forked from OSchip/llvm-project
1244 lines
59 KiB
LLVM
1244 lines
59 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
|
|
|
|
;
|
|
; Unary shuffle indices from registers
|
|
;
|
|
|
|
define <2 x double> @var_shuffle_v2f64_v2f64_xx_i64(<2 x double> %x, i64 %i0, i64 %i1) nounwind {
|
|
; SSE-LABEL: var_shuffle_v2f64_v2f64_xx_i64:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; SSE-NEXT: movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v2f64_v2f64_xx_i64:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <2 x double> %x, i64 %i0
|
|
%x1 = extractelement <2 x double> %x, i64 %i1
|
|
%r0 = insertelement <2 x double> undef, double %x0, i32 0
|
|
%r1 = insertelement <2 x double> %r0, double %x1, i32 1
|
|
ret <2 x double> %r1
|
|
}
|
|
|
|
define <2 x i64> @var_shuffle_v2i64_v2i64_xx_i64(<2 x i64> %x, i32 %i0, i32 %i1) nounwind {
|
|
; SSE-LABEL: var_shuffle_v2i64_v2i64_xx_i64:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movslq %edi, %rax
|
|
; SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE-NEXT: movslq %esi, %rcx
|
|
; SSE-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
|
|
; SSE-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
|
|
; SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v2i64_v2i64_xx_i64:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: movslq %edi, %rax
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq %esi, %rcx
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
|
|
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <2 x i64> %x, i32 %i0
|
|
%x1 = extractelement <2 x i64> %x, i32 %i1
|
|
%r0 = insertelement <2 x i64> undef, i64 %x0, i32 0
|
|
%r1 = insertelement <2 x i64> %r0, i64 %x1, i32 1
|
|
ret <2 x i64> %r1
|
|
}
|
|
|
|
define <4 x float> @var_shuffle_v4f32_v4f32_xxxx_i32(<4 x float> %x, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
|
|
; SSE2-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movslq %edi, %rax
|
|
; SSE2-NEXT: movslq %esi, %rsi
|
|
; SSE2-NEXT: movslq %edx, %rdx
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movslq %ecx, %rcx
|
|
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movslq %edi, %rax
|
|
; SSSE3-NEXT: movslq %esi, %rsi
|
|
; SSSE3-NEXT: movslq %edx, %rdx
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movslq %ecx, %rcx
|
|
; SSSE3-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; SSSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
|
|
; SSE41: # BB#0:
|
|
; SSE41-NEXT: movslq %edi, %rax
|
|
; SSE41-NEXT: movslq %esi, %rsi
|
|
; SSE41-NEXT: movslq %edx, %rdx
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movslq %ecx, %rcx
|
|
; SSE41-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; SSE41-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v4f32_v4f32_xxxx_i32:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: movslq %edi, %rax
|
|
; AVX-NEXT: movslq %esi, %rsi
|
|
; AVX-NEXT: movslq %edx, %rdx
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq %ecx, %rcx
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <4 x float> %x, i32 %i0
|
|
%x1 = extractelement <4 x float> %x, i32 %i1
|
|
%x2 = extractelement <4 x float> %x, i32 %i2
|
|
%x3 = extractelement <4 x float> %x, i32 %i3
|
|
%r0 = insertelement <4 x float> undef, float %x0, i32 0
|
|
%r1 = insertelement <4 x float> %r0, float %x1, i32 1
|
|
%r2 = insertelement <4 x float> %r1, float %x2, i32 2
|
|
%r3 = insertelement <4 x float> %r2, float %x3, i32 3
|
|
ret <4 x float> %r3
|
|
}
|
|
|
|
define <4 x i32> @var_shuffle_v4i32_v4i32_xxxx_i32(<4 x i32> %x, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
|
|
; SSE2-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movslq %edi, %rax
|
|
; SSE2-NEXT: movslq %esi, %rsi
|
|
; SSE2-NEXT: movslq %edx, %rdx
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movslq %ecx, %rcx
|
|
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movslq %edi, %rax
|
|
; SSSE3-NEXT: movslq %esi, %rsi
|
|
; SSSE3-NEXT: movslq %edx, %rdx
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movslq %ecx, %rcx
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSE41: # BB#0:
|
|
; SSE41-NEXT: movslq %edi, %rax
|
|
; SSE41-NEXT: movslq %esi, %rsi
|
|
; SSE41-NEXT: movslq %edx, %rdx
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movslq %ecx, %rcx
|
|
; SSE41-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrd $1, -24(%rsp,%rsi,4), %xmm0
|
|
; SSE41-NEXT: pinsrd $2, -24(%rsp,%rdx,4), %xmm0
|
|
; SSE41-NEXT: pinsrd $3, -24(%rsp,%rcx,4), %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: movslq %edi, %rax
|
|
; AVX-NEXT: movslq %esi, %rsi
|
|
; AVX-NEXT: movslq %edx, %rdx
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq %ecx, %rcx
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vpinsrd $1, -24(%rsp,%rsi,4), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrd $2, -24(%rsp,%rdx,4), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrd $3, -24(%rsp,%rcx,4), %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <4 x i32> %x, i32 %i0
|
|
%x1 = extractelement <4 x i32> %x, i32 %i1
|
|
%x2 = extractelement <4 x i32> %x, i32 %i2
|
|
%x3 = extractelement <4 x i32> %x, i32 %i3
|
|
%r0 = insertelement <4 x i32> undef, i32 %x0, i32 0
|
|
%r1 = insertelement <4 x i32> %r0, i32 %x1, i32 1
|
|
%r2 = insertelement <4 x i32> %r1, i32 %x2, i32 2
|
|
%r3 = insertelement <4 x i32> %r2, i32 %x3, i32 3
|
|
ret <4 x i32> %r3
|
|
}
|
|
|
|
define <8 x i16> @var_shuffle_v8i16_v8i16_xxxxxxxx_i16(<8 x i16> %x, i16 %i0, i16 %i1, i16 %i2, i16 %i3, i16 %i4, i16 %i5, i16 %i6, i16 %i7) nounwind {
|
|
; SSE2-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movswq %di, %rax
|
|
; SSE2-NEXT: movswq %si, %rsi
|
|
; SSE2-NEXT: movswq %dx, %rdx
|
|
; SSE2-NEXT: movswq %cx, %r10
|
|
; SSE2-NEXT: movswq %r8w, %r11
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movswq %r9w, %r8
|
|
; SSE2-NEXT: movswq {{[0-9]+}}(%rsp), %rcx
|
|
; SSE2-NEXT: movswq {{[0-9]+}}(%rsp), %rdi
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rcx,2), %ecx
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rdi,2), %edi
