llvm-project/llvm/test/CodeGen/X86/vector-trunc.ll

2129 lines
80 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BWVL
define <8 x i32> @trunc8i64_8i32(<8 x i64> %a) {
; SSE-LABEL: trunc8i64_8i32:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i32:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc8i64_8i32:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
entry:
%0 = trunc <8 x i64> %a to <8 x i32>
ret <8 x i32> %0
}
define <8 x i32> @trunc8i64_8i32_ashr(<8 x i64> %a) {
; SSE-LABEL: trunc8i64_8i32_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i32_ashr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,3],xmm3[1,3]
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc8i64_8i32_ashr:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,3],xmm2[1,3]
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32_ashr:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [1,3,5,7,5,7,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_ashr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsraq $32, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
entry:
%0 = ashr <8 x i64> %a, <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
%1 = trunc <8 x i64> %0 to <8 x i32>
ret <8 x i32> %1
}
define <8 x i32> @trunc8i64_8i32_lshr(<8 x i64> %a) {
; SSE-LABEL: trunc8i64_8i32_lshr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i32_lshr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[1,3],xmm3[1,3]
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm2[1,3]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc8i64_8i32_lshr:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsrlq $32, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i32_lshr:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vpsrlq $32, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpsrlq $32, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i32_lshr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsrlq $32, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: retq
entry:
%0 = lshr <8 x i64> %a, <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
%1 = trunc <8 x i64> %0 to <8 x i32>
ret <8 x i32> %1
}
define <8 x i16> @trunc8i64_8i16(<8 x i64> %a) {
; SSE2-LABEL: trunc8i64_8i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i64_8i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i64_8i16:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i16:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [65535,65535,65535,65535]
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc8i64_8i16:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[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-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc8i64_8i16:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[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-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i16:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = trunc <8 x i64> %a to <8 x i16>
ret <8 x i16> %0
}
define void @trunc8i64_8i8(<8 x i64> %a) {
; SSE2-LABEL: trunc8i64_8i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movq %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i64_8i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: pand %xmm4, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: pand %xmm4, %xmm1
; SSSE3-NEXT: pand %xmm4, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: packuswb %xmm0, %xmm0
; SSSE3-NEXT: movq %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i64_8i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE41-NEXT: pand %xmm4, %xmm3
; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pand %xmm4, %xmm1
; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: packuswb %xmm0, %xmm0
; SSE41-NEXT: movq %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i64_8i8:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [255,255,255,255]
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i64_8i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc8i64_8i8:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpmovqb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = trunc <8 x i64> %a to <8 x i8>
store <8 x i8> %0, <8 x i8>* undef, align 4
ret void
}
define <8 x i16> @trunc8i32_8i16(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i16:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[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: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i16:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <8 x i32> %a to <8 x i16>
ret <8 x i16> %0
}
define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
; SSE-LABEL: trunc8i32_8i16_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16_ashr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrad $16, %xmm1, %xmm1
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16_ashr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i16_ashr:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16_ashr:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16_ashr:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16_ashr:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = ashr <8 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <8 x i32> %0 to <8 x i16>
ret <8 x i16> %1
}
