blob: b06f3294e0a27375a580c2cddba4ec494977c387 [file] [log] [blame]
; 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=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=ALL,AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefixes=ALL,AVX,AVX2,AVX2-FAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+fast-variable-shuffle | FileCheck %s --check-prefixes=ALL,AVX,AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+fast-variable-shuffle | FileCheck %s --check-prefixes=ALL,AVX,AVX512,AVX512DQ
;
; add
;
define <4 x i32> @trunc_add_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
; SSE-LABEL: trunc_add_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: paddq %xmm3, %xmm1
; SSE-NEXT: paddq %xmm2, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpaddq %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpaddq %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; 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: trunc_add_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpaddq %ymm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_add_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: vpaddq %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <4 x i64> %a0, %a1
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_add_v8i64_v8i16(<8 x i64> %a0, <8 x i64> %a1) nounwind {
; SSE-LABEL: trunc_add_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: paddq %xmm6, %xmm2
; SSE-NEXT: paddq %xmm7, %xmm3
; SSE-NEXT: paddq %xmm4, %xmm0
; SSE-NEXT: paddq %xmm5, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpaddq %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpaddq %xmm3, %xmm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpaddq %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm4[0],xmm3[1,2,3],xmm4[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpaddq %ymm3, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: trunc_add_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpaddq %ymm3, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpaddq %ymm2, %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: 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: trunc_add_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpaddq %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <8 x i64> %a0, %a1
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_add_v8i32_v8i16(<8 x i32> %a0, <8 x i32> %a1) nounwind {
; SSE-LABEL: trunc_add_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: paddd %xmm2, %xmm0
; SSE-NEXT: paddd %xmm3, %xmm1
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v8i32_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpaddd %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_v8i32_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0
; 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
;
; AVX512-LABEL: trunc_add_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpaddd %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <8 x i32> %a0, %a1
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_add_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
; SSE-LABEL: trunc_add_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm0
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm1
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm2
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm3
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm4
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm5
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm6
; SSE-NEXT: paddq {{[0-9]+}}(%rsp), %xmm7
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm8
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpaddq %xmm5, %xmm1, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpaddq %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpaddq %xmm6, %xmm2, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm6
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vpaddq %xmm6, %xmm2, %xmm2
; AVX1-NEXT: vpaddq %xmm7, %xmm3, %xmm6
; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm7
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vpaddq %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vmovddup {{.*#+}} xmm7 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm7 = mem[0,0]
; AVX1-NEXT: vpand %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vpand %xmm7, %xmm6, %xmm6
; AVX1-NEXT: vpackusdw %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpand %xmm7, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm7, %xmm5, %xmm5
; AVX1-NEXT: vpackusdw %xmm2, %xmm5, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm7, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm7, %xmm4, %xmm3
; AVX1-NEXT: vpackusdw %xmm1, %xmm3, %xmm1
; AVX1-NEXT: vpand %xmm7, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm7, %xmm8, %xmm3
; AVX1-NEXT: vpackusdw %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpaddq %ymm5, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpaddq %ymm4, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpaddq %ymm7, %ymm3, %ymm3
; AVX2-SLOW-NEXT: vpaddq %ymm6, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_add_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpaddq %ymm5, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpaddq %ymm4, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpaddq %ymm7, %ymm3, %ymm3
; AVX2-FAST-NEXT: vpaddq %ymm6, %ymm2, %ymm2
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_add_v16i64_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpaddq %zmm3, %zmm1, %zmm1
; AVX512-NEXT: vpaddq %zmm2, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm1, %ymm1
; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <16 x i64> %a0, %a1
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_add_v16i32_v16i8(<16 x i32> %a0, <16 x i32> %a1) nounwind {
; SSE-LABEL: trunc_add_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: paddd %xmm4, %xmm0
; SSE-NEXT: paddd %xmm5, %xmm1
; SSE-NEXT: paddd %xmm6, %xmm2
; SSE-NEXT: paddd %xmm7, %xmm3
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpaddd %xmm3, %xmm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpaddd %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm3, %xmm4, %xmm2
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_v16i32_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpaddd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpaddd %ymm3, %ymm1, %ymm1
; 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: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_add_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <16 x i32> %a0, %a1
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_add_v16i16_v16i8(<16 x i16> %a0, <16 x i16> %a1) nounwind {
; SSE-LABEL: trunc_add_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: paddw %xmm2, %xmm0
; SSE-NEXT: paddw %xmm3, %xmm1
