVX512-NEXT: negb %cl
|
|
; AVX512-NEXT: cmpb %dl, %cl
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: orb %al, %cl
|
|
; AVX512-NEXT: setne %al
|
|
; AVX512-NEXT: kmovd %eax, %k2
|
|
; AVX512-NEXT: kxorw %k2, %k1, %k1
|
|
; AVX512-NEXT: kshiftlw $15, %k1, %k1
|
|
; AVX512-NEXT: kshiftrw $14, %k1, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k0
|
|
; AVX512-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512-NEXT: movl %r11d, %eax
|
|
; AVX512-NEXT: imulb %bl
|
|
; AVX512-NEXT: movl %eax, %esi
|
|
; AVX512-NEXT: seto %al
|
|
; AVX512-NEXT: movl %esi, %ecx
|
|
; AVX512-NEXT: andb $1, %cl
|
|
; AVX512-NEXT: negb %cl
|
|
; AVX512-NEXT: cmpb %sil, %cl
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: orb %al, %cl
|
|
; AVX512-NEXT: setne %al
|
|
; AVX512-NEXT: kmovd %eax, %k2
|
|
; AVX512-NEXT: kxorw %k2, %k1, %k1
|
|
; AVX512-NEXT: kshiftlw $15, %k1, %k1
|
|
; AVX512-NEXT: kshiftrw $13, %k1, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k0
|
|
; AVX512-NEXT: kshiftlw $13, %k0, %k0
|
|
; AVX512-NEXT: kshiftrw $13, %k0, %k0
|
|
; AVX512-NEXT: movl %r10d, %eax
|
|
; AVX512-NEXT: imulb %r9b
|
|
; AVX512-NEXT: # kill: def $al killed $al def $eax
|
|
; AVX512-NEXT: seto %cl
|
|
; AVX512-NEXT: movl %eax, %ebx
|
|
; AVX512-NEXT: andb $1, %bl
|
|
; AVX512-NEXT: negb %bl
|
|
; AVX512-NEXT: cmpb %al, %bl
|
|
; AVX512-NEXT: setne %bl
|
|
; AVX512-NEXT: orb %cl, %bl
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: kmovd %ecx, %k1
|
|
; AVX512-NEXT: kshiftlw $3, %k1, %k1
|
|
; AVX512-NEXT: korw %k1, %k0, %k1
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa32 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: kmovd %r8d, %k0
|
|
; AVX512-NEXT: kshiftrw $1, %k0, %k1
|
|
; AVX512-NEXT: kmovd %edx, %k2
|
|
; AVX512-NEXT: kxorw %k2, %k1, %k1
|
|
; AVX512-NEXT: kshiftlw $15, %k1, %k1
|
|
; AVX512-NEXT: kshiftrw $14, %k1, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k0
|
|
; AVX512-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512-NEXT: kmovd %esi, %k2
|
|
; AVX512-NEXT: kxorw %k2, %k1, %k1
|
|
; AVX512-NEXT: kshiftlw $15, %k1, %k1
|
|
; AVX512-NEXT: kshiftrw $13, %k1, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k0
|
|
; AVX512-NEXT: kshiftrw $3, %k0, %k1
|
|
; AVX512-NEXT: kmovd %eax, %k2
|
|
; AVX512-NEXT: kxorw %k2, %k1, %k1
|
|
; AVX512-NEXT: kshiftlw $15, %k1, %k1
|
|
; AVX512-NEXT: kshiftrw $12, %k1, %k1
|
|
; AVX512-NEXT: kxorw %k1, %k0, %k0
|
|
; AVX512-NEXT: kmovd %k0, %eax
|
|
; AVX512-NEXT: movb %al, (%rdi)
|
|
; AVX512-NEXT: popq %rbx
|
|
; AVX512-NEXT: retq
|
|
%t = call {<4 x i1>, <4 x i1>} @llvm.smul.with.overflow.v4i1(<4 x i1> %a0, <4 x i1> %a1)
|
|
%val = extractvalue {<4 x i1>, <4 x i1>} %t, 0
|
|
%obit = extractvalue {<4 x i1>, <4 x i1>} %t, 1