define <8 x i16> @trunc8i32_8i16_lshr(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i16_lshr:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i16_lshr:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,10,11,14,15,14,15,255,255]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i16_lshr:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: psrld $16, %xmm1
; SSE41-NEXT: psrld $16, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i16_lshr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i16_lshr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i16_lshr:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i16_lshr:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i16_lshr:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i16_lshr:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = lshr <8 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <8 x i32> %0 to <8 x i16>
ret <8 x i16> %1
}
define void @trunc8i32_8i8(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movq %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i32_8i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: movq %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i32_8i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: movq %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc8i32_8i8:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc8i32_8i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-NEXT: vmovq %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc8i32_8i8:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vmovq %xmm0, (%rax)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc8i32_8i8:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpmovdb %ymm0, (%rax)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc8i32_8i8:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovdb %zmm0, %xmm0
; AVX512BW-NEXT: vmovq %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc8i32_8i8:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovdb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <8 x i32> %a to <8 x i8>
store <8 x i8> %0, <8 x i8>* undef, align 4
ret void
}
define void @trunc16i32_16i16(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm2
; SSE2-NEXT: psrad $16, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: pslld $16, %xmm1
; SSSE3-NEXT: psrad $16, %xmm1
; SSSE3-NEXT: pslld $16, %xmm0
; SSSE3-NEXT: psrad $16, %xmm0
; SSSE3-NEXT: packssdw %xmm1, %xmm0
; SSSE3-NEXT: pslld $16, %xmm3
; SSSE3-NEXT: psrad $16, %xmm3
; SSSE3-NEXT: pslld $16, %xmm2
; SSSE3-NEXT: psrad $16, %xmm2
; SSSE3-NEXT: packssdw %xmm3, %xmm2
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i16:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1],xmm1[2],xmm4[3],xmm1[4],xmm4[5],xmm1[6],xmm4[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1],xmm0[2],xmm4[3],xmm0[4],xmm4[5],xmm0[6],xmm4[7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1],xmm3[2],xmm4[3],xmm3[4],xmm4[5],xmm3[6],xmm4[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1],xmm2[2],xmm4[3],xmm2[4],xmm4[5],xmm2[6],xmm4[7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i16:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [65535,65535,65535,65535,65535,65535,65535,65535]
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vmovdqu %xmm1, (%rax)
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i16:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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 %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqu %xmm1, (%rax)
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = trunc <16 x i32> %a to <16 x i16>
store <16 x i16> %0, <16 x i16>* undef, align 4
ret void
}
define void @trunc16i32_16i16_ashr(<16 x i32> %a) {
; SSE-LABEL: trunc16i32_16i16_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: psrad $16, %xmm3
; SSE-NEXT: psrad $16, %xmm2
; SSE-NEXT: packssdw %xmm3, %xmm2
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm2, (%rax)
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i16_ashr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm1, %xmm1
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm1, (%rax)
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i16_ashr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrad $16, %ymm1, %ymm1
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16_ashr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsrld $16, %zmm0, %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = ashr <16 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <16 x i32> %0 to <16 x i16>
store <16 x i16> %1, <16 x i16>* undef, align 4
ret void
}
define void @trunc16i32_16i16_lshr(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i16_lshr:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i16_lshr:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: psrad $16, %xmm1
; SSSE3-NEXT: psrad $16, %xmm0
; SSSE3-NEXT: packssdw %xmm1, %xmm0
; SSSE3-NEXT: psrad $16, %xmm3
; SSSE3-NEXT: psrad $16, %xmm2
; SSSE3-NEXT: packssdw %xmm3, %xmm2
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i16_lshr:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: psrld $16, %xmm3
; SSE41-NEXT: psrld $16, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: psrld $16, %xmm1
