llvm-project/llvm/test/CodeGen/X86/vector-reduce-and-bool.ll

1860 lines
61 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VL
;
; Truncate
;
define i1 @trunc_v2i64_v2i1(<2 x i64>) {
; SSE-LABEL: trunc_v2i64_v2i1:
; SSE: # %bb.0:
; SSE-NEXT: psllq $63, %xmm0
; SSE-NEXT: movmskpd %xmm0, %eax
; SSE-NEXT: cmpb $3, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_v2i64_v2i1:
; AVX: # %bb.0:
; AVX-NEXT: vpsllq $63, %xmm0, %xmm0
; AVX-NEXT: vmovmskpd %xmm0, %eax
; AVX-NEXT: cmpb $3, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: trunc_v2i64_v2i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsllq $63, %xmm0, %xmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $3, %al
; AVX512F-NEXT: cmpb $3, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v2i64_v2i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllq $63, %xmm0, %xmm0
; AVX512BW-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $3, %al
; AVX512BW-NEXT: cmpb $3, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v2i64_v2i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllq $63, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmq %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $3, %al
; AVX512VL-NEXT: cmpb $3, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = trunc <2 x i64> %0 to <2 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v2i1(<2 x i1> %a)
ret i1 %b
}
define i1 @trunc_v4i32_v4i1(<4 x i32>) {
; SSE-LABEL: trunc_v4i32_v4i1:
; SSE: # %bb.0:
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: movmskps %xmm0, %eax
; SSE-NEXT: cmpb $15, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_v4i32_v4i1:
; AVX: # %bb.0:
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: cmpb $15, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: trunc_v4i32_v4i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $15, %al
; AVX512F-NEXT: cmpb $15, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v4i32_v4i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512BW-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $15, %al
; AVX512BW-NEXT: cmpb $15, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v4i32_v4i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $15, %al
; AVX512VL-NEXT: cmpb $15, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = trunc <4 x i32> %0 to <4 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v4i1(<4 x i1> %a)
ret i1 %b
}
define i1 @trunc_v8i16_v8i1(<8 x i8>) {
; SSE2-LABEL: trunc_v8i16_v8i1:
; SSE2: # %bb.0:
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE2-NEXT: psllw $15, %xmm0
; SSE2-NEXT: packsswb %xmm0, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpb $-1, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v8i16_v8i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pmovzxbw {{.*#+}} 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
; SSE41-NEXT: psllw $15, %xmm0
; SSE41-NEXT: packsswb %xmm0, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpb $-1, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX-LABEL: trunc_v8i16_v8i1:
; AVX: # %bb.0:
; AVX-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
; AVX-NEXT: vpsllw $15, %xmm0, %xmm0
; AVX-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX-NEXT: vpmovmskb %xmm0, %eax
; AVX-NEXT: cmpb $-1, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: trunc_v8i16_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v8i16_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX512BW-NEXT: vpmovb2m %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v8i16_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX512VL-NEXT: vpmovb2m %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = trunc <8 x i8> %0 to <8 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @trunc_v16i8_v16i1(<16 x i8>) {
; SSE-LABEL: trunc_v16i8_v16i1:
; SSE: # %bb.0:
; SSE-NEXT: psllw $7, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_v16i8_v16i1:
; AVX: # %bb.0:
; AVX-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX-NEXT: vpmovmskb %xmm0, %eax
; AVX-NEXT: cmpw $-1, %ax
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512-LABEL: trunc_v16i8_v16i1:
; AVX512: # %bb.0:
; AVX512-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX512-NEXT: vpmovmskb %xmm0, %eax
; AVX512-NEXT: cmpw $-1, %ax
; AVX512-NEXT: sete %al
; AVX512-NEXT: retq
%a = trunc <16 x i8> %0 to <16 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @trunc_v4i64_v4i1(<4 x i64>) {
; SSE-LABEL: trunc_v4i64_v4i1:
; SSE: # %bb.0:
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: movmskps %xmm0, %eax
; SSE-NEXT: cmpb $15, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: trunc_v4i64_v4i1:
; AVX: # %bb.0:
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: cmpb $15, %al
; AVX-NEXT: sete %al
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
;
; AVX512F-LABEL: trunc_v4i64_v4i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsllq $63, %ymm0, %ymm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $15, %al