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rax,2), %eax
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rsi,2), %esi
|
|
; SSE2-NEXT: movd %ecx, %xmm0
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rdx,2), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm1
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSE2-NEXT: movzwl -24(%rsp,%r10,2), %ecx
|
|
; SSE2-NEXT: movd %eax, %xmm0
|
|
; SSE2-NEXT: movzwl -24(%rsp,%r11,2), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm2
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSE2-NEXT: movd %edi, %xmm1
|
|
; SSE2-NEXT: movd %ecx, %xmm2
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
|
|
; SSE2-NEXT: movd %esi, %xmm1
|
|
; SSE2-NEXT: movzwl -24(%rsp,%r8,2), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movswq %di, %rax
|
|
; SSSE3-NEXT: movswq %si, %rsi
|
|
; SSSE3-NEXT: movswq %dx, %rdx
|
|
; SSSE3-NEXT: movswq %cx, %r10
|
|
; SSSE3-NEXT: movswq %r8w, %r11
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movswq %r9w, %r8
|
|
; SSSE3-NEXT: movswq {{[0-9]+}}(%rsp), %rcx
|
|
; SSSE3-NEXT: movswq {{[0-9]+}}(%rsp), %rdi
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rcx,2), %ecx
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rdi,2), %edi
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rax,2), %eax
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rsi,2), %esi
|
|
; SSSE3-NEXT: movd %ecx, %xmm0
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rdx,2), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm1
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%r10,2), %ecx
|
|
; SSSE3-NEXT: movd %eax, %xmm0
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%r11,2), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm2
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSSE3-NEXT: movd %edi, %xmm1
|
|
; SSSE3-NEXT: movd %ecx, %xmm2
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
|
|
; SSSE3-NEXT: movd %esi, %xmm1
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%r8,2), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm3
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
|
|
; SSE41: # BB#0:
|
|
; SSE41-NEXT: pushq %rbx
|
|
; SSE41-NEXT: movswq %di, %rax
|
|
; SSE41-NEXT: movswq %si, %rbx
|
|
; SSE41-NEXT: movswq %dx, %r11
|
|
; SSE41-NEXT: movswq %cx, %r10
|
|
; SSE41-NEXT: movswq %r8w, %rdi
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movswq %r9w, %rcx
|
|
; SSE41-NEXT: movswq {{[0-9]+}}(%rsp), %rdx
|
|
; SSE41-NEXT: movswq {{[0-9]+}}(%rsp), %rsi
|
|
; SSE41-NEXT: movzwl -16(%rsp,%rdx,2), %edx
|
|
; SSE41-NEXT: movzwl -16(%rsp,%rsi,2), %esi
|
|
; SSE41-NEXT: movzwl -16(%rsp,%rax,2), %eax
|
|
; SSE41-NEXT: movd %eax, %xmm0
|
|
; SSE41-NEXT: pinsrw $1, -16(%rsp,%rbx,2), %xmm0
|
|
; SSE41-NEXT: pinsrw $2, -16(%rsp,%r11,2), %xmm0
|
|
; SSE41-NEXT: pinsrw $3, -16(%rsp,%r10,2), %xmm0
|
|
; SSE41-NEXT: pinsrw $4, -16(%rsp,%rdi,2), %xmm0
|
|
; SSE41-NEXT: pinsrw $5, -16(%rsp,%rcx,2), %xmm0
|
|
; SSE41-NEXT: pinsrw $6, %edx, %xmm0
|
|
; SSE41-NEXT: pinsrw $7, %esi, %xmm0
|
|
; SSE41-NEXT: popq %rbx
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v8i16_v8i16_xxxxxxxx_i16:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: pushq %r14
|
|
; AVX-NEXT: pushq %rbx
|
|
; AVX-NEXT: movswq %di, %r10
|
|
; AVX-NEXT: movswq %si, %r11
|
|
; AVX-NEXT: movswq %dx, %r14
|
|
; AVX-NEXT: movswq %cx, %rcx
|
|
; AVX-NEXT: movswq %r8w, %rdi
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movswq %r9w, %rax
|
|
; AVX-NEXT: movswq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX-NEXT: movswq {{[0-9]+}}(%rsp), %rdx
|
|
; AVX-NEXT: movzwl -24(%rsp,%rsi,2), %esi
|
|
; AVX-NEXT: movzwl -24(%rsp,%rdx,2), %edx
|
|
; AVX-NEXT: movzwl -24(%rsp,%r10,2), %ebx
|
|
; AVX-NEXT: vmovd %ebx, %xmm0
|
|
; AVX-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $2, -24(%rsp,%r14,2), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $4, -24(%rsp,%rdi,2), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $6, %esi, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrw $7, %edx, %xmm0, %xmm0
|
|
; AVX-NEXT: popq %rbx
|
|
; AVX-NEXT: popq %r14
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <8 x i16> %x, i16 %i0
|
|
%x1 = extractelement <8 x i16> %x, i16 %i1
|
|
%x2 = extractelement <8 x i16> %x, i16 %i2
|
|
%x3 = extractelement <8 x i16> %x, i16 %i3
|
|
%x4 = extractelement <8 x i16> %x, i16 %i4
|
|
%x5 = extractelement <8 x i16> %x, i16 %i5
|
|
%x6 = extractelement <8 x i16> %x, i16 %i6
|
|
%x7 = extractelement <8 x i16> %x, i16 %i7
|
|
%r0 = insertelement <8 x i16> undef, i16 %x0, i32 0
|
|
%r1 = insertelement <8 x i16> %r0, i16 %x1, i32 1
|
|
%r2 = insertelement <8 x i16> %r1, i16 %x2, i32 2
|
|
%r3 = insertelement <8 x i16> %r2, i16 %x3, i32 3
|
|
%r4 = insertelement <8 x i16> %r3, i16 %x4, i32 4
|
|
%r5 = insertelement <8 x i16> %r4, i16 %x5, i32 5
|
|
%r6 = insertelement <8 x i16> %r5, i16 %x6, i32 6
|
|
%r7 = insertelement <8 x i16> %r6, i16 %x7, i32 7
|
|
ret <8 x i16> %r7
|
|
}
|
|
|
|
define <16 x i8> @var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8(<16 x i8> %x, i8 %i0, i8 %i1, i8 %i2, i8 %i3, i8 %i4, i8 %i5, i8 %i6, i8 %i7, i8 %i8, i8 %i9, i8 %i10, i8 %i11, i8 %i12, i8 %i13, i8 %i14, i8 %i15) nounwind {
|
|
; SSE2-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %r10
|
|
; SSE2-NEXT: leaq -{{[0-9]+}}(%rsp), %r11
|
|
; SSE2-NEXT: movzbl (%r10,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm15
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm8
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm9
|
|
; SSE2-NEXT: movsbq %dl, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm10
|
|
; SSE2-NEXT: movsbq %dil, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm0
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm11
|
|
; SSE2-NEXT: movsbq %r8b, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm7
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm2
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm12