; SSE41-NEXT: psrld $16, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i16_lshr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm1, (%rax)
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i16_lshr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrld $16, %ymm1, %ymm1
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i16_lshr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsrld $16, %zmm0, %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = lshr <16 x i32> %a, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
%1 = trunc <16 x i32> %0 to <16 x i16>
store <16 x i16> %1, <16 x i16>* undef, align 4
ret void
}
define void @trunc16i32_16i8(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSSE3-NEXT: pand %xmm4, %xmm3
; SSSE3-NEXT: pand %xmm4, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: pand %xmm4, %xmm1
; SSSE3-NEXT: pand %xmm4, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE41-NEXT: pand %xmm4, %xmm3
; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pand %xmm4, %xmm1
; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packuswb %xmm2, %xmm0
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i8:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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 %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i8:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = trunc <16 x i32> %a to <16 x i8>
store <16 x i8> %0, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i32_16i8_ashr(<16 x i32> %a) {
; SSE-LABEL: trunc16i32_16i8_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: psrad $24, %xmm1
; SSE-NEXT: psrad $24, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: psrad $24, %xmm3
; SSE-NEXT: psrad $24, %xmm2
; SSE-NEXT: packssdw %xmm3, %xmm2
; SSE-NEXT: packsswb %xmm2, %xmm0
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i8_ashr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrad $24, %xmm1, %xmm1
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8_ashr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrad $24, %ymm1, %ymm1
; AVX2-NEXT: vpsrad $24, %ymm0, %ymm0
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i8_ashr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsrld $24, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = ashr <16 x i32> %a, <i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
%1 = trunc <16 x i32> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i32_16i8_lshr(<16 x i32> %a) {
; SSE2-LABEL: trunc16i32_16i8_lshr:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: psrld $24, %xmm1
; SSE2-NEXT: psrld $24, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: psrld $24, %xmm3
; SSE2-NEXT: psrld $24, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i32_16i8_lshr:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: psrld $24, %xmm1
; SSSE3-NEXT: psrld $24, %xmm0
; SSSE3-NEXT: packuswb %xmm1, %xmm0
; SSSE3-NEXT: psrld $24, %xmm3
; SSSE3-NEXT: psrld $24, %xmm2
; SSSE3-NEXT: packuswb %xmm3, %xmm2
; SSSE3-NEXT: packuswb %xmm2, %xmm0
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i32_16i8_lshr:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: psrld $24, %xmm1
; SSE41-NEXT: psrld $24, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: psrld $24, %xmm3
; SSE41-NEXT: psrld $24, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: packuswb %xmm2, %xmm0
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i32_16i8_lshr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm2, %xmm2
; AVX1-NEXT: vpsrld $24, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i32_16i8_lshr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrld $24, %ymm1, %ymm1
; AVX2-NEXT: vpsrld $24, %ymm0, %ymm0
; AVX2-NEXT: vpackusdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc16i32_16i8_lshr:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpsrld $24, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rax)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
entry:
%0 = lshr <16 x i32> %a, <i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
%1 = trunc <16 x i32> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
;PR25684
define void @trunc16i16_16i8(<16 x i16> %a) {
; SSE2-LABEL: trunc16i16_16i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc16i16_16i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc16i16_16i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc16i16_16i8:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc16i16_16i8:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc16i16_16i8:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc16i16_16i8:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <16 x i16> %a to <16 x i8>
store <16 x i8> %0, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
; SSE-LABEL: trunc16i16_16i8_ashr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: psraw $8, %xmm1
; SSE-NEXT: psraw $8, %xmm0
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc16i16_16i8_ashr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsraw $8, %xmm1, %xmm1