|
|
%res = sext <4 x i1> %obit to <4 x i32>
|
|
store <4 x i1> %val, <4 x i1>* %p2
|
|
ret <4 x i32> %res
|
|
}
|
|
|
|
define <2 x i32> @smulo_v2i128(<2 x i128> %a0, <2 x i128> %a1, <2 x i128>* %p2) nounwind {
|
|
; SSE2-LABEL: smulo_v2i128:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: pushq %rbp
|
|
; SSE2-NEXT: pushq %r15
|
|
; SSE2-NEXT: pushq %r14
|
|
; SSE2-NEXT: pushq %r13
|
|
; SSE2-NEXT: pushq %r12
|
|
; SSE2-NEXT: pushq %rbx
|
|
; SSE2-NEXT: subq $24, %rsp
|
|
; SSE2-NEXT: movq %r8, %rax
|
|
; SSE2-NEXT: movq %rcx, %r14
|
|
; SSE2-NEXT: movq %rdx, %rbx
|
|
; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; SSE2-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSE2-NEXT: movq %rax, %rdx
|
|
; SSE2-NEXT: movq %r9, %rcx
|
|
; SSE2-NEXT: callq __muloti4
|
|
; SSE2-NEXT: movq %rax, %r13
|
|
; SSE2-NEXT: movq %rdx, %rbp
|
|
; SSE2-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSE2-NEXT: movq %rbx, %rdi
|
|
; SSE2-NEXT: movq %r14, %rsi
|
|
; SSE2-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; SSE2-NEXT: movq %r12, %rcx
|
|
; SSE2-NEXT: callq __muloti4
|
|
; SSE2-NEXT: xorl %ecx, %ecx
|
|
; SSE2-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: setne %cl
|
|
; SSE2-NEXT: xorl %esi, %esi
|
|
; SSE2-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: setne %sil
|
|
; SSE2-NEXT: movd %esi, %xmm0
|
|
; SSE2-NEXT: pinsrw $4, %ecx, %xmm0
|
|
; SSE2-NEXT: movq %rdx, 24(%r15)
|
|
; SSE2-NEXT: movq %rax, 16(%r15)
|
|
; SSE2-NEXT: movq %rbp, 8(%r15)
|
|
; SSE2-NEXT: movq %r13, (%r15)
|
|
; SSE2-NEXT: psllq $63, %xmm0
|
|
; SSE2-NEXT: psrad $31, %xmm0
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
|
|
; SSE2-NEXT: addq $24, %rsp
|
|
; SSE2-NEXT: popq %rbx
|
|
; SSE2-NEXT: popq %r12
|
|
; SSE2-NEXT: popq %r13
|
|
; SSE2-NEXT: popq %r14
|
|
; SSE2-NEXT: popq %r15
|
|
; SSE2-NEXT: popq %rbp
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: smulo_v2i128:
|
|
; SSSE3: # %bb.0:
|
|
; SSSE3-NEXT: pushq %rbp
|
|
; SSSE3-NEXT: pushq %r15
|
|
; SSSE3-NEXT: pushq %r14
|
|
; SSSE3-NEXT: pushq %r13
|
|
; SSSE3-NEXT: pushq %r12
|
|
; SSSE3-NEXT: pushq %rbx
|
|
; SSSE3-NEXT: subq $24, %rsp
|
|
; SSSE3-NEXT: movq %r8, %rax
|
|
; SSSE3-NEXT: movq %rcx, %r14
|
|
; SSSE3-NEXT: movq %rdx, %rbx
|
|
; SSSE3-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; SSSE3-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; SSSE3-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSSE3-NEXT: movq %rax, %rdx
|
|
; SSSE3-NEXT: movq %r9, %rcx
|
|
; SSSE3-NEXT: callq __muloti4
|
|
; SSSE3-NEXT: movq %rax, %r13
|
|
; SSSE3-NEXT: movq %rdx, %rbp
|
|
; SSSE3-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSSE3-NEXT: movq %rbx, %rdi
|
|
; SSSE3-NEXT: movq %r14, %rsi
|
|
