maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/vector-rotate-128.ll

2253 lines
89 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
; 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=+avx512f | FileCheck %s --check-prefixes=AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VLBW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefixes=XOP,XOPAVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefixes=XOP,XOPAVX2
; Just one 32-bit run to make sure we do reasonable things for i64 rotates.
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=X32-SSE,X32-SSE2
;
; Variable Rotates
;
define <2 x i64> @var_rotate_v2i64(<2 x i64> %a, <2 x i64> %b) nounwind {
; SSE2-LABEL: var_rotate_v2i64:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [64,64]
; SSE2-NEXT: psubq %xmm1, %xmm2
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: psllq %xmm1, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE2-NEXT: movdqa %xmm0, %xmm4
; SSE2-NEXT: psllq %xmm1, %xmm4
; SSE2-NEXT: movsd {{.*#+}} xmm4 = xmm3[0],xmm4[1]
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: psrlq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE2-NEXT: psrlq %xmm2, %xmm0
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE2-NEXT: orpd %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: var_rotate_v2i64:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [64,64]
; SSE41-NEXT: psubq %xmm1, %xmm2
; SSE41-NEXT: movdqa %xmm0, %xmm3
; SSE41-NEXT: psllq %xmm1, %xmm3
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-NEXT: movdqa %xmm0, %xmm4
; SSE41-NEXT: psllq %xmm1, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm4 = xmm3[0,1,2,3],xmm4[4,5,6,7]
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psrlq %xmm2, %xmm1
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE41-NEXT: psrlq %xmm2, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE41-NEXT: por %xmm4, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: var_rotate_v2i64:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [64,64]
; AVX1-NEXT: vpsubq %xmm1, %xmm2, %xmm2
; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm3
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm3[0,1,2,3],xmm1[4,5,6,7]
; AVX1-NEXT: vpsrlq %xmm2, %xmm0, %xmm3
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; AVX1-NEXT: vpsrlq %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm3[0,1,2,3],xmm0[4,5,6,7]
; AVX1-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_rotate_v2i64:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [64,64]
; AVX2-NEXT: vpsubq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsllvq %xmm1, %xmm0, %xmm1
; AVX2-NEXT: vpsrlvq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: var_rotate_v2i64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: var_rotate_v2i64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolvq %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: var_rotate_v2i64:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: var_rotate_v2i64:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolvq %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: var_rotate_v2i64:
; XOP: # %bb.0:
; XOP-NEXT: vprotq %xmm1, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: var_rotate_v2i64:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa {{.*#+}} xmm2 = [64,0,64,0]
; X32-SSE-NEXT: psubq %xmm1, %xmm2
; X32-SSE-NEXT: movdqa %xmm0, %xmm3
; X32-SSE-NEXT: psllq %xmm1, %xmm3
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; X32-SSE-NEXT: movdqa %xmm0, %xmm4
; X32-SSE-NEXT: psllq %xmm1, %xmm4
; X32-SSE-NEXT: movsd {{.*#+}} xmm4 = xmm3[0],xmm4[1]
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlq %xmm2, %xmm1
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; X32-SSE-NEXT: psrlq %xmm2, %xmm0
; X32-SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; X32-SSE-NEXT: orpd %xmm4, %xmm0
; X32-SSE-NEXT: retl
%b64 = sub <2 x i64> <i64 64, i64 64>, %b
%shl = shl <2 x i64> %a, %b
%lshr = lshr <2 x i64> %a, %b64
%or = or <2 x i64> %shl, %lshr
ret <2 x i64> %or
}
define <4 x i32> @var_rotate_v4i32(<4 x i32> %a, <4 x i32> %b) nounwind {
; SSE2-LABEL: var_rotate_v4i32:
; SSE2: # %bb.0:
; SSE2-NEXT: pslld $23, %xmm1
; SSE2-NEXT: paddd {{.*}}(%rip), %xmm1
; SSE2-NEXT: cvttps2dq %xmm1, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; 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: por %xmm3, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: var_rotate_v4i32:
; SSE41: # %bb.0:
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE41-NEXT: pslld $23, %xmm1
; SSE41-NEXT: paddd {{.*}}(%rip), %xmm1
; SSE41-NEXT: cvttps2dq %xmm1, %xmm1
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; SSE41-NEXT: pmuludq %xmm2, %xmm3
; SSE41-NEXT: pmuludq %xmm1, %xmm0
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm3[2,3],xmm1[4,5],xmm3[6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,0,2,2]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; SSE41-NEXT: por %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: var_rotate_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; AVX1-NEXT: vpslld $23, %xmm1, %xmm1
; AVX1-NEXT: vpaddd {{.*}}(%rip), %xmm1, %xmm1
; AVX1-NEXT: vcvttps2dq %xmm1, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; AVX1-NEXT: vpmuludq %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,0,2,2]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_rotate_v4i32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsllvd %xmm1, %xmm0, %xmm2
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm3 = [32,32,32,32]
; AVX2-NEXT: vpsubd %xmm1, %xmm3, %xmm1
; AVX2-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: var_rotate_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: var_rotate_v4i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolvd %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: var_rotate_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: var_rotate_v4i32:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolvd %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: var_rotate_v4i32:
; XOP: # %bb.0:
; XOP-NEXT: vprotd %xmm1, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: var_rotate_v4i32:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: pslld $23, %xmm1
; X32-SSE-NEXT: paddd {{\.LCPI.*}}, %xmm1
; X32-SSE-NEXT: cvttps2dq %xmm1, %xmm1
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; X32-SSE-NEXT: pmuludq %xmm1, %xmm0
; X32-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; X32-SSE-NEXT: pmuludq %xmm2, %xmm1
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
; X32-SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X32-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X32-SSE-NEXT: por %xmm3, %xmm0
; X32-SSE-NEXT: retl
%b32 = sub <4 x i32> <i32 32, i32 32, i32 32, i32 32>, %b
%shl = shl <4 x i32> %a, %b
%lshr = lshr <4 x i32> %a, %b32
%or = or <4 x i32> %shl, %lshr
ret <4 x i32> %or
}
define <8 x i16> @var_rotate_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
; SSE2-LABEL: var_rotate_v8i16:
; SSE2: # %bb.0:
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; SSE2-NEXT: pslld $23, %xmm3
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [1065353216,1065353216,1065353216,1065353216]
; SSE2-NEXT: paddd %xmm4, %xmm3
; SSE2-NEXT: cvttps2dq %xmm3, %xmm3
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; SSE2-NEXT: pslld $23, %xmm1
; SSE2-NEXT: paddd %xmm4, %xmm1
; SSE2-NEXT: cvttps2dq %xmm1, %xmm1
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: pmulhuw %xmm1, %xmm2
; SSE2-NEXT: pmullw %xmm1, %xmm0
; SSE2-NEXT: por %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: var_rotate_v8i16:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm2, %xmm2
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm3 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
; SSE41-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE41-NEXT: pslld $23, %xmm1