; AVX1-NEXT: vpsraw $8, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8_ashr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsraw $8, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8_ashr:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc16i16_16i8_ashr:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc16i16_16i8_ashr:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vpsraw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc16i16_16i8_ashr:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = ashr <16 x i16> %a, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%1 = trunc <16 x i16> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
define void @trunc16i16_16i8_lshr(<16 x i16> %a) {
; SSE-LABEL: trunc16i16_16i8_lshr:
; SSE: # %bb.0: # %entry
; SSE-NEXT: psrlw $8, %xmm1
; SSE-NEXT: psrlw $8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: movdqu %xmm0, (%rax)
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc16i16_16i8_lshr:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc16i16_16i8_lshr:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc16i16_16i8_lshr:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc16i16_16i8_lshr:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc16i16_16i8_lshr:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vmovdqu %xmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc16i16_16i8_lshr:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = lshr <16 x i16> %a, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%1 = trunc <16 x i16> %0 to <16 x i8>
store <16 x i8> %1, <16 x i8>* undef, align 4
ret void
}
define void @trunc32i16_32i8(<32 x i16> %a) {
; SSE2-LABEL: trunc32i16_32i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: movdqu %xmm2, (%rax)
; SSE2-NEXT: movdqu %xmm0, (%rax)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc32i16_32i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm4, %xmm1
; SSSE3-NEXT: pshufb %xmm4, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: pshufb %xmm4, %xmm3
; SSSE3-NEXT: pshufb %xmm4, %xmm2
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSSE3-NEXT: movdqu %xmm2, (%rax)
; SSSE3-NEXT: movdqu %xmm0, (%rax)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc32i16_32i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm4, %xmm1
; SSE41-NEXT: pshufb %xmm4, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: pshufb %xmm4, %xmm3
; SSE41-NEXT: pshufb %xmm4, %xmm2
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSE41-NEXT: movdqu %xmm2, (%rax)
; SSE41-NEXT: movdqu %xmm0, (%rax)
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc32i16_32i8:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpackuswb %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vmovdqu %xmm1, (%rax)
; AVX1-NEXT: vmovdqu %xmm0, (%rax)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc32i16_32i8:
; AVX2: # %bb.0: # %entry
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
; AVX2-NEXT: vpackuswb %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc32i16_32i8:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
; AVX512F-NEXT: vpmovdb %zmm1, (%rax)
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, (%rax)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc32i16_32i8:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
; AVX512VL-NEXT: vpmovdb %zmm1, (%rax)
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, (%rax)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc32i16_32i8:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vpmovwb %zmm0, (%rax)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc32i16_32i8:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovwb %zmm0, (%rax)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <32 x i16> %a to <32 x i8>
store <32 x i8> %0, <32 x i8>* undef, align 4
ret void
}
define <8 x i32> @trunc2x4i64_8i32(<4 x i64> %a, <4 x i64> %b) {
; SSE-LABEL: trunc2x4i64_8i32:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc2x4i64_8i32:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc2x4i64_8i32:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc2x4i64_8i32:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: trunc2x4i64_8i32:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2x4i64_8i32:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512VL-NEXT: vpmovqd %ymm1, %xmm1
; AVX512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2x4i64_8i32:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2x4i64_8i32:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
; AVX512BWVL-NEXT: vpmovqd %ymm1, %xmm1
; AVX512BWVL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <4 x i64> %a to <4 x i32>
%1 = trunc <4 x i64> %b to <4 x i32>
%2 = shufflevector <4 x i32> %0, <4 x i32> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i32> %2
}
define <8 x i16> @trunc2x4i64_8i16(<4 x i64> %a, <4 x i64> %b) {
; SSE2-LABEL: trunc2x4i64_8i16:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc2x4i64_8i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc2x4i64_8i16:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; SSE41-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE41-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc2x4i64_8i16:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc2x4i64_8i16:
; AVX2-SLOW: # %bb.0: # %entry
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX2-SLOW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc2x4i64_8i16:
; AVX2-FAST: # %bb.0: # %entry