; AVX512F-NEXT: cmpb $15, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v4i64_v4i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllq $63, %ymm0, %ymm0
; AVX512BW-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $15, %al
; AVX512BW-NEXT: cmpb $15, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v4i64_v4i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllq $63, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmq %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $15, %al
; AVX512VL-NEXT: cmpb $15, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <4 x i64> %0 to <4 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v4i1(<4 x i1> %a)
ret i1 %b
}
define i1 @trunc_v8i32_v8i1(<8 x i32>) {
; SSE2-LABEL: trunc_v8i32_v8i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pslld $16, %xmm1
; SSE2-NEXT: psrad $16, %xmm1
; SSE2-NEXT: pslld $16, %xmm0
; SSE2-NEXT: psrad $16, %xmm0
; SSE2-NEXT: packssdw %xmm1, %xmm0
; SSE2-NEXT: psllw $15, %xmm0
; SSE2-NEXT: packsswb %xmm0, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpb $-1, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v8i32_v8i1:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: psllw $15, %xmm0
; SSE41-NEXT: packsswb %xmm0, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpb $-1, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v8i32_v8i1:
; 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: vpsllw $15, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpb $-1, %al
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v8i32_v8i1:
; 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: vpsllw $15, %xmm0, %xmm0
; AVX2-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpb $-1, %al
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v8i32_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v8i32_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512BW-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v8i32_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <8 x i32> %0 to <8 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @trunc_v16i16_v16i1(<16 x i16>) {
; SSE2-LABEL: trunc_v16i16_v16i1:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: psllw $7, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpw $-1, %ax
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v16i16_v16i1:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm2, %xmm1
; SSE41-NEXT: pshufb %xmm2, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: psllw $7, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpw $-1, %ax
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v16i16_v16i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v16i16_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpw $-1, %ax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v16i16_v16i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kortestw %k0, %k0
; AVX512F-NEXT: setb %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v16i16_v16i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllw $15, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovw2m %zmm0, %k0
; AVX512BW-NEXT: kortestw %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v16i16_v16i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllw $15, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovw2m %ymm0, %k0
; AVX512VL-NEXT: kortestw %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <16 x i16> %0 to <16 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @trunc_v32i8_v32i1(<32 x i8>) {
; SSE-LABEL: trunc_v32i8_v32i1:
; SSE: # %bb.0:
; SSE-NEXT: pand %xmm1, %xmm0
; SSE-NEXT: psllw $7, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: trunc_v32i8_v32i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v32i8_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpsllw $7, %ymm0, %ymm0
; AVX2-NEXT: vpmovmskb %ymm0, %eax
; AVX2-NEXT: cmpl $-1, %eax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v32i8_v32i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v32i8_v32i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllw $7, %ymm0, %ymm0
; AVX512BW-NEXT: vpmovmskb %ymm0, %eax
; AVX512BW-NEXT: cmpl $-1, %eax
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v32i8_v32i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllw $7, %ymm0, %ymm0
; AVX512VL-NEXT: vpmovmskb %ymm0, %eax
; AVX512VL-NEXT: cmpl $-1, %eax
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <32 x i8> %0 to <32 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v32i1(<32 x i1> %a)
ret i1 %b
}
define i1 @trunc_v8i64_v8i1(<8 x i64>) {
; SSE2-LABEL: trunc_v8i64_v8i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm3[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
; SSE2-NEXT: psllw $15, %xmm2
; SSE2-NEXT: packsswb %xmm0, %xmm2
; SSE2-NEXT: pmovmskb %xmm2, %eax
; SSE2-NEXT: cmpb $-1, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v8i64_v8i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packusdw %xmm2, %xmm0
; SSE41-NEXT: psllw $15, %xmm0
; SSE41-NEXT: packsswb %xmm0, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpb $-1, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v8i64_v8i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [65535,65535,65535,65535]