; SSSE3-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; SSSE3-NEXT: movq %r12, %rcx
|
|
; SSSE3-NEXT: callq __muloti4
|
|
; SSSE3-NEXT: xorl %ecx, %ecx
|
|
; SSSE3-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: setne %cl
|
|
; SSSE3-NEXT: xorl %esi, %esi
|
|
; SSSE3-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: setne %sil
|
|
; SSSE3-NEXT: movd %esi, %xmm0
|
|
; SSSE3-NEXT: pinsrw $4, %ecx, %xmm0
|
|
; SSSE3-NEXT: movq %rdx, 24(%r15)
|
|
; SSSE3-NEXT: movq %rax, 16(%r15)
|
|
; SSSE3-NEXT: movq %rbp, 8(%r15)
|
|
; SSSE3-NEXT: movq %r13, (%r15)
|
|
; SSSE3-NEXT: psllq $63, %xmm0
|
|
; SSSE3-NEXT: psrad $31, %xmm0
|
|
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
|
|
; SSSE3-NEXT: addq $24, %rsp
|
|
; SSSE3-NEXT: popq %rbx
|
|
; SSSE3-NEXT: popq %r12
|
|
; SSSE3-NEXT: popq %r13
|
|
; SSSE3-NEXT: popq %r14
|
|
; SSSE3-NEXT: popq %r15
|
|
; SSSE3-NEXT: popq %rbp
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: smulo_v2i128:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: pushq %rbp
|
|
; SSE41-NEXT: pushq %r15
|
|
; SSE41-NEXT: pushq %r14
|
|
; SSE41-NEXT: pushq %r13
|
|
; SSE41-NEXT: pushq %r12
|
|
; SSE41-NEXT: pushq %rbx
|
|
; SSE41-NEXT: subq $24, %rsp
|
|
; SSE41-NEXT: movq %r8, %rax
|
|
; SSE41-NEXT: movq %rcx, %r14
|
|
; SSE41-NEXT: movq %rdx, %rbx
|
|
; SSE41-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; SSE41-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; SSE41-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSE41-NEXT: movq %rax, %rdx
|
|
; SSE41-NEXT: movq %r9, %rcx
|
|
; SSE41-NEXT: callq __muloti4
|
|
; SSE41-NEXT: movq %rax, %r13
|
|
; SSE41-NEXT: movq %rdx, %rbp
|
|
; SSE41-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; SSE41-NEXT: movq %rbx, %rdi
|
|
; SSE41-NEXT: movq %r14, %rsi
|
|
; SSE41-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; SSE41-NEXT: movq %r12, %rcx
|
|
; SSE41-NEXT: callq __muloti4
|
|
; SSE41-NEXT: xorl %ecx, %ecx
|
|
; SSE41-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: setne %cl
|
|
; SSE41-NEXT: xorl %esi, %esi
|
|
; SSE41-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: setne %sil
|
|
; SSE41-NEXT: movd %esi, %xmm0
|
|
; SSE41-NEXT: pinsrb $8, %ecx, %xmm0
|
|
; SSE41-NEXT: movq %rdx, 24(%r15)
|
|
; SSE41-NEXT: movq %rax, 16(%r15)
|
|
; SSE41-NEXT: movq %rbp, 8(%r15)
|
|
; SSE41-NEXT: movq %r13, (%r15)
|
|
; SSE41-NEXT: psllq $63, %xmm0
|
|
; SSE41-NEXT: psrad $31, %xmm0
|
|
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
|
|
; SSE41-NEXT: addq $24, %rsp
|
|
; SSE41-NEXT: popq %rbx
|
|
; SSE41-NEXT: popq %r12
|
|
; SSE41-NEXT: popq %r13
|
|
; SSE41-NEXT: popq %r14
|
|
; SSE41-NEXT: popq %r15
|
|
; SSE41-NEXT: popq %rbp
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: smulo_v2i128:
|
|
; AVX1: # %bb.0:
|
|
; AVX1-NEXT: pushq %rbp
|
|
; AVX1-NEXT: pushq %r15
|
|
; AVX1-NEXT: pushq %r14
|
|
; AVX1-NEXT: pushq %r13
|
|
; AVX1-NEXT: pushq %r12
|
|
; AVX1-NEXT: pushq %rbx
|
|
; AVX1-NEXT: subq $24, %rsp
|
|
; AVX1-NEXT: movq %r8, %rax
|
|
; AVX1-NEXT: movq %rcx, %r14
|
|
; AVX1-NEXT: movq %rdx, %rbx
|
|
; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; AVX1-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX1-NEXT: movq %rax, %rdx
|
|
; AVX1-NEXT: movq %r9, %rcx
|
|
; AVX1-NEXT: callq __muloti4
|
|
; AVX1-NEXT: movq %rax, %r13
|
|
; AVX1-NEXT: movq %rdx, %rbp
|
|
; AVX1-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX1-NEXT: movq %rbx, %rdi
|
|
; AVX1-NEXT: movq %r14, %rsi
|
|
; AVX1-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX1-NEXT: movq %r12, %rcx
|
|
; AVX1-NEXT: callq __muloti4
|
|
; AVX1-NEXT: xorl %ecx, %ecx
|
|
; AVX1-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: setne %cl
|
|
; AVX1-NEXT: xorl %esi, %esi
|
|
; AVX1-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: setne %sil
|
|
; AVX1-NEXT: vmovd %esi, %xmm0
|
|
; AVX1-NEXT: vpinsrb $8, %ecx, %xmm0, %xmm0
|
|
; AVX1-NEXT: movq %rdx, 24(%r15)
|
|
; AVX1-NEXT: movq %rax, 16(%r15)
|
|
; AVX1-NEXT: movq %rbp, 8(%r15)
|
|
; AVX1-NEXT: movq %r13, (%r15)
|
|
; AVX1-NEXT: vpsllq $63, %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpcmpgtq %xmm0, %xmm1, %xmm0
|
|
; AVX1-NEXT: addq $24, %rsp
|
|
; AVX1-NEXT: popq %rbx
|
|
; AVX1-NEXT: popq %r12
|
|
; AVX1-NEXT: popq %r13
|
|
; AVX1-NEXT: popq %r14
|
|
; AVX1-NEXT: popq %r15
|
|
; AVX1-NEXT: popq %rbp
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: smulo_v2i128:
|
|
; AVX2: # %bb.0:
|
|
; AVX2-NEXT: pushq %rbp
|
|
; AVX2-NEXT: pushq %r15
|
|
; AVX2-NEXT: pushq %r14
|
|
; AVX2-NEXT: pushq %r13
|
|
; AVX2-NEXT: pushq %r12
|
|
; AVX2-NEXT: pushq %rbx
|
|
; AVX2-NEXT: subq $24, %rsp
|
|
; AVX2-NEXT: movq %r8, %rax
|
|
; AVX2-NEXT: movq %rcx, %r14
|
|
; AVX2-NEXT: movq %rdx, %rbx
|
|
; AVX2-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; AVX2-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; AVX2-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX2-NEXT: movq %rax, %rdx
|
|
; AVX2-NEXT: movq %r9, %rcx
|
|
; AVX2-NEXT: callq __muloti4
|
|
; AVX2-NEXT: movq %rax, %r13
|
|
; AVX2-NEXT: movq %rdx, %rbp
|
|
; AVX2-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX2-NEXT: movq %rbx, %rdi
|
|
; AVX2-NEXT: movq %r14, %rsi
|
|
; AVX2-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX2-NEXT: movq %r12, %rcx
|
|
; AVX2-NEXT: callq __muloti4
|
|
; AVX2-NEXT: xorl %ecx, %ecx
|
|
; AVX2-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: setne %cl
|
|
; AVX2-NEXT: xorl %esi, %esi
|
|
; AVX2-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: setne %sil