; AVX2-FAST-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,2,3,0,1,8,9,8,9,10,11,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,8,9,8,9,10,11,8,9,10,11,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX2-FAST-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: trunc2x4i64_8i16:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
; AVX512F-NEXT: vpmovqw %zmm1, %xmm1
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2x4i64_8i16:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vpmovqw %ymm0, %xmm0
; AVX512VL-NEXT: vpmovqw %ymm1, %xmm1
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2x4i64_8i16:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
; AVX512BW-NEXT: vpmovqw %zmm1, %xmm1
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2x4i64_8i16:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vpmovqw %ymm0, %xmm0
; AVX512BWVL-NEXT: vpmovqw %ymm1, %xmm1
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <4 x i64> %a to <4 x i16>
%1 = trunc <4 x i64> %b to <4 x i16>
%2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %2
}
define <4 x i32> @trunc2x2i64_4i32(<2 x i64> %a, <2 x i64> %b) {
; SSE-LABEL: trunc2x2i64_4i32:
; SSE: # %bb.0: # %entry
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX-LABEL: trunc2x2i64_4i32:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc2x2i64_4i32:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX512-NEXT: retq
entry:
%0 = trunc <2 x i64> %a to <2 x i32>
%1 = trunc <2 x i64> %b to <2 x i32>
%2 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %2
}
define i64 @trunc2i64_i64(<2 x i64> %inval) {
; SSE-LABEL: trunc2i64_i64:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: movq %xmm0, %rax
; SSE-NEXT: retq
;
; AVX-LABEL: trunc2i64_i64:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc2i64_i64:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512-NEXT: vmovq %xmm0, %rax
; AVX512-NEXT: retq
entry:
%0 = trunc <2 x i64> %inval to <2 x i32>
%1 = bitcast <2 x i32> %0 to i64
ret i64 %1
}
define <8 x i16> @trunc2x4i32_8i16(<4 x i32> %a, <4 x i32> %b) {
; SSE2-LABEL: trunc2x4i32_8i16:
; SSE2: # %bb.0: # %entry
; 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: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc2x4i32_8i16:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc2x4i32_8i16:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: retq
;
; AVX-LABEL: trunc2x4i32_8i16:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT: retq
;
; AVX512F-LABEL: trunc2x4i32_8i16:
; AVX512F: # %bb.0: # %entry
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc2x4i32_8i16:
; AVX512VL: # %bb.0: # %entry
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc2x4i32_8i16:
; AVX512BW: # %bb.0: # %entry
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc2x4i32_8i16:
; AVX512BWVL: # %bb.0: # %entry
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [0,2,4,6,8,10,12,14]
; AVX512BWVL-NEXT: vpermt2w %xmm1, %xmm2, %xmm0
; AVX512BWVL-NEXT: retq
entry:
%0 = trunc <4 x i32> %a to <4 x i16>
%1 = trunc <4 x i32> %b to <4 x i16>
%2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %2
}
; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
define i64 @trunc4i32_i64(<4 x i32> %inval) {
; SSE2-LABEL: trunc4i32_i64:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: movq %xmm0, %rax
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc4i32_i64:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: movq %xmm0, %rax
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc4i32_i64:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: movq %xmm0, %rax
; SSE41-NEXT: retq
;
; AVX-LABEL: trunc4i32_i64:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc4i32_i64:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512-NEXT: vmovq %xmm0, %rax
; AVX512-NEXT: retq
entry:
%0 = trunc <4 x i32> %inval to <4 x i16>
%1 = bitcast <4 x i16> %0 to i64
ret i64 %1
}
define <16 x i8> @trunc2x8i16_16i8(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: trunc2x8i16_16i8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc2x8i16_16i8:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT: pshufb %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm2, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc2x8i16_16i8:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: retq
;
; AVX-LABEL: trunc2x8i16_16i8:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc2x8i16_16i8:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512-NEXT: retq
entry:
%0 = trunc <8 x i16> %a to <8 x i8>
%1 = trunc <8 x i16> %b to <8 x i8>
%2 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %2
}
; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
define i64 @trunc8i16_i64(<8 x i16> %inval) {
; SSE2-LABEL: trunc8i16_i64:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: packuswb %xmm0, %xmm0
; SSE2-NEXT: movq %xmm0, %rax
; SSE2-NEXT: retq
;
; SSSE3-LABEL: trunc8i16_i64:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; SSSE3-NEXT: movq %xmm0, %rax
; SSSE3-NEXT: retq
;
; SSE41-LABEL: trunc8i16_i64:
; SSE41: # %bb.0: # %entry
; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; SSE41-NEXT: movq %xmm0, %rax
; SSE41-NEXT: retq
;
; AVX-LABEL: trunc8i16_i64:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX-NEXT: vmovq %xmm0, %rax
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc8i16_i64:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512-NEXT: vmovq %xmm0, %rax