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [1065353216,1065353216,1065353216,1065353216]
; SSE41-NEXT: paddd %xmm2, %xmm1
; SSE41-NEXT: cvttps2dq %xmm1, %xmm1
; SSE41-NEXT: pslld $23, %xmm3
; SSE41-NEXT: paddd %xmm2, %xmm3
; SSE41-NEXT: cvttps2dq %xmm3, %xmm2
; SSE41-NEXT: packusdw %xmm1, %xmm2
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: pmulhuw %xmm2, %xmm1
; SSE41-NEXT: pmullw %xmm2, %xmm0
; SSE41-NEXT: por %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: var_rotate_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm2 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; AVX1-NEXT: vpslld $23, %xmm2, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [1065353216,1065353216,1065353216,1065353216]
; AVX1-NEXT: vpaddd %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vcvttps2dq %xmm2, %xmm2
; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
; AVX1-NEXT: vpslld $23, %xmm1, %xmm1
; AVX1-NEXT: vpaddd %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vcvttps2dq %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpmulhuw %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpor %xmm2, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_rotate_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} 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
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpsllvd %ymm2, %ymm0, %ymm2
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
; AVX2-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm4 = [16,16,16,16,16,16,16,16]
; AVX2-NEXT: vpsubw %xmm1, %xmm4, %xmm1
; AVX2-NEXT: vpmovzxwd {{.*#+}} 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
; AVX2-NEXT: vpsrlvd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: var_rotate_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovzxwd {{.*#+}} 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
; AVX512F-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512F-NEXT: vpsllvd %ymm2, %ymm0, %ymm2
; AVX512F-NEXT: vpmovdw %zmm2, %ymm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512F-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512F-NEXT: vpmovzxwd {{.*#+}} 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
; AVX512F-NEXT: vpsrlvd %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: var_rotate_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} 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
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512VL-NEXT: vpsllvd %ymm2, %ymm0, %ymm2
; AVX512VL-NEXT: vpmovdw %ymm2, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512VL-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} 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
; AVX512VL-NEXT: vpsrlvd %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: var_rotate_v8i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vpsllvw %zmm1, %zmm0, %zmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512BW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512BW-NEXT: vpsrlvw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: var_rotate_v8i16:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpsllvw %xmm1, %xmm0, %xmm2
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512VLBW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512VLBW-NEXT: vpsrlvw %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: var_rotate_v8i16:
; XOP: # %bb.0:
; XOP-NEXT: vprotw %xmm1, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: var_rotate_v8i16:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: pxor %xmm2, %xmm2
; X32-SSE-NEXT: movdqa %xmm1, %xmm3
; X32-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
; X32-SSE-NEXT: pslld $23, %xmm3
; X32-SSE-NEXT: movdqa {{.*#+}} xmm4 = [1065353216,1065353216,1065353216,1065353216]
; X32-SSE-NEXT: paddd %xmm4, %xmm3
; X32-SSE-NEXT: cvttps2dq %xmm3, %xmm3
; X32-SSE-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
; X32-SSE-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,6,6,7]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; X32-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; X32-SSE-NEXT: pslld $23, %xmm1
; X32-SSE-NEXT: paddd %xmm4, %xmm1
; X32-SSE-NEXT: cvttps2dq %xmm1, %xmm1
; X32-SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; X32-SSE-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X32-SSE-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: pmulhuw %xmm1, %xmm2
; X32-SSE-NEXT: pmullw %xmm1, %xmm0
; X32-SSE-NEXT: por %xmm2, %xmm0
; X32-SSE-NEXT: retl
%b16 = sub <8 x i16> <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>, %b
%shl = shl <8 x i16> %a, %b
%lshr = lshr <8 x i16> %a, %b16
%or = or <8 x i16> %shl, %lshr
ret <8 x i16> %or
}
define <16 x i8> @var_rotate_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
; SSE2-LABEL: var_rotate_v16i8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: psllw $5, %xmm1
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm3, %xmm3
; SSE2-NEXT: pcmpgtb %xmm1, %xmm3
; SSE2-NEXT: movdqa %xmm2, %xmm4
; SSE2-NEXT: psrlw $4, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: movdqa %xmm2, %xmm5
; SSE2-NEXT: psllw $4, %xmm5
; SSE2-NEXT: pand {{.*}}(%rip), %xmm5
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pand %xmm3, %xmm5
; SSE2-NEXT: pandn %xmm2, %xmm3
; SSE2-NEXT: por %xmm5, %xmm3
; SSE2-NEXT: movdqa %xmm3, %xmm2
; SSE2-NEXT: psrlw $6, %xmm2
; SSE2-NEXT: pand {{.*}}(%rip), %xmm2
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: psllw $2, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: por %xmm2, %xmm4
; SSE2-NEXT: paddb %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pcmpgtb %xmm1, %xmm2
; SSE2-NEXT: pand %xmm2, %xmm4
; SSE2-NEXT: pandn %xmm3, %xmm2
; SSE2-NEXT: por %xmm4, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm3
; SSE2-NEXT: paddb %xmm2, %xmm3
; SSE2-NEXT: movdqa %xmm2, %xmm4
; SSE2-NEXT: psrlw $7, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: paddb %xmm1, %xmm1
; SSE2-NEXT: pcmpgtb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm2, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: var_rotate_v16i8:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa %xmm1, %xmm2
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psrlw $4, %xmm0
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psllw $4, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: psllw $5, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: psrlw $6, %xmm0
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psllw $2, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: paddb %xmm2, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: paddb %xmm1, %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psrlw $7, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: paddb %xmm2, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: var_rotate_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: var_rotate_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512F-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512F-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX512F-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: var_rotate_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512VL-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512VL-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512VL-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512VL-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX512VL-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: var_rotate_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-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
; AVX512BW-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
; AVX512BW-NEXT: vpsllvw %zmm2, %zmm0, %zmm2
; AVX512BW-NEXT: vpmovwb %zmm2, %ymm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
; AVX512BW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
; AVX512BW-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