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $15, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpb $-1, %al
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v8i64_v8i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX2-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX2-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %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: vpsllw $15, %xmm0, %xmm0
; AVX2-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpb $-1, %al
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v8i64_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v8i64_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512BW-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v8i64_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512VL-NEXT: vptestmq %zmm0, %zmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <8 x i64> %0 to <8 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @trunc_v16i32_v16i1(<16 x i32>) {
; SSE2-LABEL: trunc_v16i32_v16i1:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: packuswb %xmm2, %xmm0
; SSE2-NEXT: psllw $7, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpw $-1, %ax
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v16i32_v16i1:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE41-NEXT: pand %xmm4, %xmm3
; SSE41-NEXT: pand %xmm4, %xmm2
; SSE41-NEXT: packusdw %xmm3, %xmm2
; SSE41-NEXT: pand %xmm4, %xmm1
; SSE41-NEXT: pand %xmm4, %xmm0
; SSE41-NEXT: packusdw %xmm1, %xmm0
; SSE41-NEXT: packuswb %xmm2, %xmm0
; SSE41-NEXT: psllw $7, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpw $-1, %ax
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v16i32_v16i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovaps {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255]
; AVX1-NEXT: vandps %ymm2, %ymm1, %ymm1
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
; AVX1-NEXT: vpackusdw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v16i32_v16i1:
; 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: vpsllw $7, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpw $-1, %ax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: trunc_v16i32_v16i1:
; AVX512: # %bb.0:
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512-NEXT: kortestw %k0, %k0
; AVX512-NEXT: setb %al
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%a = trunc <16 x i32> %0 to <16 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @trunc_v32i16_v32i1(<32 x i16>) {
; SSE2-LABEL: trunc_v32i16_v32i1:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
; SSE2-NEXT: pand %xmm4, %xmm3
; SSE2-NEXT: pand %xmm4, %xmm2
; SSE2-NEXT: packuswb %xmm3, %xmm2
; SSE2-NEXT: pand %xmm4, %xmm1
; SSE2-NEXT: pand %xmm4, %xmm0
; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: psllw $7, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpw $-1, %ax
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v32i16_v32i1:
; SSE41: # %bb.0:
; SSE41-NEXT: movdqa {{.*#+}} xmm4 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT: pshufb %xmm4, %xmm3
; SSE41-NEXT: pshufb %xmm4, %xmm2
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; SSE41-NEXT: pshufb %xmm4, %xmm1
; SSE41-NEXT: pshufb %xmm4, %xmm0
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT: pand %xmm2, %xmm0
; SSE41-NEXT: psllw $7, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpw $-1, %ax
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v32i16_v32i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v32i16_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpand %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
; AVX2-NEXT: vpackuswb %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vpsllw $7, %ymm0, %ymm0
; AVX2-NEXT: vpmovmskb %ymm0, %eax
; AVX2-NEXT: cmpl $-1, %eax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v32i16_v32i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vpand %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v32i16_v32i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllw $15, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovw2m %zmm0, %k0
; AVX512BW-NEXT: kortestd %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v32i16_v32i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllw $15, %zmm0, %zmm0
; AVX512VL-NEXT: vpmovw2m %zmm0, %k0
; AVX512VL-NEXT: kortestd %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <32 x i16> %0 to <32 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v32i1(<32 x i1> %a)
ret i1 %b
}
define i1 @trunc_v64i8_v64i1(<64 x i8>) {
; SSE2-LABEL: trunc_v64i8_v64i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pand %xmm3, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE2-NEXT: pand %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: psrld $16, %xmm0
; SSE2-NEXT: pand %xmm1, %xmm0
; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: psrlw $8, %xmm1
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: movd %xmm1, %eax