|
|
; AVX2-NEXT: vmovd %esi, %xmm0
|
|
; AVX2-NEXT: vpinsrb $8, %ecx, %xmm0, %xmm0
|
|
; AVX2-NEXT: movq %rdx, 24(%r15)
|
|
; AVX2-NEXT: movq %rax, 16(%r15)
|
|
; AVX2-NEXT: movq %rbp, 8(%r15)
|
|
; AVX2-NEXT: movq %r13, (%r15)
|
|
; AVX2-NEXT: vpsllq $63, %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpcmpgtq %xmm0, %xmm1, %xmm0
|
|
; AVX2-NEXT: addq $24, %rsp
|
|
; AVX2-NEXT: popq %rbx
|
|
; AVX2-NEXT: popq %r12
|
|
; AVX2-NEXT: popq %r13
|
|
; AVX2-NEXT: popq %r14
|
|
; AVX2-NEXT: popq %r15
|
|
; AVX2-NEXT: popq %rbp
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: smulo_v2i128:
|
|
; AVX512: # %bb.0:
|
|
; AVX512-NEXT: pushq %rbp
|
|
; AVX512-NEXT: pushq %r15
|
|
; AVX512-NEXT: pushq %r14
|
|
; AVX512-NEXT: pushq %r13
|
|
; AVX512-NEXT: pushq %r12
|
|
; AVX512-NEXT: pushq %rbx
|
|
; AVX512-NEXT: subq $24, %rsp
|
|
; AVX512-NEXT: movq %r8, %rax
|
|
; AVX512-NEXT: movq %rcx, %r14
|
|
; AVX512-NEXT: movq %rdx, %rbx
|
|
; AVX512-NEXT: movq {{[0-9]+}}(%rsp), %r15
|
|
; AVX512-NEXT: movq {{[0-9]+}}(%rsp), %r12
|
|
; AVX512-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX512-NEXT: movq %rax, %rdx
|
|
; AVX512-NEXT: movq %r9, %rcx
|
|
; AVX512-NEXT: callq __muloti4
|
|
; AVX512-NEXT: movq %rax, %r13
|
|
; AVX512-NEXT: movq %rdx, %rbp
|
|
; AVX512-NEXT: movq $0, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: leaq {{[0-9]+}}(%rsp), %r8
|
|
; AVX512-NEXT: movq %rbx, %rdi
|
|
; AVX512-NEXT: movq %r14, %rsi
|
|
; AVX512-NEXT: movq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX512-NEXT: movq %r12, %rcx
|
|
; AVX512-NEXT: callq __muloti4
|
|
; AVX512-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: kmovd %ecx, %k0
|
|
; AVX512-NEXT: kshiftlw $1, %k0, %k0
|
|
; AVX512-NEXT: cmpq $0, {{[0-9]+}}(%rsp)
|
|
; AVX512-NEXT: setne %cl
|
|
; AVX512-NEXT: andl $1, %ecx
|
|
; AVX512-NEXT: kmovw %ecx, %k1
|
|
; AVX512-NEXT: korw %k0, %k1, %k1
|
|
; AVX512-NEXT: movq %rdx, 24(%r15)
|
|
; AVX512-NEXT: movq %rax, 16(%r15)
|
|
; AVX512-NEXT: movq %rbp, 8(%r15)
|
|
; AVX512-NEXT: movq %r13, (%r15)
|
|
; AVX512-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
|
; AVX512-NEXT: vmovdqa64 %xmm0, %xmm0 {%k1} {z}
|
|
; AVX512-NEXT: addq $24, %rsp
|
|
; AVX512-NEXT: popq %rbx
|
|
; AVX512-NEXT: popq %r12
|
|
; AVX512-NEXT: popq %r13
|
|
; AVX512-NEXT: popq %r14
|
|
; AVX512-NEXT: popq %r15
|
|
; AVX512-NEXT: popq %rbp
|
|
; AVX512-NEXT: retq
|
|
%t = call {<2 x i128>, <2 x i1>} @llvm.smul.with.overflow.v2i128(<2 x i128> %a0, <2 x i128> %a1)
|
|
%val = extractvalue {<2 x i128>, <2 x i1>} %t, 0
|
|
%obit = extractvalue {<2 x i128>, <2 x i1>} %t, 1
|
|
%res = sext <2 x i1> %obit to <2 x i32>
|
|
store <2 x i128> %val, <2 x i128>* %p2
|
|
ret <2 x i32> %res
|
|
}
|