; AVX512BW-NEXT: vpsrlvw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: var_rotate_v16i8:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-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
; AVX512VLBW-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
; AVX512VLBW-NEXT: vpsllvw %ymm2, %ymm0, %ymm2
; AVX512VLBW-NEXT: vpmovwb %ymm2, %xmm2
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
; AVX512VLBW-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
; AVX512VLBW-NEXT: vpsrlvw %ymm1, %ymm0, %ymm0
; AVX512VLBW-NEXT: vpmovwb %ymm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VLBW-NEXT: vzeroupper
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: var_rotate_v16i8:
; XOP: # %bb.0:
; XOP-NEXT: vprotb %xmm1, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: var_rotate_v16i8:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: psllw $5, %xmm1
; X32-SSE-NEXT: pxor %xmm0, %xmm0
; X32-SSE-NEXT: pxor %xmm3, %xmm3
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm3
; X32-SSE-NEXT: movdqa %xmm2, %xmm4
; X32-SSE-NEXT: psrlw $4, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: movdqa %xmm2, %xmm5
; X32-SSE-NEXT: psllw $4, %xmm5
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm5
; X32-SSE-NEXT: por %xmm4, %xmm5
; X32-SSE-NEXT: pand %xmm3, %xmm5
; X32-SSE-NEXT: pandn %xmm2, %xmm3
; X32-SSE-NEXT: por %xmm5, %xmm3
; X32-SSE-NEXT: movdqa %xmm3, %xmm2
; X32-SSE-NEXT: psrlw $6, %xmm2
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm2
; X32-SSE-NEXT: movdqa %xmm3, %xmm4
; X32-SSE-NEXT: psllw $2, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: por %xmm2, %xmm4
; X32-SSE-NEXT: paddb %xmm1, %xmm1
; X32-SSE-NEXT: pxor %xmm2, %xmm2
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm2
; X32-SSE-NEXT: pand %xmm2, %xmm4
; X32-SSE-NEXT: pandn %xmm3, %xmm2
; X32-SSE-NEXT: por %xmm4, %xmm2
; X32-SSE-NEXT: movdqa %xmm2, %xmm3
; X32-SSE-NEXT: paddb %xmm2, %xmm3
; X32-SSE-NEXT: movdqa %xmm2, %xmm4
; X32-SSE-NEXT: psrlw $7, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: por %xmm3, %xmm4
; X32-SSE-NEXT: paddb %xmm1, %xmm1
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm0
; X32-SSE-NEXT: pand %xmm0, %xmm4
; X32-SSE-NEXT: pandn %xmm2, %xmm0
; X32-SSE-NEXT: por %xmm4, %xmm0
; X32-SSE-NEXT: retl
%b8 = sub <16 x i8> <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>, %b
%shl = shl <16 x i8> %a, %b
%lshr = lshr <16 x i8> %a, %b8
%or = or <16 x i8> %shl, %lshr
ret <16 x i8> %or
}
;
; Uniform Variable Rotates
;
define <2 x i64> @splatvar_rotate_v2i64(<2 x i64> %a, <2 x i64> %b) nounwind {
; SSE-LABEL: splatvar_rotate_v2i64:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[0,1,0,1]
; SSE-NEXT: movdqa {{.*#+}} xmm3 = [64,64]
; SSE-NEXT: psubq %xmm2, %xmm3
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: psllq %xmm1, %xmm2
; SSE-NEXT: psrlq %xmm3, %xmm0
; SSE-NEXT: por %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: splatvar_rotate_v2i64:
; AVX1: # %bb.0:
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[0,1,0,1]
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [64,64]
; AVX1-NEXT: vpsubq %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsllq %xmm1, %xmm0, %xmm1
; AVX1-NEXT: vpsrlq %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splatvar_rotate_v2i64:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastq %xmm1, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [64,64]
; AVX2-NEXT: vpsubq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq %xmm1, %xmm0, %xmm1
; AVX2-NEXT: vpsrlvq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: splatvar_rotate_v2i64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vpbroadcastq %xmm1, %xmm1
; AVX512F-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatvar_rotate_v2i64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpbroadcastq %xmm1, %xmm1
; AVX512VL-NEXT: vprolvq %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatvar_rotate_v2i64:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vpbroadcastq %xmm1, %xmm1
; AVX512BW-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatvar_rotate_v2i64:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpbroadcastq %xmm1, %xmm1
; AVX512VLBW-NEXT: vprolvq %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOPAVX1-LABEL: splatvar_rotate_v2i64:
; XOPAVX1: # %bb.0:
; XOPAVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,1]
; XOPAVX1-NEXT: vprotq %xmm1, %xmm0, %xmm0
; XOPAVX1-NEXT: retq
;
; XOPAVX2-LABEL: splatvar_rotate_v2i64:
; XOPAVX2: # %bb.0:
; XOPAVX2-NEXT: vpbroadcastq %xmm1, %xmm1
; XOPAVX2-NEXT: vprotq %xmm1, %xmm0, %xmm0
; XOPAVX2-NEXT: retq
;
; X32-SSE-LABEL: splatvar_rotate_v2i64:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[0,1,0,1]
; X32-SSE-NEXT: movdqa {{.*#+}} xmm3 = [64,0,64,0]
; X32-SSE-NEXT: psubq %xmm2, %xmm3
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: psllq %xmm1, %xmm2
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlq %xmm3, %xmm1
; X32-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,0,1]
; X32-SSE-NEXT: psrlq %xmm3, %xmm0
; X32-SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; X32-SSE-NEXT: orpd %xmm2, %xmm0
; X32-SSE-NEXT: retl
%splat = shufflevector <2 x i64> %b, <2 x i64> undef, <2 x i32> zeroinitializer
%splat64 = sub <2 x i64> <i64 64, i64 64>, %splat
%shl = shl <2 x i64> %a, %splat
%lshr = lshr <2 x i64> %a, %splat64
%or = or <2 x i64> %shl, %lshr
ret <2 x i64> %or
}
define <4 x i32> @splatvar_rotate_v4i32(<4 x i32> %a, <4 x i32> %b) nounwind {
; SSE2-LABEL: splatvar_rotate_v4i32:
; SSE2: # %bb.0:
; SSE2-NEXT: xorps %xmm2, %xmm2
; SSE2-NEXT: xorps %xmm3, %xmm3
; SSE2-NEXT: movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; SSE2-NEXT: movdqa %xmm0, %xmm4
; SSE2-NEXT: pslld %xmm3, %xmm4
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [32,32,32,32]
; SSE2-NEXT: psubd %xmm1, %xmm3
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm3[0],xmm2[1,2,3]
; SSE2-NEXT: psrld %xmm2, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: splatvar_rotate_v4i32:
; SSE41: # %bb.0:
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; SSE41-NEXT: movdqa %xmm0, %xmm3
; SSE41-NEXT: pslld %xmm2, %xmm3
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [32,32,32,32]
; SSE41-NEXT: psubd %xmm1, %xmm2
; SSE41-NEXT: pmovzxdq {{.*#+}} xmm1 = xmm2[0],zero,xmm2[1],zero
; SSE41-NEXT: psrld %xmm1, %xmm0
; SSE41-NEXT: por %xmm3, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: splatvar_rotate_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; AVX1-NEXT: vpslld %xmm2, %xmm0, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [32,32,32,32]
; AVX1-NEXT: vpsubd %xmm1, %xmm3, %xmm1
; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
; AVX1-NEXT: vpsrld %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splatvar_rotate_v4i32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm1[0],zero,xmm1[1],zero
; AVX2-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX2-NEXT: vpslld %xmm2, %xmm0, %xmm2
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm3 = [32,32,32,32]
; AVX2-NEXT: vpsubd %xmm1, %xmm3, %xmm1
; AVX2-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: splatvar_rotate_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512F-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatvar_rotate_v4i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512VL-NEXT: vprolvd %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatvar_rotate_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512BW-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatvar_rotate_v4i32:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512VLBW-NEXT: vprolvd %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOPAVX1-LABEL: splatvar_rotate_v4i32:
; XOPAVX1: # %bb.0:
; XOPAVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; XOPAVX1-NEXT: vprotd %xmm1, %xmm0, %xmm0
; XOPAVX1-NEXT: retq
;
; XOPAVX2-LABEL: splatvar_rotate_v4i32:
; XOPAVX2: # %bb.0:
; XOPAVX2-NEXT: vpbroadcastd %xmm1, %xmm1
; XOPAVX2-NEXT: vprotd %xmm1, %xmm0, %xmm0
; XOPAVX2-NEXT: retq
;
; X32-SSE-LABEL: splatvar_rotate_v4i32:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: xorps %xmm2, %xmm2
; X32-SSE-NEXT: xorps %xmm3, %xmm3
; X32-SSE-NEXT: movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; X32-SSE-NEXT: movdqa %xmm0, %xmm4
; X32-SSE-NEXT: pslld %xmm3, %xmm4
; X32-SSE-NEXT: movdqa {{.*#+}} xmm3 = [32,32,32,32]
; X32-SSE-NEXT: psubd %xmm1, %xmm3
; X32-SSE-NEXT: movss {{.*#+}} xmm2 = xmm3[0],xmm2[1,2,3]
; X32-SSE-NEXT: psrld %xmm2, %xmm0
; X32-SSE-NEXT: por %xmm4, %xmm0
; X32-SSE-NEXT: retl
%splat = shufflevector <4 x i32> %b, <4 x i32> undef, <4 x i32> zeroinitializer
%splat32 = sub <4 x i32> <i32 32, i32 32, i32 32, i32 32>, %splat
%shl = shl <4 x i32> %a, %splat
%lshr = lshr <4 x i32> %a, %splat32
%or = or <4 x i32> %shl, %lshr
ret <4 x i32> %or
}
define <8 x i16> @splatvar_rotate_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
; SSE2-LABEL: splatvar_rotate_v8i16:
; SSE2: # %bb.0:
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm1[0,0,2,3,4,5,6,7]
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: psllw %xmm1, %xmm3
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16]
; SSE2-NEXT: psubw %xmm2, %xmm1
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: psrlw %xmm1, %xmm0
; SSE2-NEXT: por %xmm3, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: splatvar_rotate_v8i16:
; SSE41: # %bb.0:
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; SSE41-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; SSE41-NEXT: movdqa %xmm0, %xmm3
; SSE41-NEXT: psllw %xmm2, %xmm3
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [16,16,16,16,16,16,16,16]
; SSE41-NEXT: psubw %xmm1, %xmm2
; SSE41-NEXT: pmovzxwq {{.*#+}} xmm1 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero
; SSE41-NEXT: psrlw %xmm1, %xmm0
; SSE41-NEXT: por %xmm3, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: splatvar_rotate_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; AVX1-NEXT: vpsllw %xmm2, %xmm0, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX1-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX1-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX1-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splatvar_rotate_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX2-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX2-NEXT: vpsllw %xmm2, %xmm0, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX2-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX2-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX2-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: splatvar_rotate_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512F-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX512F-NEXT: vpsllw %xmm2, %xmm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512F-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512F-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512F-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatvar_rotate_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512VL-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX512VL-NEXT: vpsllw %xmm2, %xmm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512VL-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512VL-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatvar_rotate_v8i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512BW-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512BW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512BW-NEXT: vpsrlvw %zmm1, %zmm0, %zmm1
; AVX512BW-NEXT: vpsllw %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatvar_rotate_v8i16:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpmovzxwq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX512VLBW-NEXT: vpbroadcastw %xmm1, %xmm1
; AVX512VLBW-NEXT: vpsllw %xmm2, %xmm0, %xmm2
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [16,16,16,16,16,16,16,16]
; AVX512VLBW-NEXT: vpsubw %xmm1, %xmm3, %xmm1
; AVX512VLBW-NEXT: vpsrlvw %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOPAVX1-LABEL: splatvar_rotate_v8i16:
; XOPAVX1: # %bb.0:
; XOPAVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,0,2,3,4,5,6,7]
; XOPAVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
; XOPAVX1-NEXT: vprotw %xmm1, %xmm0, %xmm0
; XOPAVX1-NEXT: retq
;
; XOPAVX2-LABEL: splatvar_rotate_v8i16:
; XOPAVX2: # %bb.0:
; XOPAVX2-NEXT: vpbroadcastw %xmm1, %xmm1
; XOPAVX2-NEXT: vprotw %xmm1, %xmm0, %xmm0
; XOPAVX2-NEXT: retq
;
; X32-SSE-LABEL: splatvar_rotate_v8i16:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: pshuflw {{.*#+}} xmm2 = xmm1[0,0,2,3,4,5,6,7]
; X32-SSE-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; X32-SSE-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
; X32-SSE-NEXT: movdqa %xmm0, %xmm3
; X32-SSE-NEXT: psllw %xmm1, %xmm3
; X32-SSE-NEXT: movdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16]
; X32-SSE-NEXT: psubw %xmm2, %xmm1
; X32-SSE-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; X32-SSE-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; X32-SSE-NEXT: psrlw %xmm1, %xmm0
; X32-SSE-NEXT: por %xmm3, %xmm0
; X32-SSE-NEXT: retl
%splat = shufflevector <8 x i16> %b, <8 x i16> undef, <8 x i32> zeroinitializer
%splat16 = sub <8 x i16> <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>, %splat
%shl = shl <8 x i16> %a, %splat
%lshr = lshr <8 x i16> %a, %splat16
%or = or <8 x i16> %shl, %lshr
ret <8 x i16> %or
}
define <16 x i8> @splatvar_rotate_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
; SSE2-LABEL: splatvar_rotate_v16i8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm1[0,0,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: psrlw $4, %xmm0
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: movdqa %xmm2, %xmm3
; SSE2-NEXT: psllw $4, %xmm3
; SSE2-NEXT: pand {{.*}}(%rip), %xmm3
; SSE2-NEXT: por %xmm0, %xmm3
; SSE2-NEXT: psllw $5, %xmm1
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: pcmpgtb %xmm1, %xmm4
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pandn %xmm2, %xmm4
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: movdqa %xmm4, %xmm2
; SSE2-NEXT: psrlw $6, %xmm2
; SSE2-NEXT: pand {{.*}}(%rip), %xmm2
; SSE2-NEXT: movdqa %xmm4, %xmm3
; SSE2-NEXT: psllw $2, %xmm3
; SSE2-NEXT: pand {{.*}}(%rip), %xmm3
; SSE2-NEXT: por %xmm2, %xmm3
; SSE2-NEXT: paddb %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pcmpgtb %xmm1, %xmm2
; SSE2-NEXT: pand %xmm2, %xmm3
; SSE2-NEXT: pandn %xmm4, %xmm2
; SSE2-NEXT: por %xmm3, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm3
; SSE2-NEXT: paddb %xmm2, %xmm3
; SSE2-NEXT: movdqa %xmm2, %xmm4
; SSE2-NEXT: psrlw $7, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: paddb %xmm1, %xmm1
; SSE2-NEXT: pcmpgtb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm2, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: splatvar_rotate_v16i8:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa %xmm1, %xmm2
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: pxor %xmm0, %xmm0
; SSE41-NEXT: pshufb %xmm0, %xmm2
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: psrlw $4, %xmm0
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psllw $4, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: psllw $5, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: psrlw $6, %xmm0
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psllw $2, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: paddb %xmm2, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: paddb %xmm1, %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psrlw $7, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm0, %xmm3
; SSE41-NEXT: paddb %xmm2, %xmm2