; SSE2-NEXT: # kill: def $al killed $al killed $eax
; SSE2-NEXT: retq
;
; SSE41-LABEL: trunc_v64i8_v64i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pand %xmm3, %xmm1
; SSE41-NEXT: pand %xmm2, %xmm1
; SSE41-NEXT: pand %xmm0, %xmm1
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE41-NEXT: pand %xmm1, %xmm0
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; SSE41-NEXT: pand %xmm0, %xmm1
; SSE41-NEXT: movdqa %xmm1, %xmm0
; SSE41-NEXT: psrld $16, %xmm0
; SSE41-NEXT: pand %xmm1, %xmm0
; SSE41-NEXT: movdqa %xmm0, %xmm1
; SSE41-NEXT: psrlw $8, %xmm1
; SSE41-NEXT: pand %xmm0, %xmm1
; SSE41-NEXT: pextrb $0, %xmm1, %eax
; SSE41-NEXT: # kill: def $al killed $al killed $eax
; SSE41-NEXT: retq
;
; AVX1-LABEL: trunc_v64i8_v64i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX1-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX1-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpextrb $0, %xmm0, %eax
; AVX1-NEXT: # kill: def $al killed $al killed $eax
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: trunc_v64i8_v64i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
; AVX2-NEXT: # kill: def $al killed $al killed $eax
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: trunc_v64i8_v64i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX512F-NEXT: vpand %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: trunc_v64i8_v64i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vpsllw $7, %zmm0, %zmm0
; AVX512BW-NEXT: vpmovb2m %zmm0, %k0
; AVX512BW-NEXT: kshiftrq $32, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $16, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $8, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $4, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $2, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $1, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: # kill: def $al killed $al killed $eax
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: trunc_v64i8_v64i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpsllw $7, %zmm0, %zmm0
; AVX512VL-NEXT: vpmovb2m %zmm0, %k0
; AVX512VL-NEXT: kshiftrq $32, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $16, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $8, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $4, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $2, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $1, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: # kill: def $al killed $al killed $eax
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = trunc <64 x i8> %0 to <64 x i1>
%b = call i1 @llvm.experimental.vector.reduce.and.v64i1(<64 x i1> %a)
ret i1 %b
}
;
; Comparison
;
define i1 @icmp_v2i64_v2i1(<2 x i64>) {
; SSE2-LABEL: icmp_v2i64_v2i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: pcmpeqd %xmm0, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,0,3,2]
; SSE2-NEXT: pand %xmm1, %xmm0
; SSE2-NEXT: movmskpd %xmm0, %eax
; SSE2-NEXT: cmpb $3, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: icmp_v2i64_v2i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: pcmpeqq %xmm0, %xmm1
; SSE41-NEXT: movmskpd %xmm1, %eax
; SSE41-NEXT: cmpb $3, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX-LABEL: icmp_v2i64_v2i1:
; AVX: # %bb.0:
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskpd %xmm0, %eax
; AVX-NEXT: cmpb $3, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: icmp_v2i64_v2i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $3, %al
; AVX512F-NEXT: cmpb $3, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v2i64_v2i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $3, %al
; AVX512BW-NEXT: cmpb $3, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v2i64_v2i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmq %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $3, %al
; AVX512VL-NEXT: cmpb $3, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = icmp eq <2 x i64> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v2i1(<2 x i1> %a)
ret i1 %b
}
define i1 @icmp_v4i32_v4i1(<4 x i32>) {
; SSE-LABEL: icmp_v4i32_v4i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: pcmpeqd %xmm0, %xmm1
; SSE-NEXT: movmskps %xmm1, %eax
; SSE-NEXT: cmpb $15, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: icmp_v4i32_v4i1:
; AVX: # %bb.0:
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovmskps %xmm0, %eax
; AVX-NEXT: cmpb $15, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: icmp_v4i32_v4i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $15, %al
; AVX512F-NEXT: cmpb $15, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v4i32_v4i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $15, %al
; AVX512BW-NEXT: cmpb $15, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v4i32_v4i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmd %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $15, %al
; AVX512VL-NEXT: cmpb $15, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = icmp eq <4 x i32> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v4i1(<4 x i1> %a)