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm13
|
|
; SSE2-NEXT: movsbq %cl, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm6
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm14
|
|
; SSE2-NEXT: movsbq %sil, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm5
|
|
; SSE2-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm4
|
|
; SSE2-NEXT: movsbq %r9b, %rax
|
|
; SSE2-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm1
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3],xmm3[4],xmm15[4],xmm3[5],xmm15[5],xmm3[6],xmm15[6],xmm3[7],xmm15[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1],xmm0[2],xmm10[2],xmm0[3],xmm10[3],xmm0[4],xmm10[4],xmm0[5],xmm10[5],xmm0[6],xmm10[6],xmm0[7],xmm10[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm11[0],xmm7[1],xmm11[1],xmm7[2],xmm11[2],xmm7[3],xmm11[3],xmm7[4],xmm11[4],xmm7[5],xmm11[5],xmm7[6],xmm11[6],xmm7[7],xmm11[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1],xmm0[2],xmm7[2],xmm0[3],xmm7[3],xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm12[0],xmm2[1],xmm12[1],xmm2[2],xmm12[2],xmm2[3],xmm12[3],xmm2[4],xmm12[4],xmm2[5],xmm12[5],xmm2[6],xmm12[6],xmm2[7],xmm12[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm13[0],xmm6[1],xmm13[1],xmm6[2],xmm13[2],xmm6[3],xmm13[3],xmm6[4],xmm13[4],xmm6[5],xmm13[5],xmm6[6],xmm13[6],xmm6[7],xmm13[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm2[0],xmm6[1],xmm2[1],xmm6[2],xmm2[2],xmm6[3],xmm2[3],xmm6[4],xmm2[4],xmm6[5],xmm2[5],xmm6[6],xmm2[6],xmm6[7],xmm2[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm14[0],xmm5[1],xmm14[1],xmm5[2],xmm14[2],xmm5[3],xmm14[3],xmm5[4],xmm14[4],xmm5[5],xmm14[5],xmm5[6],xmm14[6],xmm5[7],xmm14[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
|
|
; 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: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1],xmm5[2],xmm6[2],xmm5[3],xmm6[3],xmm5[4],xmm6[4],xmm5[5],xmm6[5],xmm5[6],xmm6[6],xmm5[7],xmm6[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3],xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %r10
|
|
; SSSE3-NEXT: leaq -{{[0-9]+}}(%rsp), %r11
|
|
; SSSE3-NEXT: movzbl (%r10,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm15
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm8
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm9
|
|
; SSSE3-NEXT: movsbq %dl, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm3
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm10
|
|
; SSSE3-NEXT: movsbq %dil, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm0
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm11
|
|
; SSSE3-NEXT: movsbq %r8b, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm7
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm2
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm12
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm13
|
|
; SSSE3-NEXT: movsbq %cl, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm6
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm14
|
|
; SSSE3-NEXT: movsbq %sil, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm5
|
|
; SSSE3-NEXT: movsbq {{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm4
|
|
; SSSE3-NEXT: movsbq %r9b, %rax
|
|
; SSSE3-NEXT: movzbl (%rax,%r11), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm1
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3],xmm3[4],xmm15[4],xmm3[5],xmm15[5],xmm3[6],xmm15[6],xmm3[7],xmm15[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1],xmm0[2],xmm10[2],xmm0[3],xmm10[3],xmm0[4],xmm10[4],xmm0[5],xmm10[5],xmm0[6],xmm10[6],xmm0[7],xmm10[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm11[0],xmm7[1],xmm11[1],xmm7[2],xmm11[2],xmm7[3],xmm11[3],xmm7[4],xmm11[4],xmm7[5],xmm11[5],xmm7[6],xmm11[6],xmm7[7],xmm11[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1],xmm0[2],xmm7[2],xmm0[3],xmm7[3],xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm12[0],xmm2[1],xmm12[1],xmm2[2],xmm12[2],xmm2[3],xmm12[3],xmm2[4],xmm12[4],xmm2[5],xmm12[5],xmm2[6],xmm12[6],xmm2[7],xmm12[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm13[0],xmm6[1],xmm13[1],xmm6[2],xmm13[2],xmm6[3],xmm13[3],xmm6[4],xmm13[4],xmm6[5],xmm13[5],xmm6[6],xmm13[6],xmm6[7],xmm13[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm2[0],xmm6[1],xmm2[1],xmm6[2],xmm2[2],xmm6[3],xmm2[3],xmm6[4],xmm2[4],xmm6[5],xmm2[5],xmm6[6],xmm2[6],xmm6[7],xmm2[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm14[0],xmm5[1],xmm14[1],xmm5[2],xmm14[2],xmm5[3],xmm14[3],xmm5[4],xmm14[4],xmm5[5],xmm14[5],xmm5[6],xmm14[6],xmm5[7],xmm14[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
|
|
; 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: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1],xmm5[2],xmm6[2],xmm5[3],xmm6[3],xmm5[4],xmm6[4],xmm5[5],xmm6[5],xmm5[6],xmm6[6],xmm5[7],xmm6[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1],xmm0[2],xmm5[2],xmm0[3],xmm5[3],xmm0[4],xmm5[4],xmm0[5],xmm5[5],xmm0[6],xmm5[6],xmm0[7],xmm5[7]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; 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: movsbq %dil, %r15
|
|
; SSE41-NEXT: movsbq %sil, %r14
|
|
; SSE41-NEXT: movsbq %dl, %r11
|
|
; SSE41-NEXT: movsbq %cl, %r10
|
|
; SSE41-NEXT: movsbq %r8b, %r8
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movsbq %r9b, %r9
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r12
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r13
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %rbp
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %rbx
|
|
; SSE41-NEXT: leaq -{{[0-9]+}}(%rsp), %rax
|
|
; SSE41-NEXT: movzbl (%r15,%rax), %ecx
|
|
; SSE41-NEXT: movd %ecx, %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r15
|
|
; SSE41-NEXT: pinsrb $1, (%r14,%rax), %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r14
|
|
; SSE41-NEXT: pinsrb $2, (%r11,%rax), %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r11
|
|
; SSE41-NEXT: pinsrb $3, (%r10,%rax), %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %r10
|
|
; SSE41-NEXT: pinsrb $4, (%r8,%rax), %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %rcx