; AVX512-NEXT: retq
entry:
%0 = trunc <8 x i16> %inval to <8 x i8>
%1 = bitcast <8 x i8> %0 to i64
ret i64 %1
}
define <16 x i8> @trunc16i64_16i8_const() {
; SSE-LABEL: trunc16i64_16i8_const:
; SSE: # %bb.0: # %entry
; SSE-NEXT: xorps %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: trunc16i64_16i8_const:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc16i64_16i8_const:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX512-NEXT: retq
entry:
%0 = trunc <16 x i64> zeroinitializer to <16 x i8>
%1 = shufflevector <16 x i8> %0, <16 x i8> %0, <16 x i32> <i32 28, i32 30, i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 undef, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26>
ret <16 x i8> %1
}
define <8 x i16> @PR32160(<8 x i32> %x) {
; SSE-LABEL: PR32160:
; SSE: # %bb.0:
; SSE-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,2,2,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: PR32160:
; AVX1: # %bb.0:
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,8,9,8,9,8,9,8,9]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: PR32160:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; AVX2-SLOW-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: PR32160:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,8,9,8,9,8,9,8,9]
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: PR32160:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR32160:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR32160:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR32160:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4,5,4,5,4,5,4,5,4,5,4,5,4,5,4,5]
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%shuf = trunc <8 x i32> %x to <8 x i16>
%trunc = shufflevector <8 x i16> %shuf, <8 x i16> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
ret <8 x i16> %trunc
}
define void @PR34773(i16* %a0, i8* %a1) {
; SSE-LABEL: PR34773:
; SSE: # %bb.0:
; SSE-NEXT: movdqu (%rdi), %xmm0
; SSE-NEXT: movdqu 16(%rdi), %xmm1
; SSE-NEXT: movdqu 32(%rdi), %xmm2
; SSE-NEXT: movdqu 48(%rdi), %xmm3
; SSE-NEXT: psrlw $8, %xmm1
; SSE-NEXT: psrlw $8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: psrlw $8, %xmm3
; SSE-NEXT: psrlw $8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: movdqu %xmm0, (%rsi)
; SSE-NEXT: movdqu %xmm2, 16(%rsi)
; SSE-NEXT: retq
;
; AVX1-LABEL: PR34773:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqu (%rdi), %xmm0
; AVX1-NEXT: vmovdqu 16(%rdi), %xmm1
; AVX1-NEXT: vmovdqu 32(%rdi), %xmm2
; AVX1-NEXT: vmovdqu 48(%rdi), %xmm3
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsrlw $8, %xmm3, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm2, %xmm2
; AVX1-NEXT: vpackuswb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vmovdqu %xmm0, (%rsi)
; AVX1-NEXT: vmovdqu %xmm1, 16(%rsi)
; AVX1-NEXT: retq
;
; AVX2-LABEL: PR34773:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqu (%rdi), %ymm0
; AVX2-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX2-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vmovdqu %xmm0, (%rsi)
; AVX2-NEXT: vmovdqu %xmm1, 16(%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: PR34773:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqu (%rdi), %ymm0
; AVX512F-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512F-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512F-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, (%rsi)
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
; AVX512F-NEXT: vpmovdb %zmm0, 16(%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR34773:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqu (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512VL-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512VL-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, (%rsi)
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
; AVX512VL-NEXT: vpmovdb %zmm0, 16(%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR34773:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqu (%rdi), %ymm0
; AVX512BW-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512BW-NEXT: vpsrlw $8, %ymm0, %ymm0
; AVX512BW-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
; AVX512BW-NEXT: vmovdqu %xmm0, (%rsi)
; AVX512BW-NEXT: vmovdqu %xmm1, 16(%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR34773:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vpsrlw $8, (%rdi), %ymm0
; AVX512BWVL-NEXT: vpsrlw $8, 32(%rdi), %ymm1
; AVX512BWVL-NEXT: vpmovwb %ymm0, (%rsi)
; AVX512BWVL-NEXT: vpmovwb %ymm1, 16(%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%1 = getelementptr i16, i16* %a0, i64 16
%2 = getelementptr i8, i8* %a1, i64 16
%3 = bitcast i16* %a0 to <16 x i16>*
%4 = bitcast i16* %1 to <16 x i16>*
%5 = bitcast i8* %a1 to <16 x i8>*
%6 = bitcast i8* %2 to <16 x i8>*
%7 = load <16 x i16>, <16 x i16>* %3, align 2
%8 = load <16 x i16>, <16 x i16>* %4, align 2
%9 = lshr <16 x i16> %7, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%10 = lshr <16 x i16> %8, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%11 = trunc <16 x i16> %9 to <16 x i8>
%12 = trunc <16 x i16> %10 to <16 x i8>
store <16 x i8> %11, <16 x i8>* %5, align 1
store <16 x i8> %12, <16 x i8>* %6, align 1
ret void
}
; Store merging must not infinitely fight store splitting.