ret i1 %b
}
define i1 @icmp_v8i16_v8i1(<8 x i8>) {
; SSE2-LABEL: icmp_v8i16_v8i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: pcmpeqb %xmm0, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT: packsswb %xmm0, %xmm0
; SSE2-NEXT: pmovmskb %xmm0, %eax
; SSE2-NEXT: cmpb $-1, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: icmp_v8i16_v8i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: pcmpeqb %xmm0, %xmm1
; SSE41-NEXT: pmovsxbw %xmm1, %xmm0
; SSE41-NEXT: packsswb %xmm0, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpb $-1, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX-LABEL: icmp_v8i16_v8i1:
; AVX: # %bb.0:
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpmovsxbw %xmm0, %xmm0
; AVX-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
; AVX-NEXT: vpmovmskb %xmm0, %eax
; AVX-NEXT: cmpb $-1, %al
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: icmp_v8i16_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v8i16_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vptestnmb %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v8i16_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmb %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: retq
%a = icmp eq <8 x i8> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @icmp_v16i8_v16i1(<16 x i8>) {
; SSE-LABEL: icmp_v16i8_v16i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: pcmpeqb %xmm0, %xmm1
; SSE-NEXT: pmovmskb %xmm1, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX-LABEL: icmp_v16i8_v16i1:
; AVX: # %bb.0:
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX-NEXT: vpmovmskb %xmm0, %eax
; AVX-NEXT: cmpw $-1, %ax
; AVX-NEXT: sete %al
; AVX-NEXT: retq
;
; AVX512F-LABEL: icmp_v16i8_v16i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovmskb %xmm0, %eax
; AVX512F-NEXT: cmpw $-1, %ax
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v16i8_v16i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512BW-NEXT: vptestnmb %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kortestw %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v16i8_v16i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmb %xmm0, %xmm0, %k0
; AVX512VL-NEXT: kortestw %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: retq
%a = icmp eq <16 x i8> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @icmp_v4i64_v4i1(<4 x i64>) {
; SSE2-LABEL: icmp_v4i64_v4i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pcmpeqd %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,0,3,2]
; SSE2-NEXT: pand %xmm1, %xmm3
; SSE2-NEXT: pcmpeqd %xmm2, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: packssdw %xmm3, %xmm1
; SSE2-NEXT: movmskps %xmm1, %eax
; SSE2-NEXT: cmpb $15, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: icmp_v4i64_v4i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm2, %xmm2
; SSE41-NEXT: pcmpeqq %xmm2, %xmm1
; SSE41-NEXT: pcmpeqq %xmm2, %xmm0
; SSE41-NEXT: packssdw %xmm1, %xmm0
; SSE41-NEXT: movmskps %xmm0, %eax
; SSE41-NEXT: cmpb $15, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: icmp_v4i64_v4i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovmskpd %ymm0, %eax
; AVX1-NEXT: cmpb $15, %al
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v4i64_v4i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpcmpeqq %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vmovmskpd %ymm0, %eax
; AVX2-NEXT: cmpb $15, %al
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v4i64_v4i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: andb $15, %al
; AVX512F-NEXT: cmpb $15, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v4i64_v4i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: andb $15, %al
; AVX512BW-NEXT: cmpb $15, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v4i64_v4i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmq %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: andb $15, %al
; AVX512VL-NEXT: cmpb $15, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <4 x i64> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v4i1(<4 x i1> %a)
ret i1 %b
}
define i1 @icmp_v8i32_v8i1(<8 x i32>) {
; SSE-LABEL: icmp_v8i32_v8i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm2, %xmm2
; SSE-NEXT: pcmpeqd %xmm2, %xmm1
; SSE-NEXT: pcmpeqd %xmm2, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: packsswb %xmm0, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: cmpb $-1, %al
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v8i32_v8i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovmskps %ymm0, %eax
; AVX1-NEXT: cmpb $-1, %al
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v8i32_v8i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpcmpeqd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vmovmskps %ymm0, %eax
; AVX2-NEXT: cmpb $-1, %al
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v8i32_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v8i32_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v8i32_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <8 x i32> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @icmp_v16i16_v16i1(<16 x i16>) {