|
|
; SSE41-NEXT: pinsrb $5, (%r9,%rax), %xmm0
|
|
; SSE41-NEXT: movsbq {{[0-9]+}}(%rsp), %rdx
|
|
; SSE41-NEXT: movzbl (%r12,%rax), %esi
|
|
; SSE41-NEXT: movzbl (%r13,%rax), %edi
|
|
; SSE41-NEXT: movzbl (%rbp,%rax), %ebp
|
|
; SSE41-NEXT: movzbl (%rbx,%rax), %ebx
|
|
; SSE41-NEXT: movzbl (%r15,%rax), %r8d
|
|
; SSE41-NEXT: movzbl (%r14,%rax), %r9d
|
|
; SSE41-NEXT: movzbl (%r11,%rax), %r11d
|
|
; SSE41-NEXT: movzbl (%r10,%rax), %r10d
|
|
; SSE41-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE41-NEXT: movzbl (%rdx,%rax), %eax
|
|
; SSE41-NEXT: pinsrb $6, %esi, %xmm0
|
|
; SSE41-NEXT: pinsrb $7, %edi, %xmm0
|
|
; SSE41-NEXT: pinsrb $8, %ebp, %xmm0
|
|
; SSE41-NEXT: pinsrb $9, %ebx, %xmm0
|
|
; SSE41-NEXT: pinsrb $10, %r8d, %xmm0
|
|
; SSE41-NEXT: pinsrb $11, %r9d, %xmm0
|
|
; SSE41-NEXT: pinsrb $12, %r11d, %xmm0
|
|
; SSE41-NEXT: pinsrb $13, %r10d, %xmm0
|
|
; SSE41-NEXT: pinsrb $14, %ecx, %xmm0
|
|
; SSE41-NEXT: pinsrb $15, %eax, %xmm0
|
|
; 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
|
|
;
|
|
; AVX-LABEL: var_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: pushq %rbp
|
|
; AVX-NEXT: pushq %r15
|
|
; AVX-NEXT: pushq %r14
|
|
; AVX-NEXT: pushq %r13
|
|
; AVX-NEXT: pushq %r12
|
|
; AVX-NEXT: pushq %rbx
|
|
; AVX-NEXT: movsbq %dil, %r10
|
|
; AVX-NEXT: movsbq %sil, %r11
|
|
; AVX-NEXT: movsbq %dl, %r14
|
|
; AVX-NEXT: movsbq %cl, %r15
|
|
; AVX-NEXT: movsbq %r8b, %r8
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movsbq %r9b, %r9
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r12
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r13
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %rbp
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %rcx
|
|
; AVX-NEXT: leaq -{{[0-9]+}}(%rsp), %rdi
|
|
; AVX-NEXT: movzbl (%r10,%rdi), %eax
|
|
; AVX-NEXT: vmovd %eax, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r10
|
|
; AVX-NEXT: vpinsrb $1, (%r11,%rdi), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r11
|
|
; AVX-NEXT: vpinsrb $2, (%r14,%rdi), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r14
|
|
; AVX-NEXT: vpinsrb $3, (%r15,%rdi), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r15
|
|
; AVX-NEXT: vpinsrb $4, (%r8,%rdi), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %r8
|
|
; AVX-NEXT: vpinsrb $5, (%r9,%rdi), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq {{[0-9]+}}(%rsp), %rsi
|
|
; AVX-NEXT: movzbl (%r12,%rdi), %edx
|
|
; AVX-NEXT: movzbl (%r13,%rdi), %ebx
|
|
; AVX-NEXT: movzbl (%rbp,%rdi), %ebp
|
|
; AVX-NEXT: movzbl (%rcx,%rdi), %ecx
|
|
; AVX-NEXT: movzbl (%r10,%rdi), %eax
|
|
; AVX-NEXT: movzbl (%r11,%rdi), %r9d
|
|
; AVX-NEXT: movzbl (%r14,%rdi), %r10d
|
|
; AVX-NEXT: movzbl (%r15,%rdi), %r11d
|
|
; AVX-NEXT: movzbl (%r8,%rdi), %r8d
|
|
; AVX-NEXT: movzbl (%rsi,%rdi), %esi
|
|
; AVX-NEXT: vpinsrb $6, %edx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $7, %ebx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $8, %ebp, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $9, %ecx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $11, %r9d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $12, %r10d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $13, %r11d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $14, %r8d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $15, %esi, %xmm0, %xmm0
|
|
; AVX-NEXT: popq %rbx
|
|
; AVX-NEXT: popq %r12
|
|
; AVX-NEXT: popq %r13
|
|
; AVX-NEXT: popq %r14
|
|
; AVX-NEXT: popq %r15
|
|
; AVX-NEXT: popq %rbp
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <16 x i8> %x, i8 %i0
|
|
%x1 = extractelement <16 x i8> %x, i8 %i1
|
|
%x2 = extractelement <16 x i8> %x, i8 %i2
|
|
%x3 = extractelement <16 x i8> %x, i8 %i3
|
|
%x4 = extractelement <16 x i8> %x, i8 %i4
|
|
%x5 = extractelement <16 x i8> %x, i8 %i5
|
|
%x6 = extractelement <16 x i8> %x, i8 %i6
|
|
%x7 = extractelement <16 x i8> %x, i8 %i7
|
|
%x8 = extractelement <16 x i8> %x, i8 %i8
|
|
%x9 = extractelement <16 x i8> %x, i8 %i9
|
|
%x10 = extractelement <16 x i8> %x, i8 %i10
|
|
%x11 = extractelement <16 x i8> %x, i8 %i11
|
|
%x12 = extractelement <16 x i8> %x, i8 %i12
|
|
%x13 = extractelement <16 x i8> %x, i8 %i13
|
|
%x14 = extractelement <16 x i8> %x, i8 %i14
|
|
%x15 = extractelement <16 x i8> %x, i8 %i15
|
|
%r0 = insertelement <16 x i8> undef, i8 %x0 , i32 0
|
|
%r1 = insertelement <16 x i8> %r0 , i8 %x1 , i32 1
|
|
%r2 = insertelement <16 x i8> %r1 , i8 %x2 , i32 2
|
|
%r3 = insertelement <16 x i8> %r2 , i8 %x3 , i32 3
|
|
%r4 = insertelement <16 x i8> %r3 , i8 %x4 , i32 4
|
|
%r5 = insertelement <16 x i8> %r4 , i8 %x5 , i32 5
|
|
%r6 = insertelement <16 x i8> %r5 , i8 %x6 , i32 6
|
|
%r7 = insertelement <16 x i8> %r6 , i8 %x7 , i32 7
|
|
%r8 = insertelement <16 x i8> %r7 , i8 %x8 , i32 8
|
|
%r9 = insertelement <16 x i8> %r8 , i8 %x9 , i32 9
|
|
%r10 = insertelement <16 x i8> %r9 , i8 %x10, i32 10
|
|
%r11 = insertelement <16 x i8> %r10, i8 %x11, i32 11
|
|
%r12 = insertelement <16 x i8> %r11, i8 %x12, i32 12
|
|
%r13 = insertelement <16 x i8> %r12, i8 %x13, i32 13
|
|
%r14 = insertelement <16 x i8> %r13, i8 %x14, i32 14
|
|
%r15 = insertelement <16 x i8> %r14, i8 %x15, i32 15
|
|
ret <16 x i8> %r15
|
|
}
|
|
|
|
;
|
|
; Unary shuffle indices from memory
|
|
;
|
|
|
|
define <4 x i32> @mem_shuffle_v4i32_v4i32_xxxx_i32(<4 x i32> %x, i32* %i) nounwind {
|
|
; SSE2-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movslq (%rdi), %rax
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movslq 4(%rdi), %rcx
|
|
; SSE2-NEXT: movslq 8(%rdi), %rdx
|
|
; SSE2-NEXT: movslq 12(%rdi), %rsi
|
|
; SSE2-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
|
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movslq (%rdi), %rax
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movslq 4(%rdi), %rcx
|
|
; SSSE3-NEXT: movslq 8(%rdi), %rdx
|
|
; SSSE3-NEXT: movslq 12(%rdi), %rsi
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSSE3-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
|