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: splatvar_rotate_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX1-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX1-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX1-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX1-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX1-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX1-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX1-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splatvar_rotate_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX2-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX2-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX2-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX2-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX2-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX2-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX2-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX2-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: splatvar_rotate_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX512F-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512F-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512F-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX512F-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatvar_rotate_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX512VL-NEXT: vpsrlw $4, %xmm0, %xmm2
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512VL-NEXT: vpsllw $4, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512VL-NEXT: vpsllw $5, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpsrlw $6, %xmm0, %xmm2
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512VL-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm2, %xmm3, %xmm2
; AVX512VL-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpaddb %xmm0, %xmm0, %xmm2
; AVX512VL-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpaddb %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatvar_rotate_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX512BW-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
; AVX512BW-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
; AVX512BW-NEXT: vpsllvw %zmm2, %zmm0, %zmm2
; AVX512BW-NEXT: vpmovwb %zmm2, %ymm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
; AVX512BW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
; AVX512BW-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
; AVX512BW-NEXT: vpsrlvw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatvar_rotate_v16i8:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %xmm1
; AVX512VLBW-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
; AVX512VLBW-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
; AVX512VLBW-NEXT: vpsllvw %ymm2, %ymm0, %ymm2
; AVX512VLBW-NEXT: vpmovwb %ymm2, %xmm2
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm3, %xmm1
; AVX512VLBW-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
; AVX512VLBW-NEXT: vpsrlvw %ymm1, %ymm0, %ymm0
; AVX512VLBW-NEXT: vpmovwb %ymm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm0, %xmm2, %xmm0
; AVX512VLBW-NEXT: vzeroupper
; AVX512VLBW-NEXT: retq
;
; XOPAVX1-LABEL: splatvar_rotate_v16i8:
; XOPAVX1: # %bb.0:
; XOPAVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; XOPAVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; XOPAVX1-NEXT: vprotb %xmm1, %xmm0, %xmm0
; XOPAVX1-NEXT: retq
;
; XOPAVX2-LABEL: splatvar_rotate_v16i8:
; XOPAVX2: # %bb.0:
; XOPAVX2-NEXT: vpbroadcastb %xmm1, %xmm1
; XOPAVX2-NEXT: vprotb %xmm1, %xmm0, %xmm0
; XOPAVX2-NEXT: retq
;
; X32-SSE-LABEL: splatvar_rotate_v16i8:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; X32-SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm1[0,0,2,3,4,5,6,7]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
; X32-SSE-NEXT: movdqa %xmm2, %xmm0
; X32-SSE-NEXT: psrlw $4, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: movdqa %xmm2, %xmm3
; X32-SSE-NEXT: psllw $4, %xmm3
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm3
; X32-SSE-NEXT: por %xmm0, %xmm3
; X32-SSE-NEXT: psllw $5, %xmm1
; X32-SSE-NEXT: pxor %xmm0, %xmm0
; X32-SSE-NEXT: pxor %xmm4, %xmm4
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm4
; X32-SSE-NEXT: pand %xmm4, %xmm3
; X32-SSE-NEXT: pandn %xmm2, %xmm4
; X32-SSE-NEXT: por %xmm3, %xmm4
; X32-SSE-NEXT: movdqa %xmm4, %xmm2
; X32-SSE-NEXT: psrlw $6, %xmm2
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm2
; X32-SSE-NEXT: movdqa %xmm4, %xmm3
; X32-SSE-NEXT: psllw $2, %xmm3
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm3
; X32-SSE-NEXT: por %xmm2, %xmm3
; X32-SSE-NEXT: paddb %xmm1, %xmm1
; X32-SSE-NEXT: pxor %xmm2, %xmm2
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm2
; X32-SSE-NEXT: pand %xmm2, %xmm3
; X32-SSE-NEXT: pandn %xmm4, %xmm2
; X32-SSE-NEXT: por %xmm3, %xmm2
; X32-SSE-NEXT: movdqa %xmm2, %xmm3
; X32-SSE-NEXT: paddb %xmm2, %xmm3
; X32-SSE-NEXT: movdqa %xmm2, %xmm4
; X32-SSE-NEXT: psrlw $7, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: por %xmm3, %xmm4
; X32-SSE-NEXT: paddb %xmm1, %xmm1
; X32-SSE-NEXT: pcmpgtb %xmm1, %xmm0
; X32-SSE-NEXT: pand %xmm0, %xmm4
; X32-SSE-NEXT: pandn %xmm2, %xmm0
; X32-SSE-NEXT: por %xmm4, %xmm0
; X32-SSE-NEXT: retl
%splat = shufflevector <16 x i8> %b, <16 x i8> undef, <16 x i32> zeroinitializer
%splat8 = sub <16 x i8> <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>, %splat
%shl = shl <16 x i8> %a, %splat
%lshr = lshr <16 x i8> %a, %splat8
%or = or <16 x i8> %shl, %lshr
ret <16 x i8> %or
}
;
; Constant Rotates
;
define <2 x i64> @constant_rotate_v2i64(<2 x i64> %a) nounwind {
; SSE2-LABEL: constant_rotate_v2i64:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: psllq $4, %xmm1
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: psllq $14, %xmm2
; SSE2-NEXT: movsd {{.*#+}} xmm2 = xmm1[0],xmm2[1]
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: psrlq $60, %xmm1
; SSE2-NEXT: psrlq $50, %xmm0
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE2-NEXT: orpd %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: constant_rotate_v2i64:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psllq $14, %xmm1
; SSE41-NEXT: movdqa %xmm0, %xmm2
; SSE41-NEXT: psllq $4, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psrlq $50, %xmm1
; SSE41-NEXT: psrlq $60, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT: por %xmm2, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: constant_rotate_v2i64:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsllq $14, %xmm0, %xmm1
; AVX1-NEXT: vpsllq $4, %xmm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm2[0,1,2,3],xmm1[4,5,6,7]
; AVX1-NEXT: vpsrlq $50, %xmm0, %xmm2
; AVX1-NEXT: vpsrlq $60, %xmm0, %xmm0
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: constant_rotate_v2i64:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsllvq {{.*}}(%rip), %xmm0, %xmm1
; AVX2-NEXT: vpsrlvq {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: constant_rotate_v2i64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm1 = [4,14]
; AVX512F-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: constant_rotate_v2i64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolvq {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: constant_rotate_v2i64:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm1 = [4,14]
; AVX512BW-NEXT: vprolvq %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: constant_rotate_v2i64:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolvq {{.*}}(%rip), %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: constant_rotate_v2i64:
; XOP: # %bb.0:
; XOP-NEXT: vprotq {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: constant_rotate_v2i64:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psllq $4, %xmm1
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: psllq $14, %xmm2
; X32-SSE-NEXT: movsd {{.*#+}} xmm2 = xmm1[0],xmm2[1]
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlq $60, %xmm1
; X32-SSE-NEXT: psrlq $50, %xmm0
; X32-SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; X32-SSE-NEXT: orpd %xmm2, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <2 x i64> %a, <i64 4, i64 14>