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpaddw %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpaddw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpaddw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_add_v16i16_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpaddw %ymm1, %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, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_add_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpaddw %ymm1, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_add_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpaddw %ymm1, %ymm0, %ymm0
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = add <16 x i16> %a0, %a1
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
define <8 x i16> @trunc_add_v8i32_v8i16_sext_8i8(<16 x i8> %a0, <8 x i32> %a1) {
; SSE-LABEL: trunc_add_v8i32_v8i16_sext_8i8:
; SSE: # %bb.0:
; SSE-NEXT: pslld $16, %xmm2
; SSE-NEXT: psrad $16, %xmm2
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: packssdw %xmm2, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE-NEXT: psraw $8, %xmm0
; SSE-NEXT: paddw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_v8i32_v8i16_sext_8i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %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, %xmm1, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vpmovsxbw %xmm0, %xmm0
; AVX1-NEXT: vpaddw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_v8i32_v8i16_sext_8i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovsxbw %xmm0, %xmm0
; AVX2-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[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 {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vpaddw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_add_v8i32_v8i16_sext_8i8:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512-NEXT: vpmovdw %zmm1, %ymm1
; AVX512-NEXT: vpmovsxbw %xmm0, %xmm0
; AVX512-NEXT: vpaddw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = shufflevector <16 x i8> %a0, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = sext <8 x i8> %1 to <8 x i32>
%3 = add <8 x i32> %2, %a1
%4 = trunc <8 x i32> %3 to <8 x i16>
ret <8 x i16> %4
}
;
; add to constant
;
define <4 x i32> @trunc_add_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: paddd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX1-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_const_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_add_const_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_add_const_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_add_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: paddw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_const_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_add_const_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; 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: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_add_const_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_add_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: paddw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v8i32_v8i16:
; AVX1: # %bb.0:
; 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: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_const_v8i32_v8i16:
; AVX2: # %bb.0:
; 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: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_add_const_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: vpaddw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_add_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: paddb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vmovddup {{.*#+}} xmm5 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm5 = mem[0,0]
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vpackusdw %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_add_const_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_add_const_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_add_const_v16i64_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm1, %ymm1
; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_add_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: paddb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_const_v16i32_v16i8:
; 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, %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: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_add_const_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = add <16 x i32> %a0, <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>
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_add_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
; SSE-LABEL: trunc_add_const_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: paddb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_add_const_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_add_const_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_add_const_v16i16_v16i8:
; AVX512F: # %bb.0:
; 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, %xmm0
; AVX512F-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_add_const_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_add_const_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = add <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
;
; sub
;
define <4 x i32> @trunc_sub_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
; SSE-LABEL: trunc_sub_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: psubq %xmm3, %xmm1
; SSE-NEXT: psubq %xmm2, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpsubq %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpsubq %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpsubq %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; 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: trunc_sub_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpsubq %ymm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_sub_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsubq %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <4 x i64> %a0, %a1
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_sub_v8i64_v8i16(<8 x i64> %a0, <8 x i64> %a1) nounwind {
; SSE-LABEL: trunc_sub_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: psubq %xmm6, %xmm2
; SSE-NEXT: psubq %xmm7, %xmm3
; SSE-NEXT: psubq %xmm4, %xmm0
; SSE-NEXT: psubq %xmm5, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsubq %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubq %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpsubq %xmm3, %xmm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpsubq %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm4[0],xmm3[1,2,3],xmm4[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpsubq %ymm3, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpsubq %ymm2, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: trunc_sub_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpsubq %ymm3, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpsubq %ymm2, %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: 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: trunc_sub_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsubq %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <8 x i64> %a0, %a1