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; SSE41: # BB#0:
|
|
; SSE41-NEXT: movslq (%rdi), %rax
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movslq 4(%rdi), %rcx
|
|
; SSE41-NEXT: movslq 8(%rdi), %rdx
|
|
; SSE41-NEXT: movslq 12(%rdi), %rsi
|
|
; SSE41-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE41-NEXT: pinsrd $1, -24(%rsp,%rcx,4), %xmm0
|
|
; SSE41-NEXT: pinsrd $2, -24(%rsp,%rdx,4), %xmm0
|
|
; SSE41-NEXT: pinsrd $3, -24(%rsp,%rsi,4), %xmm0
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: mem_shuffle_v4i32_v4i32_xxxx_i32:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: movslq (%rdi), %rax
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq 4(%rdi), %rcx
|
|
; AVX-NEXT: movslq 8(%rdi), %rdx
|
|
; AVX-NEXT: movslq 12(%rdi), %rsi
|
|
; AVX-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vpinsrd $1, -24(%rsp,%rcx,4), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrd $2, -24(%rsp,%rdx,4), %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrd $3, -24(%rsp,%rsi,4), %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%p0 = getelementptr inbounds i32, i32* %i, i64 0
|
|
%p1 = getelementptr inbounds i32, i32* %i, i64 1
|
|
%p2 = getelementptr inbounds i32, i32* %i, i64 2
|
|
%p3 = getelementptr inbounds i32, i32* %i, i64 3
|
|
%i0 = load i32, i32* %p0, align 4
|
|
%i1 = load i32, i32* %p1, align 4
|
|
%i2 = load i32, i32* %p2, align 4
|
|
%i3 = load i32, i32* %p3, align 4
|
|
%x0 = extractelement <4 x i32> %x, i32 %i0
|
|
%x1 = extractelement <4 x i32> %x, i32 %i1
|
|
%x2 = extractelement <4 x i32> %x, i32 %i2
|
|
%x3 = extractelement <4 x i32> %x, i32 %i3
|
|
%r0 = insertelement <4 x i32> undef, i32 %x0, i32 0
|
|
%r1 = insertelement <4 x i32> %r0, i32 %x1, i32 1
|
|
%r2 = insertelement <4 x i32> %r1, i32 %x2, i32 2
|
|
%r3 = insertelement <4 x i32> %r2, i32 %x3, i32 3
|
|
ret <4 x i32> %r3
|
|
}
|
|
|
|
define <16 x i8> @mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8(<16 x i8> %x, i8* %i) nounwind {
|
|
; SSE2-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movsbq (%rdi), %rcx
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: leaq -{{[0-9]+}}(%rsp), %rax
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm0
|
|
; SSE2-NEXT: movsbq 8(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm8
|
|
; SSE2-NEXT: movsbq 12(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm9
|
|
; SSE2-NEXT: movsbq 4(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: movsbq 14(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm10
|
|
; SSE2-NEXT: movsbq 6(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm5
|
|
; SSE2-NEXT: movsbq 10(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm11
|
|
; SSE2-NEXT: movsbq 2(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm7
|
|
; SSE2-NEXT: movsbq 15(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm12
|
|
; SSE2-NEXT: movsbq 7(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm2
|
|
; SSE2-NEXT: movsbq 11(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm13
|
|
; SSE2-NEXT: movsbq 3(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm6
|
|
; SSE2-NEXT: movsbq 13(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm14
|
|
; SSE2-NEXT: movsbq 5(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm4
|
|
; SSE2-NEXT: movsbq 9(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm15
|
|
; SSE2-NEXT: movsbq 1(%rdi), %rcx
|
|
; SSE2-NEXT: movzbl (%rcx,%rax), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm1
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3],xmm0[4],xmm8[4],xmm0[5],xmm8[5],xmm0[6],xmm8[6],xmm0[7],xmm8[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm10[0],xmm5[1],xmm10[1],xmm5[2],xmm10[2],xmm5[3],xmm10[3],xmm5[4],xmm10[4],xmm5[5],xmm10[5],xmm5[6],xmm10[6],xmm5[7],xmm10[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm11[0],xmm7[1],xmm11[1],xmm7[2],xmm11[2],xmm7[3],xmm11[3],xmm7[4],xmm11[4],xmm7[5],xmm11[5],xmm7[6],xmm11[6],xmm7[7],xmm11[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm5[0],xmm7[1],xmm5[1],xmm7[2],xmm5[2],xmm7[3],xmm5[3],xmm7[4],xmm5[4],xmm7[5],xmm5[5],xmm7[6],xmm5[6],xmm7[7],xmm5[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1],xmm0[2],xmm7[2],xmm0[3],xmm7[3],xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm12[0],xmm2[1],xmm12[1],xmm2[2],xmm12[2],xmm2[3],xmm12[3],xmm2[4],xmm12[4],xmm2[5],xmm12[5],xmm2[6],xmm12[6],xmm2[7],xmm12[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm13[0],xmm6[1],xmm13[1],xmm6[2],xmm13[2],xmm6[3],xmm13[3],xmm6[4],xmm13[4],xmm6[5],xmm13[5],xmm6[6],xmm13[6],xmm6[7],xmm13[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm2[0],xmm6[1],xmm2[1],xmm6[2],xmm2[2],xmm6[3],xmm2[3],xmm6[4],xmm2[4],xmm6[5],xmm2[5],xmm6[6],xmm2[6],xmm6[7],xmm2[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm14[0],xmm4[1],xmm14[1],xmm4[2],xmm14[2],xmm4[3],xmm14[3],xmm4[4],xmm14[4],xmm4[5],xmm14[5],xmm4[6],xmm14[6],xmm4[7],xmm14[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm15[0],xmm1[1],xmm15[1],xmm1[2],xmm15[2],xmm1[3],xmm15[3],xmm1[4],xmm15[4],xmm1[5],xmm15[5],xmm1[6],xmm15[6],xmm1[7],xmm15[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1],xmm1[2],xmm6[2],xmm1[3],xmm6[3],xmm1[4],xmm6[4],xmm1[5],xmm6[5],xmm1[6],xmm6[6],xmm1[7],xmm6[7]
|
|
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movsbq (%rdi), %rcx
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: leaq -{{[0-9]+}}(%rsp), %rax
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm0
|
|
; SSSE3-NEXT: movsbq 8(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm8
|
|
; SSSE3-NEXT: movsbq 12(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm9
|
|
; SSSE3-NEXT: movsbq 4(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm3
|
|
; SSSE3-NEXT: movsbq 14(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm10
|
|
; SSSE3-NEXT: movsbq 6(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm5
|
|
; SSSE3-NEXT: movsbq 10(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm11
|
|
; SSSE3-NEXT: movsbq 2(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm7