define void @store_merge_split(<8 x i32> %w1, <8 x i32> %w2, i64 %idx, <8 x i16>* %p) align 2 {
; SSE2-LABEL: store_merge_split:
; SSE2: # %bb.0:
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: pslld $16, %xmm3
; SSE2-NEXT: psrad $16, %xmm3
; SSE2-NEXT: pslld $16, %xmm2
; SSE2-NEXT: psrad $16, %xmm2
; SSE2-NEXT: packssdw %xmm3, %xmm2
; SSE2-NEXT: shlq $4, %rdi
; SSE2-NEXT: movdqu %xmm0, (%rsi,%rdi)
; SSE2-NEXT: movdqu %xmm2, 16(%rsi,%rdi)
; SSE2-NEXT: retq
;
; SSSE3-LABEL: store_merge_split:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT: pshufb %xmm4, %xmm1
; SSSE3-NEXT: pshufb %xmm4, %xmm0
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: pshufb %xmm4, %xmm3
; SSSE3-NEXT: pshufb %xmm4, %xmm2
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSSE3-NEXT: shlq $4, %rdi
; SSSE3-NEXT: movdqu %xmm0, (%rsi,%rdi)
; SSSE3-NEXT: movdqu %xmm2, 16(%rsi,%rdi)
; SSSE3-NEXT: retq
;
; SSE41-LABEL: store_merge_split:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm4, %xmm1
; SSE41-NEXT: pshufb %xmm4, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: pshufb %xmm4, %xmm3
; SSE41-NEXT: pshufb %xmm4, %xmm2
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSE41-NEXT: shlq $4, %rdi
; SSE41-NEXT: movdqu %xmm0, (%rsi,%rdi)
; SSE41-NEXT: movdqu %xmm2, 16(%rsi,%rdi)
; SSE41-NEXT: retq
;
; AVX1-LABEL: store_merge_split:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: shlq $4, %rdi
; AVX1-NEXT: vmovdqu %xmm0, (%rsi,%rdi)
; AVX1-NEXT: vmovdqu %xmm1, 16(%rsi,%rdi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: store_merge_split:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [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 %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: shlq $4, %rdi
; AVX2-NEXT: vmovdqu %xmm0, (%rsi,%rdi)
; AVX2-NEXT: vmovdqu %xmm1, 16(%rsi,%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: store_merge_split:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm1, %ymm1
; AVX512F-NEXT: shlq $4, %rdi
; AVX512F-NEXT: vmovdqu %xmm0, (%rsi,%rdi)
; AVX512F-NEXT: vmovdqu %xmm1, 16(%rsi,%rdi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: store_merge_split:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: shlq $4, %rdi
; AVX512VL-NEXT: vpmovdw %ymm0, (%rsi,%rdi)
; AVX512VL-NEXT: vpmovdw %ymm1, 16(%rsi,%rdi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: store_merge_split:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT: vpmovdw %zmm1, %ymm1
; AVX512BW-NEXT: shlq $4, %rdi
; AVX512BW-NEXT: vmovdqu %xmm0, (%rsi,%rdi)
; AVX512BW-NEXT: vmovdqu %xmm1, 16(%rsi,%rdi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: store_merge_split:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: shlq $4, %rdi
; AVX512BWVL-NEXT: vpmovdw %ymm0, (%rsi,%rdi)
; AVX512BWVL-NEXT: vpmovdw %ymm1, 16(%rsi,%rdi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%t1 = trunc <8 x i32> %w1 to <8 x i16>
%t2 = trunc <8 x i32> %w2 to <8 x i16>
%g1 = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i64 %idx
%g2 = getelementptr inbounds <8 x i16>, <8 x i16>* %g1, i64 1
store <8 x i16> %t1, <8 x i16>* %g1, align 2
store <8 x i16> %t2, <8 x i16>* %g2, align 2
ret void
}