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_sub_v8i32_v8i16(<8 x i32> %a0, <8 x i32> %a1) nounwind {
; SSE-LABEL: trunc_sub_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: psubd %xmm2, %xmm0
; SSE-NEXT: psubd %xmm3, %xmm1
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v8i32_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_v8i32_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; 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
;
; AVX512-LABEL: trunc_sub_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <8 x i32> %a0, %a1
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_sub_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
; SSE-LABEL: trunc_sub_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm0
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm1
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm2
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm3
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm4
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm5
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm6
; SSE-NEXT: psubq {{[0-9]+}}(%rsp), %xmm7
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsubq %xmm4, %xmm0, %xmm8
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubq %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpsubq %xmm5, %xmm1, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpsubq %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpsubq %xmm6, %xmm2, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm6
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vpsubq %xmm6, %xmm2, %xmm2
; AVX1-NEXT: vpsubq %xmm7, %xmm3, %xmm6
; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm7
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vpsubq %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vmovddup {{.*#+}} xmm7 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm7 = mem[0,0]
; AVX1-NEXT: vpand %xmm7, %xmm3, %xmm3
; AVX1-NEXT: vpand %xmm7, %xmm6, %xmm6
; AVX1-NEXT: vpackusdw %xmm3, %xmm6, %xmm3
; AVX1-NEXT: vpand %xmm7, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm7, %xmm5, %xmm5
; AVX1-NEXT: vpackusdw %xmm2, %xmm5, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm7, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm7, %xmm4, %xmm3
; AVX1-NEXT: vpackusdw %xmm1, %xmm3, %xmm1
; AVX1-NEXT: vpand %xmm7, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm7, %xmm8, %xmm3
; AVX1-NEXT: vpackusdw %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpsubq %ymm5, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpsubq %ymm4, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsubq %ymm7, %ymm3, %ymm3
; AVX2-SLOW-NEXT: vpsubq %ymm6, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_sub_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpsubq %ymm5, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpsubq %ymm4, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpsubq %ymm7, %ymm3, %ymm3
; AVX2-FAST-NEXT: vpsubq %ymm6, %ymm2, %ymm2
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_sub_v16i64_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsubq %zmm3, %zmm1, %zmm1
; AVX512-NEXT: vpsubq %zmm2, %zmm0, %zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm1, %ymm1
; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <16 x i64> %a0, %a1
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_sub_v16i32_v16i8(<16 x i32> %a0, <16 x i32> %a1) nounwind {
; SSE-LABEL: trunc_sub_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: psubd %xmm4, %xmm0
; SSE-NEXT: psubd %xmm5, %xmm1
; SSE-NEXT: psubd %xmm6, %xmm2
; SSE-NEXT: psubd %xmm7, %xmm3
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsubd %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpsubd %xmm3, %xmm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpsubd %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm3, %xmm4, %xmm2
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_v16i32_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsubd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpsubd %ymm3, %ymm1, %ymm1
; 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: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_sub_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsubd %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <16 x i32> %a0, %a1
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_sub_v16i16_v16i8(<16 x i16> %a0, <16 x i16> %a1) nounwind {
; SSE-LABEL: trunc_sub_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: psubw %xmm2, %xmm0
; SSE-NEXT: psubw %xmm3, %xmm1
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsubw %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsubw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsubw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_sub_v16i16_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsubw %ymm1, %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, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_sub_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsubw %ymm1, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_sub_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpsubw %ymm1, %ymm0, %ymm0
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = sub <16 x i16> %a0, %a1
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_ext_sub_v16i16_v16i8(<16 x i8> %x, <16 x i8> %y) {
; SSE-LABEL: trunc_ext_sub_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: psubb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_ext_sub_v16i16_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsubb %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%a = zext <16 x i8> %x to <16 x i16>
%b = zext <16 x i8> %y to <16 x i16>
%c = sub <16 x i16> %a, %b
%d = trunc <16 x i16> %c to <16 x i8>
ret <16 x i8> %d
}
;
; sub to constant
;
define <4 x i32> @trunc_sub_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: psubd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX1-NEXT: vpsubd {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_const_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpsubd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_sub_const_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpsubd {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_sub_const_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpsubd {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_sub_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: psubw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_const_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_sub_const_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; 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: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_sub_const_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_sub_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: psubw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v8i32_v8i16:
; AVX1: # %bb.0:
; 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: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_const_v8i32_v8i16:
; AVX2: # %bb.0:
; 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: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_sub_const_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: vpsubw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_sub_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: psubb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vmovddup {{.*#+}} xmm5 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm5 = mem[0,0]
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vpackusdw %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_sub_const_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_sub_const_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_sub_const_v16i64_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm1, %ymm1
; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_sub_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: psubb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vandps %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_const_v16i32_v16i8:
; 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, %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: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_sub_const_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = sub <16 x i32> %a0, <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>
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_sub_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
; SSE-LABEL: trunc_sub_const_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: psubb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_sub_const_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_sub_const_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_sub_const_v16i16_v16i8:
; AVX512F: # %bb.0:
; 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, %xmm0
; AVX512F-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_sub_const_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_sub_const_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = sub <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_ext_sub_const_rhs_v16i16_v16i8(<16 x i8> %x) {
; SSE-LABEL: trunc_ext_sub_const_rhs_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: psubb {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_ext_sub_const_rhs_v16i16_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%a = zext <16 x i8> %x to <16 x i16>
%b = sub <16 x i16> %a, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
%c = trunc <16 x i16> %b to <16 x i8>
ret <16 x i8> %c
}
define <16 x i8> @trunc_ext_sub_const_lhs_v16i16_v16i8(<16 x i8> %x) {
; SSE-LABEL: trunc_ext_sub_const_lhs_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
; SSE-NEXT: psubb %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_ext_sub_const_lhs_v16i16_v16i8:
; AVX: # %bb.0:
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
; AVX-NEXT: vpsubb %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%a = zext <16 x i8> %x to <16 x i16>
%b = sub <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>, %a
%c = trunc <16 x i16> %b to <16 x i8>
ret <16 x i8> %c
}
;
; mul
;
define <4 x i32> @trunc_mul_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
; SSE-LABEL: trunc_mul_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: pmuludq %xmm3, %xmm1
; SSE-NEXT: pmuludq %xmm2, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v4i64_v4i32:
; AVX1: # %bb.0:
; 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: vpmulld %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-FAST-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: trunc_mul_v4i64_v4i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
; AVX512F-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_mul_v4i64_v4i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_mul_v4i64_v4i32:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512DQ-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512DQ-NEXT: vpmullq %zmm1, %zmm0, %zmm0
; AVX512DQ-NEXT: vpmovqd %zmm0, %ymm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = mul <4 x i64> %a0, %a1
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_mul_v8i64_v8i16(<8 x i64> %a0, <8 x i64> %a1) nounwind {
; SSE-LABEL: trunc_mul_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm5[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm7[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm6[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm6 = xmm6[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm5[0],xmm6[1],xmm5[1]
; SSE-NEXT: movsd {{.*#+}} xmm6 = xmm4[0],xmm6[1]
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: pmullw %xmm6, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vpxor %xmm5, %xmm5, %xmm5
; AVX1-NEXT: vpblendw {{.*#+}} xmm4 = xmm4[0],xmm5[1,2,3],xmm4[4],xmm5[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
; AVX1-NEXT: vpackusdw %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT: vpblendw {{.*#+}} xmm4 = xmm4[0],xmm5[1,2,3],xmm4[4],xmm5[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm5[1,2,3],xmm2[4],xmm5[5,6,7]
; AVX1-NEXT: vpackusdw %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm5[1,2,3],xmm1[4],xmm5[5,6,7]
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm3 = xmm3[0],xmm5[1,2,3],xmm3[4],xmm5[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm5[1,2,3],xmm0[4],xmm5[5,6,7]
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmullw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpmullw %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpmullw %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: trunc_mul_v8i64_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovqw %zmm1, %xmm1
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
; AVX512F-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_mul_v8i64_v8i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpmovqw %zmm1, %xmm1
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
; AVX512BW-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_mul_v8i64_v8i16:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpmullq %zmm1, %zmm0, %zmm0
; AVX512DQ-NEXT: vpmovqw %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = mul <8 x i64> %a0, %a1
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_mul_v8i32_v8i16(<8 x i32> %a0, <8 x i32> %a1) nounwind {
; SSE-LABEL: trunc_mul_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSE-NEXT: pmuludq %xmm2, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE-NEXT: pmuludq %xmm3, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