|
|
; SSSE3-NEXT: movsbq 15(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm12
|
|
; SSSE3-NEXT: movsbq 7(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm2
|
|
; SSSE3-NEXT: movsbq 11(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm13
|
|
; SSSE3-NEXT: movsbq 3(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm6
|
|
; SSSE3-NEXT: movsbq 13(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm14
|
|
; SSSE3-NEXT: movsbq 5(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm4
|
|
; SSSE3-NEXT: movsbq 9(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm15
|
|
; SSSE3-NEXT: movsbq 1(%rdi), %rcx
|
|
; SSSE3-NEXT: movzbl (%rcx,%rax), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm1
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3],xmm0[4],xmm8[4],xmm0[5],xmm8[5],xmm0[6],xmm8[6],xmm0[7],xmm8[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm10[0],xmm5[1],xmm10[1],xmm5[2],xmm10[2],xmm5[3],xmm10[3],xmm5[4],xmm10[4],xmm5[5],xmm10[5],xmm5[6],xmm10[6],xmm5[7],xmm10[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm11[0],xmm7[1],xmm11[1],xmm7[2],xmm11[2],xmm7[3],xmm11[3],xmm7[4],xmm11[4],xmm7[5],xmm11[5],xmm7[6],xmm11[6],xmm7[7],xmm11[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm5[0],xmm7[1],xmm5[1],xmm7[2],xmm5[2],xmm7[3],xmm5[3],xmm7[4],xmm5[4],xmm7[5],xmm5[5],xmm7[6],xmm5[6],xmm7[7],xmm5[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm7[0],xmm0[1],xmm7[1],xmm0[2],xmm7[2],xmm0[3],xmm7[3],xmm0[4],xmm7[4],xmm0[5],xmm7[5],xmm0[6],xmm7[6],xmm0[7],xmm7[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm12[0],xmm2[1],xmm12[1],xmm2[2],xmm12[2],xmm2[3],xmm12[3],xmm2[4],xmm12[4],xmm2[5],xmm12[5],xmm2[6],xmm12[6],xmm2[7],xmm12[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm13[0],xmm6[1],xmm13[1],xmm6[2],xmm13[2],xmm6[3],xmm13[3],xmm6[4],xmm13[4],xmm6[5],xmm13[5],xmm6[6],xmm13[6],xmm6[7],xmm13[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm2[0],xmm6[1],xmm2[1],xmm6[2],xmm2[2],xmm6[3],xmm2[3],xmm6[4],xmm2[4],xmm6[5],xmm2[5],xmm6[6],xmm2[6],xmm6[7],xmm2[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm14[0],xmm4[1],xmm14[1],xmm4[2],xmm14[2],xmm4[3],xmm14[3],xmm4[4],xmm14[4],xmm4[5],xmm14[5],xmm4[6],xmm14[6],xmm4[7],xmm14[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm15[0],xmm1[1],xmm15[1],xmm1[2],xmm15[2],xmm1[3],xmm15[3],xmm1[4],xmm15[4],xmm1[5],xmm15[5],xmm1[6],xmm15[6],xmm1[7],xmm15[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1],xmm1[2],xmm6[2],xmm1[3],xmm6[3],xmm1[4],xmm6[4],xmm1[5],xmm6[5],xmm1[6],xmm6[6],xmm1[7],xmm6[7]
|
|
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; 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: movsbq (%rdi), %rax
|
|
; SSE41-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movsbq 1(%rdi), %r15
|
|
; SSE41-NEXT: movsbq 2(%rdi), %r8
|
|
; SSE41-NEXT: movsbq 3(%rdi), %r9
|
|
; SSE41-NEXT: movsbq 4(%rdi), %r10
|
|
; SSE41-NEXT: movsbq 5(%rdi), %r11
|
|
; SSE41-NEXT: movsbq 6(%rdi), %r14
|
|
; SSE41-NEXT: movsbq 7(%rdi), %r12
|
|
; SSE41-NEXT: movsbq 8(%rdi), %r13
|
|
; SSE41-NEXT: movsbq 9(%rdi), %rdx
|
|
; SSE41-NEXT: movsbq 10(%rdi), %rcx
|
|
; SSE41-NEXT: movsbq 11(%rdi), %rsi
|
|
; SSE41-NEXT: movsbq 12(%rdi), %rbx
|
|
; SSE41-NEXT: leaq -{{[0-9]+}}(%rsp), %rbp
|
|
; SSE41-NEXT: movzbl (%rax,%rbp), %eax
|
|
; SSE41-NEXT: movd %eax, %xmm0
|
|
; SSE41-NEXT: movsbq 13(%rdi), %rax
|
|
; SSE41-NEXT: pinsrb $1, (%r15,%rbp), %xmm0
|
|
; SSE41-NEXT: movsbq 14(%rdi), %r15
|
|
; SSE41-NEXT: movsbq 15(%rdi), %rdi
|
|
; SSE41-NEXT: movzbl (%rdi,%rbp), %edi
|
|
; SSE41-NEXT: movzbl (%r15,%rbp), %r15d
|
|
; SSE41-NEXT: movzbl (%rax,%rbp), %eax
|
|
; SSE41-NEXT: movzbl (%rbx,%rbp), %ebx
|
|
; SSE41-NEXT: movzbl (%rsi,%rbp), %esi
|
|
; SSE41-NEXT: movzbl (%rcx,%rbp), %ecx
|
|
; SSE41-NEXT: movzbl (%rdx,%rbp), %edx
|
|
; SSE41-NEXT: movzbl (%r13,%rbp), %r13d
|
|
; SSE41-NEXT: movzbl (%r12,%rbp), %r12d
|
|
; SSE41-NEXT: movzbl (%r14,%rbp), %r14d
|
|
; SSE41-NEXT: movzbl (%r11,%rbp), %r11d
|
|
; SSE41-NEXT: movzbl (%r10,%rbp), %r10d
|
|
; SSE41-NEXT: movzbl (%r9,%rbp), %r9d
|
|
; SSE41-NEXT: movzbl (%r8,%rbp), %ebp
|
|
; SSE41-NEXT: pinsrb $2, %ebp, %xmm0
|
|
; SSE41-NEXT: pinsrb $3, %r9d, %xmm0
|
|
; SSE41-NEXT: pinsrb $4, %r10d, %xmm0
|
|
; SSE41-NEXT: pinsrb $5, %r11d, %xmm0
|
|
; SSE41-NEXT: pinsrb $6, %r14d, %xmm0
|
|
; SSE41-NEXT: pinsrb $7, %r12d, %xmm0
|
|
; SSE41-NEXT: pinsrb $8, %r13d, %xmm0
|
|
; SSE41-NEXT: pinsrb $9, %edx, %xmm0
|
|
; SSE41-NEXT: pinsrb $10, %ecx, %xmm0
|
|
; SSE41-NEXT: pinsrb $11, %esi, %xmm0
|
|
; SSE41-NEXT: pinsrb $12, %ebx, %xmm0
|
|
; SSE41-NEXT: pinsrb $13, %eax, %xmm0
|
|
; SSE41-NEXT: pinsrb $14, %r15d, %xmm0
|
|
; SSE41-NEXT: pinsrb $15, %edi, %xmm0
|
|
; 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
|
|
;
|
|
; AVX-LABEL: mem_shuffle_v16i8_v16i8_xxxxxxxxxxxxxxxx_i8:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: pushq %rbp
|
|
; AVX-NEXT: pushq %r15
|
|
; AVX-NEXT: pushq %r14
|
|
; AVX-NEXT: pushq %r13
|
|
; AVX-NEXT: pushq %r12
|
|
; AVX-NEXT: pushq %rbx
|
|
; AVX-NEXT: movsbq (%rdi), %rsi
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movsbq 1(%rdi), %r15
|
|
; AVX-NEXT: movsbq 2(%rdi), %r8
|
|
; AVX-NEXT: movsbq 3(%rdi), %r9
|
|
; AVX-NEXT: movsbq 4(%rdi), %r10
|
|
; AVX-NEXT: movsbq 5(%rdi), %r11
|
|
; AVX-NEXT: movsbq 6(%rdi), %r14
|
|
; AVX-NEXT: movsbq 7(%rdi), %r12
|
|
; AVX-NEXT: movsbq 8(%rdi), %r13
|
|
; AVX-NEXT: movsbq 9(%rdi), %rdx
|
|
; AVX-NEXT: movsbq 10(%rdi), %rax
|
|
; AVX-NEXT: movsbq 11(%rdi), %rcx
|
|
; AVX-NEXT: movsbq 12(%rdi), %rbx
|
|
; AVX-NEXT: leaq -{{[0-9]+}}(%rsp), %rbp
|
|
; AVX-NEXT: movzbl (%rsi,%rbp), %esi
|
|
; AVX-NEXT: vmovd %esi, %xmm0
|
|
; AVX-NEXT: movsbq 13(%rdi), %rsi
|
|
; AVX-NEXT: vpinsrb $1, (%r15,%rbp), %xmm0, %xmm0
|
|
; AVX-NEXT: movsbq 14(%rdi), %r15
|
|
; AVX-NEXT: movsbq 15(%rdi), %rdi
|
|
; AVX-NEXT: movzbl (%rdi,%rbp), %edi
|
|
; AVX-NEXT: movzbl (%r15,%rbp), %r15d
|
|
; AVX-NEXT: movzbl (%rsi,%rbp), %esi
|
|
; AVX-NEXT: movzbl (%rbx,%rbp), %ebx
|
|
; AVX-NEXT: movzbl (%rcx,%rbp), %ecx