; SSE-LABEL: icmp_v16i16_v16i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm2, %xmm2
; SSE-NEXT: pcmpeqw %xmm2, %xmm1
; SSE-NEXT: pcmpeqw %xmm2, %xmm0
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v16i16_v16i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpcmpeqw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v16i16_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpw $-1, %ax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v16i16_v16i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kortestw %k0, %k0
; AVX512F-NEXT: setb %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v16i16_v16i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vptestnmw %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kortestw %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v16i16_v16i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmw %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kortestw %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <16 x i16> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @icmp_v32i8_v32i1(<32 x i8>) {
; SSE-LABEL: icmp_v32i8_v32i1:
; SSE: # %bb.0:
; SSE-NEXT: por %xmm1, %xmm0
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: pcmpeqb %xmm0, %xmm1
; SSE-NEXT: pmovmskb %xmm1, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v32i8_v32i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpcmpeqb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v32i8_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpcmpeqb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpmovmskb %ymm0, %eax
; AVX2-NEXT: cmpl $-1, %eax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v32i8_v32i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpcmpeqb %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v32i8_v32i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
; AVX512BW-NEXT: vptestnmb %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kortestd %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v32i8_v32i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmb %ymm0, %ymm0, %k0
; AVX512VL-NEXT: kortestd %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <32 x i8> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v32i1(<32 x i1> %a)
ret i1 %b
}
define i1 @icmp_v8i64_v8i1(<8 x i64>) {
; SSE2-LABEL: icmp_v8i64_v8i1:
; SSE2: # %bb.0:
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: pcmpeqd %xmm4, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm3[1,0,3,2]
; SSE2-NEXT: pand %xmm3, %xmm5
; SSE2-NEXT: pcmpeqd %xmm4, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,0,3,2]
; SSE2-NEXT: pand %xmm2, %xmm3
; SSE2-NEXT: packssdw %xmm5, %xmm3
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,0,3,2]
; SSE2-NEXT: pand %xmm1, %xmm2
; SSE2-NEXT: pcmpeqd %xmm4, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,0,3,2]
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: packssdw %xmm2, %xmm1
; SSE2-NEXT: packssdw %xmm3, %xmm1
; SSE2-NEXT: packsswb %xmm0, %xmm1
; SSE2-NEXT: pmovmskb %xmm1, %eax
; SSE2-NEXT: cmpb $-1, %al
; SSE2-NEXT: sete %al
; SSE2-NEXT: retq
;
; SSE41-LABEL: icmp_v8i64_v8i1:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm4, %xmm4
; SSE41-NEXT: pcmpeqq %xmm4, %xmm3
; SSE41-NEXT: pcmpeqq %xmm4, %xmm2
; SSE41-NEXT: packssdw %xmm3, %xmm2
; SSE41-NEXT: pcmpeqq %xmm4, %xmm1
; SSE41-NEXT: pcmpeqq %xmm4, %xmm0
; SSE41-NEXT: packssdw %xmm1, %xmm0
; SSE41-NEXT: packssdw %xmm2, %xmm0
; SSE41-NEXT: packsswb %xmm0, %xmm0
; SSE41-NEXT: pmovmskb %xmm0, %eax
; SSE41-NEXT: cmpb $-1, %al
; SSE41-NEXT: sete %al
; SSE41-NEXT: retq
;
; AVX1-LABEL: icmp_v8i64_v8i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqq %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: vmovmskps %ymm0, %eax
; AVX1-NEXT: cmpb $-1, %al
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v8i64_v8i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpcmpeqq %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpcmpeqq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vmovmskps %ymm0, %eax
; AVX2-NEXT: cmpb $-1, %al
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v8i64_v8i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: cmpb $-1, %al
; AVX512F-NEXT: sete %al
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v8i64_v8i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: cmpb $-1, %al
; AVX512BW-NEXT: sete %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v8i64_v8i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmq %zmm0, %zmm0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: cmpb $-1, %al
; AVX512VL-NEXT: sete %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <8 x i64> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1> %a)
ret i1 %b
}
define i1 @icmp_v16i32_v16i1(<16 x i32>) {
; SSE-LABEL: icmp_v16i32_v16i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm4, %xmm4
; SSE-NEXT: pcmpeqd %xmm4, %xmm3
; SSE-NEXT: pcmpeqd %xmm4, %xmm2