%lshr = lshr <2 x i64> %a, <i64 60, i64 50>
%or = or <2 x i64> %shl, %lshr
ret <2 x i64> %or
}
define <4 x i32> @constant_rotate_v4i32(<4 x i32> %a) nounwind {
; SSE2-LABEL: constant_rotate_v4i32:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [16,32,64,128]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; 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: por %xmm3, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: constant_rotate_v4i32:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [16,32,64,128]
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
; SSE41-NEXT: pmuludq %xmm2, %xmm3
; SSE41-NEXT: pmuludq %xmm1, %xmm0
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm3[2,3],xmm1[4,5],xmm3[6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,0,2,2]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; SSE41-NEXT: por %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: constant_rotate_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [16,32,64,128]
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[1,1,3,3]
; AVX1-NEXT: vpmuludq %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,3,3]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,0,2,2]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: constant_rotate_v4i32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsrlvd {{.*}}(%rip), %xmm0, %xmm1
; AVX2-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: constant_rotate_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm1 = [4,5,6,7]
; AVX512F-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: constant_rotate_v4i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolvd {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: constant_rotate_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm1 = [4,5,6,7]
; AVX512BW-NEXT: vprolvd %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: constant_rotate_v4i32:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolvd {{.*}}(%rip), %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: constant_rotate_v4i32:
; XOP: # %bb.0:
; XOP-NEXT: vprotd {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: constant_rotate_v4i32:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa {{.*#+}} xmm1 = [16,32,64,128]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; X32-SSE-NEXT: pmuludq %xmm1, %xmm0
; X32-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; X32-SSE-NEXT: pmuludq %xmm2, %xmm1
; X32-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
; X32-SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X32-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X32-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X32-SSE-NEXT: por %xmm3, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <4 x i32> %a, <i32 4, i32 5, i32 6, i32 7>
%lshr = lshr <4 x i32> %a, <i32 28, i32 27, i32 26, i32 25>
%or = or <4 x i32> %shl, %lshr
ret <4 x i32> %or
}
define <8 x i16> @constant_rotate_v8i16(<8 x i16> %a) nounwind {
; SSE-LABEL: constant_rotate_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [1,2,4,8,16,32,64,128]
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: pmulhuw %xmm1, %xmm2
; SSE-NEXT: pmullw %xmm1, %xmm0
; SSE-NEXT: por %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: constant_rotate_v8i16:
; AVX: # %bb.0:
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [1,2,4,8,16,32,64,128]
; AVX-NEXT: vpmulhuw %xmm1, %xmm0, %xmm2
; AVX-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm2, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: constant_rotate_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm1 = [1,2,4,8,16,32,64,128]
; AVX512F-NEXT: vpmulhuw %xmm1, %xmm0, %xmm2
; AVX512F-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpor %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: constant_rotate_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [1,2,4,8,16,32,64,128]
; AVX512VL-NEXT: vpmulhuw %xmm1, %xmm0, %xmm2
; AVX512VL-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: vpor %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: constant_rotate_v8i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7]
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = [16,15,14,13,12,11,10,9]
; AVX512BW-NEXT: vpsrlvw %zmm2, %zmm0, %zmm2
; AVX512BW-NEXT: vpsllvw %zmm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpor %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: constant_rotate_v8i16:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vpsrlvw {{.*}}(%rip), %xmm0, %xmm1
; AVX512VLBW-NEXT: vpsllvw {{.*}}(%rip), %xmm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: constant_rotate_v8i16:
; XOP: # %bb.0:
; XOP-NEXT: vprotw {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: constant_rotate_v8i16:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa {{.*#+}} xmm1 = [1,2,4,8,16,32,64,128]
; X32-SSE-NEXT: movdqa %xmm0, %xmm2
; X32-SSE-NEXT: pmulhuw %xmm1, %xmm2
; X32-SSE-NEXT: pmullw %xmm1, %xmm0
; X32-SSE-NEXT: por %xmm2, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <8 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>
%lshr = lshr <8 x i16> %a, <i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9>
%or = or <8 x i16> %shl, %lshr
ret <8 x i16> %or
}
define <16 x i8> @constant_rotate_v16i8(<16 x i8> %a) nounwind {
; SSE2-LABEL: constant_rotate_v16i8:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [8192,24640,41088,57536,57600,41152,24704,8256]
; SSE2-NEXT: pxor %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm3, %xmm3
; SSE2-NEXT: pcmpgtb %xmm2, %xmm3
; SSE2-NEXT: movdqa %xmm1, %xmm4
; SSE2-NEXT: psrlw $4, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: movdqa %xmm1, %xmm5
; SSE2-NEXT: psllw $4, %xmm5
; SSE2-NEXT: pand {{.*}}(%rip), %xmm5
; SSE2-NEXT: por %xmm4, %xmm5
; SSE2-NEXT: pand %xmm3, %xmm5
; SSE2-NEXT: pandn %xmm1, %xmm3
; SSE2-NEXT: por %xmm5, %xmm3
; SSE2-NEXT: movdqa %xmm3, %xmm1
; SSE2-NEXT: psrlw $6, %xmm1
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: psllw $2, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: por %xmm1, %xmm4
; SSE2-NEXT: paddb %xmm2, %xmm2
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: pcmpgtb %xmm2, %xmm1
; SSE2-NEXT: pand %xmm1, %xmm4
; SSE2-NEXT: pandn %xmm3, %xmm1
; SSE2-NEXT: por %xmm4, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: paddb %xmm1, %xmm3
; SSE2-NEXT: movdqa %xmm1, %xmm4
; SSE2-NEXT: psrlw $7, %xmm4
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
; SSE2-NEXT: por %xmm3, %xmm4
; SSE2-NEXT: paddb %xmm2, %xmm2
; SSE2-NEXT: pcmpgtb %xmm2, %xmm0
; SSE2-NEXT: pand %xmm0, %xmm4
; SSE2-NEXT: pandn %xmm1, %xmm0
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: constant_rotate_v16i8:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psrlw $4, %xmm0
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: movdqa %xmm1, %xmm2
; SSE41-NEXT: psllw $4, %xmm2
; SSE41-NEXT: pand {{.*}}(%rip), %xmm2
; SSE41-NEXT: por %xmm0, %xmm2
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [8192,24640,41088,57536,57600,41152,24704,8256]
; SSE41-NEXT: pblendvb %xmm0, %xmm2, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm2
; SSE41-NEXT: psrlw $6, %xmm2
; SSE41-NEXT: pand {{.*}}(%rip), %xmm2
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psllw $2, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm2, %xmm3
; SSE41-NEXT: paddb %xmm0, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm2
; SSE41-NEXT: paddb %xmm1, %xmm2
; SSE41-NEXT: movdqa %xmm1, %xmm3
; SSE41-NEXT: psrlw $7, %xmm3
; SSE41-NEXT: pand {{.*}}(%rip), %xmm3
; SSE41-NEXT: por %xmm2, %xmm3
; SSE41-NEXT: paddb %xmm0, %xmm0
; SSE41-NEXT: pblendvb %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: constant_rotate_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsllw $4, %xmm0, %xmm2
; AVX-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX-NEXT: vpor %xmm1, %xmm2, %xmm1