|
|
; AVX-NEXT: movzbl (%rax,%rbp), %eax
|
|
; AVX-NEXT: movzbl (%rdx,%rbp), %edx
|
|
; AVX-NEXT: movzbl (%r13,%rbp), %r13d
|
|
; AVX-NEXT: movzbl (%r12,%rbp), %r12d
|
|
; AVX-NEXT: movzbl (%r14,%rbp), %r14d
|
|
; AVX-NEXT: movzbl (%r11,%rbp), %r11d
|
|
; AVX-NEXT: movzbl (%r10,%rbp), %r10d
|
|
; AVX-NEXT: movzbl (%r9,%rbp), %r9d
|
|
; AVX-NEXT: movzbl (%r8,%rbp), %ebp
|
|
; AVX-NEXT: vpinsrb $2, %ebp, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $3, %r9d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $4, %r10d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $5, %r11d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $6, %r14d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $7, %r12d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $8, %r13d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $9, %edx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $11, %ecx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $12, %ebx, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $13, %esi, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $14, %r15d, %xmm0, %xmm0
|
|
; AVX-NEXT: vpinsrb $15, %edi, %xmm0, %xmm0
|
|
; AVX-NEXT: popq %rbx
|
|
; AVX-NEXT: popq %r12
|
|
; AVX-NEXT: popq %r13
|
|
; AVX-NEXT: popq %r14
|
|
; AVX-NEXT: popq %r15
|
|
; AVX-NEXT: popq %rbp
|
|
; AVX-NEXT: retq
|
|
%p0 = getelementptr inbounds i8, i8* %i, i64 0
|
|
%p1 = getelementptr inbounds i8, i8* %i, i64 1
|
|
%p2 = getelementptr inbounds i8, i8* %i, i64 2
|
|
%p3 = getelementptr inbounds i8, i8* %i, i64 3
|
|
%p4 = getelementptr inbounds i8, i8* %i, i64 4
|
|
%p5 = getelementptr inbounds i8, i8* %i, i64 5
|
|
%p6 = getelementptr inbounds i8, i8* %i, i64 6
|
|
%p7 = getelementptr inbounds i8, i8* %i, i64 7
|
|
%p8 = getelementptr inbounds i8, i8* %i, i64 8
|
|
%p9 = getelementptr inbounds i8, i8* %i, i64 9
|
|
%p10 = getelementptr inbounds i8, i8* %i, i64 10
|
|
%p11 = getelementptr inbounds i8, i8* %i, i64 11
|
|
%p12 = getelementptr inbounds i8, i8* %i, i64 12
|
|
%p13 = getelementptr inbounds i8, i8* %i, i64 13
|
|
%p14 = getelementptr inbounds i8, i8* %i, i64 14
|
|
%p15 = getelementptr inbounds i8, i8* %i, i64 15
|
|
%i0 = load i8, i8* %p0 , align 4
|
|
%i1 = load i8, i8* %p1 , align 4
|
|
%i2 = load i8, i8* %p2 , align 4
|
|
%i3 = load i8, i8* %p3 , align 4
|
|
%i4 = load i8, i8* %p4 , align 4
|
|
%i5 = load i8, i8* %p5 , align 4
|
|
%i6 = load i8, i8* %p6 , align 4
|
|
%i7 = load i8, i8* %p7 , align 4
|
|
%i8 = load i8, i8* %p8 , align 4
|
|
%i9 = load i8, i8* %p9 , align 4
|
|
%i10 = load i8, i8* %p10, align 4
|
|
%i11 = load i8, i8* %p11, align 4
|
|
%i12 = load i8, i8* %p12, align 4
|
|
%i13 = load i8, i8* %p13, align 4
|
|
%i14 = load i8, i8* %p14, align 4
|
|
%i15 = load i8, i8* %p15, align 4
|
|
%x0 = extractelement <16 x i8> %x, i8 %i0
|
|
%x1 = extractelement <16 x i8> %x, i8 %i1
|
|
%x2 = extractelement <16 x i8> %x, i8 %i2
|
|
%x3 = extractelement <16 x i8> %x, i8 %i3
|
|
%x4 = extractelement <16 x i8> %x, i8 %i4
|
|
%x5 = extractelement <16 x i8> %x, i8 %i5
|
|
%x6 = extractelement <16 x i8> %x, i8 %i6
|
|
%x7 = extractelement <16 x i8> %x, i8 %i7
|
|
%x8 = extractelement <16 x i8> %x, i8 %i8
|
|
%x9 = extractelement <16 x i8> %x, i8 %i9
|
|
%x10 = extractelement <16 x i8> %x, i8 %i10
|
|
%x11 = extractelement <16 x i8> %x, i8 %i11
|
|
%x12 = extractelement <16 x i8> %x, i8 %i12
|
|
%x13 = extractelement <16 x i8> %x, i8 %i13
|
|
%x14 = extractelement <16 x i8> %x, i8 %i14
|
|
%x15 = extractelement <16 x i8> %x, i8 %i15
|
|
%r0 = insertelement <16 x i8> undef, i8 %x0 , i32 0
|
|
%r1 = insertelement <16 x i8> %r0 , i8 %x1 , i32 1
|
|
%r2 = insertelement <16 x i8> %r1 , i8 %x2 , i32 2
|
|
%r3 = insertelement <16 x i8> %r2 , i8 %x3 , i32 3
|
|
%r4 = insertelement <16 x i8> %r3 , i8 %x4 , i32 4
|
|
%r5 = insertelement <16 x i8> %r4 , i8 %x5 , i32 5
|
|
%r6 = insertelement <16 x i8> %r5 , i8 %x6 , i32 6
|
|
%r7 = insertelement <16 x i8> %r6 , i8 %x7 , i32 7
|
|
%r8 = insertelement <16 x i8> %r7 , i8 %x8 , i32 8
|
|
%r9 = insertelement <16 x i8> %r8 , i8 %x9 , i32 9
|
|
%r10 = insertelement <16 x i8> %r9 , i8 %x10, i32 10
|
|
%r11 = insertelement <16 x i8> %r10, i8 %x11, i32 11
|
|
%r12 = insertelement <16 x i8> %r11, i8 %x12, i32 12
|
|
%r13 = insertelement <16 x i8> %r12, i8 %x13, i32 13
|
|
%r14 = insertelement <16 x i8> %r13, i8 %x14, i32 14
|
|
%r15 = insertelement <16 x i8> %r14, i8 %x15, i32 15
|
|
ret <16 x i8> %r15
|
|
}
|
|
|
|
;
|
|
; Binary shuffle indices from registers
|
|
;
|
|
|
|
define <4 x float> @var_shuffle_v4f32_v4f32_x0yx_i32(<4 x float> %x, <4 x float> %y, i32 %i0, i32 %i1, i32 %i2, i32 %i3) nounwind {
|
|
; SSE-LABEL: var_shuffle_v4f32_v4f32_x0yx_i32:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movslq %edi, %rax
|
|
; SSE-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
|
|
; SSE-NEXT: movslq %edx, %rdx
|
|
; SSE-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE-NEXT: movslq %ecx, %rcx
|
|
; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; SSE-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: var_shuffle_v4f32_v4f32_x0yx_i32:
|
|
; AVX: # BB#0:
|
|
; AVX-NEXT: movslq %edi, %rax
|
|
; AVX-NEXT: vmovaps %xmm1, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq %edx, %rdx
|
|
; AVX-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX-NEXT: movslq %ecx, %rcx
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: vunpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
|
|
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; AVX-NEXT: retq
|
|
%x0 = extractelement <4 x float> %x, i32 %i0
|
|
%x1 = extractelement <4 x float> %x, i32 %i1
|
|
%y2 = extractelement <4 x float> %y, i32 %i2
|
|
%x3 = extractelement <4 x float> %x, i32 %i3
|
|
%r0 = insertelement <4 x float> undef, float %x0, i32 0
|
|
%r1 = insertelement <4 x float> %r0, float 0.0, i32 1
|
|
%r2 = insertelement <4 x float> %r1, float %y2, i32 2
|
|
%r3 = insertelement <4 x float> %r2, float %x3, i32 3
|
|
ret <4 x float> %r3
|
|
}
|
|
|
|