; SSE-NEXT: pmuludq %xmm2, %xmm3
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v8i32_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_v8i32_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmulld %ymm1, %ymm0, %ymm0
; 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
;
; AVX512-LABEL: trunc_mul_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmulld %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <8 x i32> %a0, %a1
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_mul_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
; SSE-LABEL: trunc_mul_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm0
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm1
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm2
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm3
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm4
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm5
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm6
; SSE-NEXT: pmuludq {{[0-9]+}}(%rsp), %xmm7
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm8
; AVX1-NEXT: vpmuludq %xmm4, %xmm8, %xmm8
; AVX1-NEXT: vpsrlq $32, %xmm4, %xmm9
; AVX1-NEXT: vpmuludq %xmm9, %xmm0, %xmm9
; AVX1-NEXT: vpaddq %xmm8, %xmm9, %xmm8
; AVX1-NEXT: vpsllq $32, %xmm8, %xmm8
; AVX1-NEXT: vpmuludq %xmm4, %xmm0, %xmm9
; AVX1-NEXT: vpaddq %xmm8, %xmm9, %xmm8
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm9
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm4
; AVX1-NEXT: vpmuludq %xmm9, %xmm4, %xmm10
; AVX1-NEXT: vpsrlq $32, %xmm9, %xmm4
; AVX1-NEXT: vpmuludq %xmm4, %xmm0, %xmm4
; AVX1-NEXT: vpaddq %xmm10, %xmm4, %xmm4
; AVX1-NEXT: vpsllq $32, %xmm4, %xmm4
; AVX1-NEXT: vpmuludq %xmm9, %xmm0, %xmm0
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm9
; AVX1-NEXT: vpsrlq $32, %xmm1, %xmm4
; AVX1-NEXT: vpmuludq %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vpsrlq $32, %xmm5, %xmm0
; AVX1-NEXT: vpmuludq %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpsllq $32, %xmm0, %xmm0
; AVX1-NEXT: vpmuludq %xmm5, %xmm1, %xmm4
; AVX1-NEXT: vpaddq %xmm0, %xmm4, %xmm10
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpsrlq $32, %xmm1, %xmm5
; AVX1-NEXT: vpmuludq %xmm0, %xmm5, %xmm5
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm4
; AVX1-NEXT: vpmuludq %xmm4, %xmm1, %xmm4
; AVX1-NEXT: vpaddq %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vpsllq $32, %xmm4, %xmm4
; AVX1-NEXT: vpmuludq %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm1
; AVX1-NEXT: vpsrlq $32, %xmm2, %xmm0
; AVX1-NEXT: vpmuludq %xmm6, %xmm0, %xmm0
; AVX1-NEXT: vpsrlq $32, %xmm6, %xmm4
; AVX1-NEXT: vpmuludq %xmm4, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm0, %xmm4, %xmm0
; AVX1-NEXT: vpsllq $32, %xmm0, %xmm0
; AVX1-NEXT: vpmuludq %xmm6, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm0, %xmm4, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vpsrlq $32, %xmm2, %xmm4
; AVX1-NEXT: vpmuludq %xmm0, %xmm4, %xmm4
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm6
; AVX1-NEXT: vpmuludq %xmm6, %xmm2, %xmm6
; AVX1-NEXT: vpaddq %xmm4, %xmm6, %xmm4
; AVX1-NEXT: vpsllq $32, %xmm4, %xmm4
; AVX1-NEXT: vpmuludq %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpaddq %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpsrlq $32, %xmm3, %xmm2
; AVX1-NEXT: vpmuludq %xmm7, %xmm2, %xmm2
; AVX1-NEXT: vpsrlq $32, %xmm7, %xmm4
; AVX1-NEXT: vpmuludq %xmm4, %xmm3, %xmm4
; AVX1-NEXT: vpaddq %xmm2, %xmm4, %xmm2
; AVX1-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX1-NEXT: vpmuludq %xmm7, %xmm3, %xmm4
; AVX1-NEXT: vpaddq %xmm2, %xmm4, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vpsrlq $32, %xmm3, %xmm6
; AVX1-NEXT: vpmuludq %xmm4, %xmm6, %xmm6
; AVX1-NEXT: vpsrlq $32, %xmm4, %xmm7
; AVX1-NEXT: vpmuludq %xmm7, %xmm3, %xmm7
; AVX1-NEXT: vpaddq %xmm6, %xmm7, %xmm6
; AVX1-NEXT: vpsllq $32, %xmm6, %xmm6
; AVX1-NEXT: vpmuludq %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpaddq %xmm6, %xmm3, %xmm3
; AVX1-NEXT: vmovddup {{.*#+}} xmm4 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm4 = mem[0,0]
; AVX1-NEXT: vpand %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm4, %xmm5, %xmm3
; AVX1-NEXT: vpackusdw %xmm0, %xmm3, %xmm0
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm4, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm4, %xmm10, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpand %xmm4, %xmm9, %xmm2
; AVX1-NEXT: vpand %xmm4, %xmm8, %xmm3
; AVX1-NEXT: vpackusdw %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm7 = ymm7[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm7 = ymm7[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld %xmm7, %xmm3, %xmm3
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm6 = ymm6[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm6 = ymm6[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld %xmm6, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm6 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm6, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm5 = ymm5[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm5 = ymm5[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld %xmm5, %xmm1, %xmm1
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm4 = ymm4[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm4 = ymm4[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm6, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm8 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm7, %ymm8, %ymm7
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm8, %ymm3
; AVX2-FAST-NEXT: vpmulld %xmm7, %xmm3, %xmm3
; AVX2-FAST-NEXT: vpermd %ymm6, %ymm8, %ymm6
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm8, %ymm2
; AVX2-FAST-NEXT: vpmulld %xmm6, %xmm2, %xmm2
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm6 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm6, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm5, %ymm8, %ymm5
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm8, %ymm1
; AVX2-FAST-NEXT: vpmulld %xmm5, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpermd %ymm4, %ymm8, %ymm4
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm8, %ymm0
; AVX2-FAST-NEXT: vpmulld %xmm4, %xmm0, %xmm0
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm6, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: trunc_mul_v16i64_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovqd %zmm3, %ymm3
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
; AVX512F-NEXT: vpmulld %ymm3, %ymm1, %ymm1
; AVX512F-NEXT: vpmovqd %zmm2, %ymm2
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
; AVX512F-NEXT: vpmulld %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_mul_v16i64_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpmovqd %zmm3, %ymm3
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT: vpmulld %ymm3, %ymm1, %ymm1
; AVX512BW-NEXT: vpmovqd %zmm2, %ymm2