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [8192,24640,41088,57536,57600,41152,24704,8256]
; AVX-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $6, %xmm0, %xmm1
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX-NEXT: vpor %xmm1, %xmm3, %xmm1
; AVX-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpaddb %xmm0, %xmm0, %xmm1
; AVX-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX-NEXT: vpor %xmm3, %xmm1, %xmm1
; AVX-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: constant_rotate_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512F-NEXT: vpsllw $4, %xmm0, %xmm2
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512F-NEXT: vpor %xmm1, %xmm2, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [8192,24640,41088,57536,57600,41152,24704,8256]
; AVX512F-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpsrlw $6, %xmm0, %xmm1
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512F-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm1, %xmm3, %xmm1
; AVX512F-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX512F-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpaddb %xmm0, %xmm0, %xmm1
; AVX512F-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512F-NEXT: vpor %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX512F-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: constant_rotate_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512VL-NEXT: vpsllw $4, %xmm0, %xmm2
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm2, %xmm2
; AVX512VL-NEXT: vpor %xmm1, %xmm2, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [8192,24640,41088,57536,57600,41152,24704,8256]
; AVX512VL-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: vpsrlw $6, %xmm0, %xmm1
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512VL-NEXT: vpsllw $2, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm1, %xmm3, %xmm1
; AVX512VL-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX512VL-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: vpaddb %xmm0, %xmm0, %xmm1
; AVX512VL-NEXT: vpsrlw $7, %xmm0, %xmm3
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm3, %xmm3
; AVX512VL-NEXT: vpor %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpaddb %xmm2, %xmm2, %xmm2
; AVX512VL-NEXT: vpblendvb %xmm2, %xmm1, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: constant_rotate_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa {{.*#+}} ymm1 = [8,7,6,5,4,3,2,1,0,1,2,3,4,5,6,7]
; AVX512BW-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
; AVX512BW-NEXT: vpsrlvw %zmm1, %zmm0, %zmm1
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,2,3,4,5,6,7,8,7,6,5,4,3,2,1]
; AVX512BW-NEXT: vpsllvw %zmm2, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: constant_rotate_v16i8:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-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
; AVX512VLBW-NEXT: vpsrlvw {{.*}}(%rip), %ymm0, %ymm1
; AVX512VLBW-NEXT: vpmovwb %ymm1, %xmm1
; AVX512VLBW-NEXT: vpsllvw {{.*}}(%rip), %ymm0, %ymm0
; AVX512VLBW-NEXT: vpmovwb %ymm0, %xmm0
; AVX512VLBW-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512VLBW-NEXT: vzeroupper
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: constant_rotate_v16i8:
; XOP: # %bb.0:
; XOP-NEXT: vprotb {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: constant_rotate_v16i8:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: movdqa {{.*#+}} xmm2 = [8192,24640,41088,57536,57600,41152,24704,8256]
; X32-SSE-NEXT: pxor %xmm0, %xmm0
; X32-SSE-NEXT: pxor %xmm3, %xmm3
; X32-SSE-NEXT: pcmpgtb %xmm2, %xmm3
; X32-SSE-NEXT: movdqa %xmm1, %xmm4
; X32-SSE-NEXT: psrlw $4, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: movdqa %xmm1, %xmm5
; X32-SSE-NEXT: psllw $4, %xmm5
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm5
; X32-SSE-NEXT: por %xmm4, %xmm5
; X32-SSE-NEXT: pand %xmm3, %xmm5
; X32-SSE-NEXT: pandn %xmm1, %xmm3
; X32-SSE-NEXT: por %xmm5, %xmm3
; X32-SSE-NEXT: movdqa %xmm3, %xmm1
; X32-SSE-NEXT: psrlw $6, %xmm1
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm1
; X32-SSE-NEXT: movdqa %xmm3, %xmm4
; X32-SSE-NEXT: psllw $2, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: por %xmm1, %xmm4
; X32-SSE-NEXT: paddb %xmm2, %xmm2
; X32-SSE-NEXT: pxor %xmm1, %xmm1
; X32-SSE-NEXT: pcmpgtb %xmm2, %xmm1
; X32-SSE-NEXT: pand %xmm1, %xmm4
; X32-SSE-NEXT: pandn %xmm3, %xmm1
; X32-SSE-NEXT: por %xmm4, %xmm1
; X32-SSE-NEXT: movdqa %xmm1, %xmm3
; X32-SSE-NEXT: paddb %xmm1, %xmm3
; X32-SSE-NEXT: movdqa %xmm1, %xmm4
; X32-SSE-NEXT: psrlw $7, %xmm4
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm4
; X32-SSE-NEXT: por %xmm3, %xmm4
; X32-SSE-NEXT: paddb %xmm2, %xmm2
; X32-SSE-NEXT: pcmpgtb %xmm2, %xmm0
; X32-SSE-NEXT: pand %xmm0, %xmm4
; X32-SSE-NEXT: pandn %xmm1, %xmm0
; X32-SSE-NEXT: por %xmm4, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <16 x i8> %a, <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1>
%lshr = lshr <16 x i8> %a, <i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>
%or = or <16 x i8> %shl, %lshr
ret <16 x i8> %or
}
;
; Uniform Constant Rotates
;
define <2 x i64> @splatconstant_rotate_v2i64(<2 x i64> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_v2i64:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psllq $14, %xmm1
; SSE-NEXT: psrlq $50, %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_v2i64:
; AVX: # %bb.0:
; AVX-NEXT: vpsllq $14, %xmm0, %xmm1
; AVX-NEXT: vpsrlq $50, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: splatconstant_rotate_v2i64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprolq $14, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatconstant_rotate_v2i64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolq $14, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatconstant_rotate_v2i64:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprolq $14, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatconstant_rotate_v2i64:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolq $14, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_v2i64:
; XOP: # %bb.0:
; XOP-NEXT: vprotq $14, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_v2i64:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psllq $14, %xmm1
; X32-SSE-NEXT: psrlq $50, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <2 x i64> %a, <i64 14, i64 14>
%lshr = lshr <2 x i64> %a, <i64 50, i64 50>
%or = or <2 x i64> %shl, %lshr
ret <2 x i64> %or
}
define <4 x i32> @splatconstant_rotate_v4i32(<4 x i32> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrld $28, %xmm1
; SSE-NEXT: pslld $4, %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_v4i32:
; AVX: # %bb.0:
; AVX-NEXT: vpsrld $28, %xmm0, %xmm1
; AVX-NEXT: vpslld $4, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: splatconstant_rotate_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprold $4, %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatconstant_rotate_v4i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprold $4, %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatconstant_rotate_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprold $4, %zmm0, %zmm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatconstant_rotate_v4i32:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprold $4, %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_v4i32:
; XOP: # %bb.0:
; XOP-NEXT: vprotd $4, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_v4i32:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrld $28, %xmm1
; X32-SSE-NEXT: pslld $4, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <4 x i32> %a, <i32 4, i32 4, i32 4, i32 4>
%lshr = lshr <4 x i32> %a, <i32 28, i32 28, i32 28, i32 28>
%or = or <4 x i32> %shl, %lshr
ret <4 x i32> %or
}
define <8 x i16> @splatconstant_rotate_v8i16(<8 x i16> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrlw $9, %xmm1