define <8 x i16> @var_shuffle_v8i16_v8i16_xyxyxy00_i16(<8 x i16> %x, <8 x i16> %y, i16 %i0, i16 %i1, i16 %i2, i16 %i3, i16 %i4, i16 %i5, i16 %i6, i16 %i7) nounwind {
|
|
; SSE2-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
|
|
; SSE2: # BB#0:
|
|
; SSE2-NEXT: movswq %di, %r10
|
|
; SSE2-NEXT: movswq %si, %rsi
|
|
; SSE2-NEXT: movswq %dx, %r11
|
|
; SSE2-NEXT: movswq %cx, %rcx
|
|
; SSE2-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movswq %r8w, %rdi
|
|
; SSE2-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
|
|
; SSE2-NEXT: movswq %r9w, %rax
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rsi,2), %esi
|
|
; SSE2-NEXT: xorl %edx, %edx
|
|
; SSE2-NEXT: movd %edx, %xmm0
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rcx,2), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm1
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSE2-NEXT: movd %esi, %xmm2
|
|
; SSE2-NEXT: movzwl -24(%rsp,%rax,2), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
|
|
; SSE2-NEXT: movzwl -40(%rsp,%r10,2), %eax
|
|
; SSE2-NEXT: movzwl -40(%rsp,%r11,2), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm1
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSE2-NEXT: movd %eax, %xmm0
|
|
; SSE2-NEXT: movzwl -40(%rsp,%rdi,2), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSSE3-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
|
|
; SSSE3: # BB#0:
|
|
; SSSE3-NEXT: movswq %di, %r10
|
|
; SSSE3-NEXT: movswq %si, %rsi
|
|
; SSSE3-NEXT: movswq %dx, %r11
|
|
; SSSE3-NEXT: movswq %cx, %rcx
|
|
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movswq %r8w, %rdi
|
|
; SSSE3-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
|
|
; SSSE3-NEXT: movswq %r9w, %rax
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rsi,2), %esi
|
|
; SSSE3-NEXT: xorl %edx, %edx
|
|
; SSSE3-NEXT: movd %edx, %xmm0
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rcx,2), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm1
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSSE3-NEXT: movd %esi, %xmm2
|
|
; SSSE3-NEXT: movzwl -24(%rsp,%rax,2), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm3
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
|
|
; SSSE3-NEXT: movzwl -40(%rsp,%r10,2), %eax
|
|
; SSSE3-NEXT: movzwl -40(%rsp,%r11,2), %ecx
|
|
; SSSE3-NEXT: movd %ecx, %xmm1
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
|
; SSSE3-NEXT: movd %eax, %xmm0
|
|
; SSSE3-NEXT: movzwl -40(%rsp,%rdi,2), %eax
|
|
; SSSE3-NEXT: movd %eax, %xmm3
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
|
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
|
; SSSE3-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
|
|
; SSE41: # BB#0:
|
|
; SSE41-NEXT: movswq %di, %rax
|
|
; SSE41-NEXT: movswq %si, %rsi
|
|
; SSE41-NEXT: movswq %dx, %rdx
|
|
; SSE41-NEXT: movswq %cx, %r10
|
|
; SSE41-NEXT: movdqa %xmm0, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movswq %r8w, %rdi
|
|
; SSE41-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
|
|
; SSE41-NEXT: movswq %r9w, %rcx
|
|
; SSE41-NEXT: movzwl -40(%rsp,%rax,2), %eax
|
|
; SSE41-NEXT: movd %eax, %xmm1
|
|
; SSE41-NEXT: pinsrw $1, -24(%rsp,%rsi,2), %xmm1
|
|
; SSE41-NEXT: pinsrw $2, -40(%rsp,%rdx,2), %xmm1
|
|
; SSE41-NEXT: pinsrw $3, -24(%rsp,%r10,2), %xmm1
|
|
; SSE41-NEXT: pinsrw $4, -40(%rsp,%rdi,2), %xmm1
|
|
; SSE41-NEXT: pinsrw $5, -24(%rsp,%rcx,2), %xmm1
|
|
; SSE41-NEXT: pxor %xmm0, %xmm0
|
|
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3,4,5],xmm0[6,7]
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
|
|
; AVX1: # BB#0:
|
|
; AVX1-NEXT: movswq %di, %r10
|
|
; AVX1-NEXT: movswq %si, %r11
|
|
; AVX1-NEXT: movswq %dx, %rdx
|
|
; AVX1-NEXT: movswq %cx, %rcx
|
|
; AVX1-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: movswq %r8w, %rdi
|
|
; AVX1-NEXT: vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
|
|
; AVX1-NEXT: movswq %r9w, %rax
|
|
; AVX1-NEXT: movzwl -40(%rsp,%r10,2), %esi
|
|
; AVX1-NEXT: vmovd %esi, %xmm0
|
|
; AVX1-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
|
|
; AVX1-NEXT: vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
|
|
; AVX1-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
|
|
; AVX1-NEXT: vpinsrw $4, -40(%rsp,%rdi,2), %xmm0, %xmm0
|
|
; AVX1-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
|
|
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: var_shuffle_v8i16_v8i16_xyxyxy00_i16:
|
|
; AVX2: # BB#0:
|
|
; AVX2-NEXT: movswq %di, %r10
|
|
; AVX2-NEXT: movswq %si, %r11
|
|
; AVX2-NEXT: movswq %dx, %rdx
|
|
; AVX2-NEXT: movswq %cx, %rcx
|
|
; AVX2-NEXT: vmovaps %xmm0, -{{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: movswq %r8w, %rdi
|
|
; AVX2-NEXT: vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
|
|
; AVX2-NEXT: movswq %r9w, %rax
|
|
; AVX2-NEXT: movzwl -40(%rsp,%r10,2), %esi
|
|
; AVX2-NEXT: vmovd %esi, %xmm0
|
|
; AVX2-NEXT: vpinsrw $1, -24(%rsp,%r11,2), %xmm0, %xmm0
|
|
; AVX2-NEXT: vpinsrw $2, -40(%rsp,%rdx,2), %xmm0, %xmm0
|
|
; AVX2-NEXT: vpinsrw $3, -24(%rsp,%rcx,2), %xmm0, %xmm0
|
|
; AVX2-NEXT: vpinsrw $4, -40(%rsp,%rdi,2), %xmm0, %xmm0
|
|
; AVX2-NEXT: vpinsrw $5, -24(%rsp,%rax,2), %xmm0, %xmm0
|
|
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
|
|
; AVX2-NEXT: retq
|
|
%x0 = extractelement <8 x i16> %x, i16 %i0
|
|
%y1 = extractelement <8 x i16> %y, i16 %i1
|
|
%x2 = extractelement <8 x i16> %x, i16 %i2
|
|
%y3 = extractelement <8 x i16> %y, i16 %i3
|
|
%x4 = extractelement <8 x i16> %x, i16 %i4
|
|
%y5 = extractelement <8 x i16> %y, i16 %i5
|
|
%x6 = extractelement <8 x i16> %x, i16 %i6
|
|
%x7 = extractelement <8 x i16> %x, i16 %i7
|
|
%r0 = insertelement <8 x i16> undef, i16 %x0, i32 0
|
|
%r1 = insertelement <8 x i16> %r0, i16 %y1, i32 1
|
|
%r2 = insertelement <8 x i16> %r1, i16 %x2, i32 2
|
|
%r3 = insertelement <8 x i16> %r2, i16 %y3, i32 3
|
|
%r4 = insertelement <8 x i16> %r3, i16 %x4, i32 4
|
|
%r5 = insertelement <8 x i16> %r4, i16 %y5, i32 5
|
|
%r6 = insertelement <8 x i16> %r5, i16 0, i32 6
|
|
%r7 = insertelement <8 x i16> %r6, i16 0, i32 7
|
|
ret <8 x i16> %r7
|
|
}
|