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT: vpmulld %ymm2, %ymm0, %ymm0
; AVX512BW-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovdb %zmm0, %xmm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_mul_v16i64_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpmullq %zmm3, %zmm1, %zmm1
; AVX512DQ-NEXT: vpmullq %zmm2, %zmm0, %zmm0
; AVX512DQ-NEXT: vpmovqd %zmm0, %ymm0
; AVX512DQ-NEXT: vpmovqd %zmm1, %ymm1
; AVX512DQ-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = mul <16 x i64> %a0, %a1
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_mul_v16i32_v16i8(<16 x i32> %a0, <16 x i32> %a1) nounwind {
; SSE-LABEL: trunc_mul_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm8 = xmm0[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
; SSE-NEXT: pmuludq %xmm8, %xmm4
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm1[1,1,3,3]
; SSE-NEXT: pmuludq %xmm5, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm5
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm2[1,1,3,3]
; SSE-NEXT: pmuludq %xmm6, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm5
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm3[1,1,3,3]
; SSE-NEXT: pmuludq %xmm7, %xmm3
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm5
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmulld %xmm2, %xmm0, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpmulld %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpmulld %xmm3, %xmm1, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpmulld %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vpand %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm3, %xmm4, %xmm2
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_v16i32_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmulld %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpmulld %ymm3, %ymm1, %ymm1
; 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: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_mul_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmulld %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <16 x i32> %a0, %a1
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_mul_v16i16_v16i8(<16 x i16> %a0, <16 x i16> %a1) nounwind {
; SSE-LABEL: trunc_mul_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: pmullw %xmm2, %xmm0
; SSE-NEXT: pmullw %xmm3, %xmm1
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_mul_v16i16_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmullw %ymm1, %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, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_mul_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpmullw %ymm1, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_mul_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpmullw %ymm1, %ymm0, %ymm0
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = mul <16 x i16> %a0, %a1
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
define <8 x i16> @trunc_mul_v8i32_v8i16_zext_8i8(<16 x i8> %a0, <8 x i32> %a1) {
; SSE-LABEL: trunc_mul_v8i32_v8i16_zext_8i8:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm3, %xmm3
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
; SSE-NEXT: pslld $16, %xmm2
; SSE-NEXT: psrad $16, %xmm2
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: packssdw %xmm2, %xmm1
; SSE-NEXT: pmullw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_v8i32_v8i16_zext_8i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %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, %xmm1, %xmm1
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX1-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_v8i32_v8i16_zext_8i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm0 = 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: vpshufb {{.*#+}} ymm1 = ymm1[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 {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_mul_v8i32_v8i16_zext_8i8:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512-NEXT: vpmovdw %zmm1, %ymm1
; AVX512-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX512-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = shufflevector <16 x i8> %a0, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = zext <8 x i8> %1 to <8 x i32>
%3 = mul <8 x i32> %2, %a1
%4 = trunc <8 x i32> %3 to <8 x i16>
ret <8 x i16> %4
}
;
; mul to constant
;
define <4 x i32> @trunc_mul_const_v4i64_v4i32(<4 x i64> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: movl $1, %eax
; SSE-NEXT: movq %rax, %xmm2
; SSE-NEXT: pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1,2,3,4,5,6,7]
; SSE-NEXT: pmuludq %xmm2, %xmm0
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm1
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX1-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_const_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_const_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_mul_const_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <4 x i64> %a0, <i64 0, i64 1, i64 2, i64 3>
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_mul_const_v8i64_v8i16(<8 x i64> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_const_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_const_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; 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: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_mul_const_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <8 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_mul_const_v8i32_v8i16(<8 x i32> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v8i32_v8i16:
; AVX1: # %bb.0:
; 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: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_const_v8i32_v8i16:
; AVX2: # %bb.0:
; 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: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_mul_const_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <8 x i32> %a0, <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_mul_const_v16i64_v16i8(<16 x i64> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movl $1, %eax
; SSE-NEXT: movq %rax, %xmm8
; SSE-NEXT: pslldq {{.*#+}} xmm8 = zero,zero,zero,zero,zero,zero,zero,zero,xmm8[0,1,2,3,4,5,6,7]
; SSE-NEXT: pmuludq %xmm8, %xmm0
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm1
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm2
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm3
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm4
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm5
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm6
; SSE-NEXT: pmuludq {{.*}}(%rip), %xmm7
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: movl $1, %eax
; AVX1-NEXT: vmovq %rax, %xmm4
; AVX1-NEXT: vpslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0,1,2,3,4,5,6,7]
; AVX1-NEXT: vpmuludq %xmm4, %xmm0, %xmm5
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm6