; SSE-NEXT: psllw $7, %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_v8i16:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $9, %xmm0, %xmm1
; AVX-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512-LABEL: splatconstant_rotate_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrlw $9, %xmm0, %xmm1
; AVX512-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX512-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_v8i16:
; XOP: # %bb.0:
; XOP-NEXT: vprotw $7, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_v8i16:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlw $9, %xmm1
; X32-SSE-NEXT: psllw $7, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <8 x i16> %a, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
%lshr = lshr <8 x i16> %a, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
%or = or <8 x i16> %shl, %lshr
ret <8 x i16> %or
}
define <16 x i8> @splatconstant_rotate_v16i8(<16 x i8> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrlw $4, %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: psllw $4, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsllw $4, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512-LABEL: splatconstant_rotate_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512-NEXT: vpsllw $4, %xmm0, %xmm0
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_v16i8:
; XOP: # %bb.0:
; XOP-NEXT: vprotb $4, %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_v16i8:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlw $4, %xmm1
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm1
; X32-SSE-NEXT: psllw $4, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <16 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
%lshr = lshr <16 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
%or = or <16 x i8> %shl, %lshr
ret <16 x i8> %or
}
;
; Masked Uniform Constant Rotates
;
define <2 x i64> @splatconstant_rotate_mask_v2i64(<2 x i64> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_mask_v2i64:
; SSE: # %bb.0:
; SSE-NEXT: psrlq $49, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_mask_v2i64:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlq $49, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: splatconstant_rotate_mask_v2i64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprolq $15, %zmm0, %zmm0
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatconstant_rotate_mask_v2i64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprolq $15, %xmm0, %xmm0
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatconstant_rotate_mask_v2i64:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprolq $15, %zmm0, %zmm0
; AVX512BW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v2i64:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprolq $15, %xmm0, %xmm0
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_mask_v2i64:
; XOP: # %bb.0:
; XOP-NEXT: vprotq $15, %xmm0, %xmm0
; XOP-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_mask_v2i64:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: psrlq $49, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <2 x i64> %a, <i64 15, i64 15>
%lshr = lshr <2 x i64> %a, <i64 49, i64 49>
%rmask = and <2 x i64> %lshr, <i64 255, i64 127>
%lmask = and <2 x i64> %shl, <i64 65, i64 33>
%or = or <2 x i64> %lmask, %rmask
ret <2 x i64> %or
}
define <4 x i32> @splatconstant_rotate_mask_v4i32(<4 x i32> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_mask_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrld $28, %xmm1
; SSE-NEXT: pslld $4, %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_mask_v4i32:
; AVX: # %bb.0:
; AVX-NEXT: vpsrld $28, %xmm0, %xmm1
; AVX-NEXT: vpslld $4, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: splatconstant_rotate_mask_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vprold $4, %zmm0, %zmm0
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: splatconstant_rotate_mask_v4i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vprold $4, %xmm0, %xmm0
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: splatconstant_rotate_mask_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vprold $4, %zmm0, %zmm0
; AVX512BW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v4i32:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: vprold $4, %xmm0, %xmm0
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512VLBW-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_mask_v4i32:
; XOP: # %bb.0:
; XOP-NEXT: vprotd $4, %xmm0, %xmm0
; XOP-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_mask_v4i32:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrld $28, %xmm1
; X32-SSE-NEXT: pslld $4, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <4 x i32> %a, <i32 4, i32 4, i32 4, i32 4>
%lshr = lshr <4 x i32> %a, <i32 28, i32 28, i32 28, i32 28>
%rmask = and <4 x i32> %lshr, <i32 127, i32 255, i32 511, i32 1023>
%lmask = and <4 x i32> %shl, <i32 1023, i32 511, i32 255, i32 127>
%or = or <4 x i32> %lmask, %rmask
ret <4 x i32> %or
}
define <8 x i16> @splatconstant_rotate_mask_v8i16(<8 x i16> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_mask_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrlw $11, %xmm1
; SSE-NEXT: psllw $5, %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_mask_v8i16:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $11, %xmm0, %xmm1
; AVX-NEXT: vpsllw $5, %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512-LABEL: splatconstant_rotate_mask_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrlw $11, %xmm0, %xmm1
; AVX512-NEXT: vpsllw $5, %xmm0, %xmm0
; AVX512-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_mask_v8i16:
; XOP: # %bb.0:
; XOP-NEXT: vprotw $5, %xmm0, %xmm0
; XOP-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_mask_v8i16:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlw $11, %xmm1
; X32-SSE-NEXT: psllw $5, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <8 x i16> %a, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
%lshr = lshr <8 x i16> %a, <i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11>
%rmask = and <8 x i16> %lshr, <i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55, i16 55>
%lmask = and <8 x i16> %shl, <i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33, i16 33>
%or = or <8 x i16> %lmask, %rmask
ret <8 x i16> %or
}
define <16 x i8> @splatconstant_rotate_mask_v16i8(<16 x i8> %a) nounwind {
; SSE-LABEL: splatconstant_rotate_mask_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: psrlw $4, %xmm1
; SSE-NEXT: pand {{.*}}(%rip), %xmm1
; SSE-NEXT: psllw $4, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: splatconstant_rotate_mask_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vpsllw $4, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512-LABEL: splatconstant_rotate_mask_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsrlw $4, %xmm0, %xmm1
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
; AVX512-NEXT: vpsllw $4, %xmm0, %xmm0
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: retq
;
; XOP-LABEL: splatconstant_rotate_mask_v16i8:
; XOP: # %bb.0:
; XOP-NEXT: vprotb $4, %xmm0, %xmm0
; XOP-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; XOP-NEXT: retq
;
; X32-SSE-LABEL: splatconstant_rotate_mask_v16i8:
; X32-SSE: # %bb.0:
; X32-SSE-NEXT: movdqa %xmm0, %xmm1
; X32-SSE-NEXT: psrlw $4, %xmm1
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm1
; X32-SSE-NEXT: psllw $4, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: por %xmm1, %xmm0
; X32-SSE-NEXT: pand {{\.LCPI.*}}, %xmm0
; X32-SSE-NEXT: retl
%shl = shl <16 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
%lshr = lshr <16 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
%rmask = and <16 x i8> %lshr, <i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55, i8 55>
%lmask = and <16 x i8> %shl, <i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33, i8 33>
%or = or <16 x i8> %lmask, %rmask
ret <16 x i8> %or
}
Reference in New Issue View Git Blame Copy Permalink