; AVX1-NEXT: vpmuludq %xmm4, %xmm6, %xmm4
; AVX1-NEXT: vpsllq $32, %xmm4, %xmm4
; AVX1-NEXT: vpaddq %xmm4, %xmm5, %xmm8
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm5 = [2,3]
; AVX1-NEXT: vpmuludq %xmm5, %xmm0, %xmm6
; AVX1-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX1-NEXT: vpmuludq %xmm5, %xmm0, %xmm0
; AVX1-NEXT: vpsllq $32, %xmm0, %xmm0
; AVX1-NEXT: vpaddq %xmm0, %xmm6, %xmm9
; AVX1-NEXT: vmovdqa {{.*#+}} xmm5 = [4,5]
; AVX1-NEXT: vpmuludq %xmm5, %xmm1, %xmm6
; AVX1-NEXT: vpsrlq $32, %xmm1, %xmm7
; AVX1-NEXT: vpmuludq %xmm5, %xmm7, %xmm5
; AVX1-NEXT: vpsllq $32, %xmm5, %xmm5
; AVX1-NEXT: vpaddq %xmm5, %xmm6, %xmm5
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [6,7]
; AVX1-NEXT: vpmuludq %xmm6, %xmm1, %xmm7
; AVX1-NEXT: vpsrlq $32, %xmm1, %xmm1
; AVX1-NEXT: vpmuludq %xmm6, %xmm1, %xmm1
; AVX1-NEXT: vpsllq $32, %xmm1, %xmm1
; AVX1-NEXT: vpaddq %xmm1, %xmm7, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [8,9]
; AVX1-NEXT: vpmuludq %xmm6, %xmm2, %xmm7
; AVX1-NEXT: vpsrlq $32, %xmm2, %xmm4
; AVX1-NEXT: vpmuludq %xmm6, %xmm4, %xmm4
; AVX1-NEXT: vpsllq $32, %xmm4, %xmm4
; AVX1-NEXT: vpaddq %xmm4, %xmm7, %xmm4
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [10,11]
; AVX1-NEXT: vpmuludq %xmm6, %xmm2, %xmm7
; AVX1-NEXT: vpsrlq $32, %xmm2, %xmm2
; AVX1-NEXT: vpmuludq %xmm6, %xmm2, %xmm2
; AVX1-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX1-NEXT: vpaddq %xmm2, %xmm7, %xmm2
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [12,13]
; AVX1-NEXT: vpmuludq %xmm6, %xmm3, %xmm7
; AVX1-NEXT: vpsrlq $32, %xmm3, %xmm0
; AVX1-NEXT: vpmuludq %xmm6, %xmm0, %xmm0
; AVX1-NEXT: vpsllq $32, %xmm0, %xmm0
; AVX1-NEXT: vpaddq %xmm0, %xmm7, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm3
; AVX1-NEXT: vmovdqa {{.*#+}} xmm6 = [14,15]
; AVX1-NEXT: vpmuludq %xmm6, %xmm3, %xmm7
; AVX1-NEXT: vpsrlq $32, %xmm3, %xmm3
; AVX1-NEXT: vpmuludq %xmm6, %xmm3, %xmm3
; AVX1-NEXT: vpsllq $32, %xmm3, %xmm3
; AVX1-NEXT: vpaddq %xmm3, %xmm7, %xmm3
; AVX1-NEXT: vmovddup {{.*#+}} xmm6 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm6 = mem[0,0]
; AVX1-NEXT: vpand %xmm6, %xmm3, %xmm3
; AVX1-NEXT: vpand %xmm6, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm6, %xmm2, %xmm2
; AVX1-NEXT: vpand %xmm6, %xmm4, %xmm3
; AVX1-NEXT: vpackusdw %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpand %xmm6, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm6, %xmm5, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpand %xmm6, %xmm9, %xmm2
; AVX1-NEXT: vpand %xmm6, %xmm8, %xmm3
; AVX1-NEXT: vpackusdw %xmm2, %xmm3, %xmm2
; AVX1-NEXT: vpackusdw %xmm1, %xmm2, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_mul_const_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld {{.*}}(%rip), %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld {{.*}}(%rip), %xmm3, %xmm3
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpmulld {{.*}}(%rip), %xmm1, %xmm1
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: trunc_mul_const_v16i64_v16i8:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermd %ymm2, %ymm4, %ymm2
; AVX2-FAST-NEXT: vpmulld {{.*}}(%rip), %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm3, %ymm4, %ymm3
; AVX2-FAST-NEXT: vpmulld {{.*}}(%rip), %xmm3, %xmm3
; AVX2-FAST-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-FAST-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-FAST-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm2, %xmm2
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm4, %ymm0
; AVX2-FAST-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX2-FAST-NEXT: vpermd %ymm1, %ymm4, %ymm1
; AVX2-FAST-NEXT: vpmulld {{.*}}(%rip), %xmm1, %xmm1
; AVX2-FAST-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX2-FAST-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-FAST-NEXT: vpand %xmm5, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_mul_const_v16i64_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: vpmulld {{.*}}(%rip), %ymm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm1, %ymm1
; AVX512-NEXT: vpmulld {{.*}}(%rip), %ymm1, %ymm1
; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <16 x i64> %a0, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%2 = trunc <16 x i64> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_mul_const_v16i32_v16i8(<16 x i32> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v16i32_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [0,1,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
; SSE-NEXT: pmuludq %xmm5, %xmm4
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm1[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
; SSE-NEXT: pmuludq %xmm5, %xmm4
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [8,9,10,11]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm2[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
; SSE-NEXT: pmuludq %xmm5, %xmm4
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [12,13,14,15]
; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,1,3,3]
; SSE-NEXT: pmuludq %xmm4, %xmm3
; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
; SSE-NEXT: pmuludq %xmm5, %xmm4
; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT: pand %xmm4, %xmm3
; SSE-NEXT: pand %xmm4, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm4, %xmm1
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v16i32_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vpmulld {{.*}}(%rip), %xmm1, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
; AVX1-NEXT: vpmulld {{.*}}(%rip), %xmm1, %xmm1
; AVX1-NEXT: vbroadcastss {{.*#+}} xmm4 = [3.57331108E-43,3.57331108E-43,3.57331108E-43,3.57331108E-43]
; AVX1-NEXT: vpand %xmm4, %xmm1, %xmm1
; AVX1-NEXT: vpand %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vpackusdw %xmm1, %xmm3, %xmm1
; AVX1-NEXT: vpand %xmm4, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm0, %xmm2, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_const_v16i32_v16i8:
; 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, %ymm1, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT: vpmullw {{.*}}(%rip), %xmm1, %xmm1
; 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: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm3, %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_mul_const_v16i32_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmulld {{.*}}(%rip), %zmm0, %zmm0
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = mul <16 x i32> %a0, <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>
%2 = trunc <16 x i32> %1 to <16 x i8>
ret <16 x i8> %2
}
define <16 x i8> @trunc_mul_const_v16i16_v16i8(<16 x i16> %a0) nounwind {
; SSE-LABEL: trunc_mul_const_v16i16_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm0
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm1
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm1
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_mul_const_v16i16_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpmullw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpackuswb %xmm0, %xmm1, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_mul_const_v16i16_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_mul_const_v16i16_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmullw {{.*}}(%rip), %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, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_mul_const_v16i16_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512DQ-LABEL: trunc_mul_const_v16i16_v16i8:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
; AVX512DQ-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
; AVX512DQ-NEXT: vpmovdb %zmm0, %xmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
%1 = mul <16 x i16> %a0, <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>
%2 = trunc <16 x i16> %1 to <16 x i8>
ret <16 x i8> %2
}
;
; and
;
define <4 x i32> @trunc_and_v4i64_v4i32(<4 x i64> %a0, <4 x i64> %a1) nounwind {
; SSE-LABEL: trunc_and_v4i64_v4i32:
; SSE: # %bb.0:
; SSE-NEXT: andps %xmm3, %xmm1
; SSE-NEXT: andps %xmm2, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_and_v4i64_v4i32:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_and_v4i64_v4i32:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vandps %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermpd {{.*#+}} 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: trunc_and_v4i64_v4i32:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vandps %ymm1, %ymm0, %ymm0
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm1, %ymm0
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512-LABEL: trunc_and_v4i64_v4i32:
; AVX512: # %bb.0:
; AVX512-NEXT: vpand %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovqd %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = and <4 x i64> %a0, %a1
%2 = trunc <4 x i64> %1 to <4 x i32>
ret <4 x i32> %2
}
define <8 x i16> @trunc_and_v8i64_v8i16(<8 x i64> %a0, <8 x i64> %a1) nounwind {
; SSE-LABEL: trunc_and_v8i64_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pand %xmm6, %xmm2
; SSE-NEXT: pand %xmm7, %xmm3
; SSE-NEXT: pand %xmm4, %xmm0
; SSE-NEXT: pand %xmm5, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm0[0,2,2,3,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,2,4,5,6,7]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_and_v8i64_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vandps %ymm3, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vxorps %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_and_v8i64_v8i16:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpand %ymm3, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $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: trunc_and_v8i64_v8i16:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vpand %ymm3, %ymm1, %ymm1
; AVX2-FAST-NEXT: vpand %ymm2, %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: 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: trunc_and_v8i64_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpandq %zmm1, %zmm0, %zmm0
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = and <8 x i64> %a0, %a1
%2 = trunc <8 x i64> %1 to <8 x i16>
ret <8 x i16> %2
}
define <8 x i16> @trunc_and_v8i32_v8i16(<8 x i32> %a0, <8 x i32> %a1) nounwind {
; SSE-LABEL: trunc_and_v8i32_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: pand %xmm2, %xmm0
; SSE-NEXT: pand %xmm3, %xmm1
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_and_v8i32_v8i16:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
; 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: trunc_and_v8i32_v8i16:
; AVX2: # %bb.0:
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
; 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
;
; AVX512-LABEL: trunc_and_v8i32_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vpand %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpmovdw %zmm0, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%1 = and <8 x i32> %a0, %a1
%2 = trunc <8 x i32> %1 to <8 x i16>
ret <8 x i16> %2
}
define <16 x i8> @trunc_and_v16i64_v16i8(<16 x i64> %a0, <16 x i64> %a1) nounwind {
; SSE-LABEL: trunc_and_v16i64_v16i8:
; SSE: # %bb.0:
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm0
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm1
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm2
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm3
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm4
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm5
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm6
; SSE-NEXT: pand {{[0-9]+}}(%rsp), %xmm7
; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT: pand %xmm8, %xmm7
; SSE-NEXT: pand %xmm8, %xmm6
; SSE-NEXT: packuswb %xmm7, %xmm6
; SSE-NEXT: pand %xmm8, %xmm5
; SSE-NEXT: pand %xmm8, %xmm4
; SSE-NEXT: packuswb %xmm5, %xmm4
; SSE-NEXT: packuswb %xmm6, %xmm4
; SSE-NEXT: pand %xmm8, %xmm3
; SSE-NEXT: pand %xmm8, %xmm2
; SSE-NEXT: packuswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm8, %xmm1
; SSE-NEXT: pand %xmm8, %xmm0
; SSE-NEXT: packuswb %xmm1, %xmm0
; SSE-NEXT: packuswb %xmm2, %xmm0
; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_and_v16i64_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vandpd %ymm4, %ymm0, %ymm0
; AVX1-NEXT: vandpd %ymm5, %ymm1, %ymm1
; AVX1-NEXT: vandpd %ymm6, %ymm2, %ymm2
; AVX1-NEXT: vandpd %ymm7, %ymm3, %ymm3
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
; AVX1-NEXT: vmovddup {{.*#+}} xmm5 = [1.2598673968951787E-321,1.2598673968951787E-321]
; AVX1-NEXT: # xmm5 = mem[0,0]
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vpackusdw %xmm4, %xmm3, %xmm3
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm4, %xmm4
; AVX1-NEXT: vandpd %xmm5, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm4, %xmm2, %xmm2
; AVX1-NEXT: vpackusdw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm1, %xmm1
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm3, %xmm3
; AVX1-NEXT: vandpd %xmm5, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: trunc_and_v16i64_v16i8:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpand %ymm5, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vpand %ymm4, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpand %ymm7, %ymm3, %ymm3
; AVX2-SLOW-NEXT: vpand %ymm6, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm2 = ymm2[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm3 = ymm3[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,2,2,3]
; AVX2-SLOW-NEXT: vinserti128 $1, %xmm3, %ymm2, %ymm2
; AVX2-SLOW-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-SLOW-NEXT: vpshufb %ymm3, %ymm2, %ymm2
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
; AVX2-SLOW-NEXT: vmovdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; AVX2-SLOW-NEXT: vpand %xmm4, %xmm2, %xmm2
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-SLOW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]