; SSE-NEXT: packssdw %xmm3, %xmm2
; SSE-NEXT: pcmpeqd %xmm4, %xmm1
; SSE-NEXT: pcmpeqd %xmm4, %xmm0
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: packsswb %xmm2, %xmm0
; SSE-NEXT: pmovmskb %xmm0, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v16i32_v16i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v16i32_v16i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpmovmskb %xmm0, %eax
; AVX2-NEXT: cmpw $-1, %ax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: icmp_v16i32_v16i1:
; AVX512: # %bb.0:
; AVX512-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512-NEXT: kortestw %k0, %k0
; AVX512-NEXT: setb %al
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%a = icmp eq <16 x i32> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1> %a)
ret i1 %b
}
define i1 @icmp_v32i16_v32i1(<32 x i16>) {
; SSE-LABEL: icmp_v32i16_v32i1:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm4, %xmm4
; SSE-NEXT: pcmpeqw %xmm4, %xmm1
; SSE-NEXT: pcmpeqw %xmm4, %xmm0
; SSE-NEXT: packsswb %xmm1, %xmm0
; SSE-NEXT: pcmpeqw %xmm4, %xmm3
; SSE-NEXT: pcmpeqw %xmm4, %xmm2
; SSE-NEXT: packsswb %xmm3, %xmm2
; SSE-NEXT: pand %xmm0, %xmm2
; SSE-NEXT: pmovmskb %xmm2, %eax
; SSE-NEXT: cmpw $-1, %ax
; SSE-NEXT: sete %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v32i16_v32i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT: vpcmpeqw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqw %xmm3, %xmm1, %xmm1
; AVX1-NEXT: vpacksswb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpcmpeqw %xmm3, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqw %xmm3, %xmm0, %xmm0
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpsllw $7, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpw $-1, %ax
; AVX1-NEXT: sete %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v32i16_v32i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT: vpcmpeqw %ymm2, %ymm1, %ymm1
; AVX2-NEXT: vpcmpeqw %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpacksswb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmovmskb %ymm0, %eax
; AVX2-NEXT: cmpl $-1, %eax
; AVX2-NEXT: sete %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v32i16_v32i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vpor %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT: vpcmpeqw %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: vpmovsxwd %ymm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v32i16_v32i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vptestnmw %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kortestd %k0, %k0
; AVX512BW-NEXT: setb %al
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v32i16_v32i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmw %zmm0, %zmm0, %k0
; AVX512VL-NEXT: kortestd %k0, %k0
; AVX512VL-NEXT: setb %al
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <32 x i16> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v32i1(<32 x i1> %a)
ret i1 %b
}
define i1 @icmp_v64i8_v64i1(<64 x i8>) {
; SSE-LABEL: icmp_v64i8_v64i1:
; SSE: # %bb.0:
; SSE-NEXT: por %xmm3, %xmm1
; SSE-NEXT: pxor %xmm3, %xmm3
; SSE-NEXT: por %xmm2, %xmm1
; SSE-NEXT: por %xmm0, %xmm1
; SSE-NEXT: pcmpeqb %xmm3, %xmm1
; SSE-NEXT: pmovmskb %xmm1, %eax
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
; SSE-NEXT: sete %al
; SSE-NEXT: negb %al
; SSE-NEXT: retq
;
; AVX1-LABEL: icmp_v64i8_v64i1:
; AVX1: # %bb.0:
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpcmpeqb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpmovmskb %xmm0, %eax
; AVX1-NEXT: cmpl $65535, %eax # imm = 0xFFFF
; AVX1-NEXT: sete %al
; AVX1-NEXT: negb %al
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: icmp_v64i8_v64i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpcmpeqb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpmovmskb %ymm0, %eax
; AVX2-NEXT: cmpl $-1, %eax
; AVX2-NEXT: sete %al
; AVX2-NEXT: negb %al
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: icmp_v64i8_v64i1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT: vpcmpeqb %ymm2, %ymm1, %ymm1
; AVX512F-NEXT: vpcmpeqb %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX512F-NEXT: vpand %xmm2, %xmm3, %xmm2
; AVX512F-NEXT: vpand %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpand %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kshiftrw $1, %k0, %k1
; AVX512F-NEXT: kandw %k1, %k0, %k0
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: # kill: def $al killed $al killed $eax
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512BW-LABEL: icmp_v64i8_v64i1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vptestnmb %zmm0, %zmm0, %k0
; AVX512BW-NEXT: kshiftrq $32, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $16, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $8, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $4, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $2, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kshiftrq $1, %k0, %k1
; AVX512BW-NEXT: kandq %k1, %k0, %k0
; AVX512BW-NEXT: kmovd %k0, %eax
; AVX512BW-NEXT: # kill: def $al killed $al killed $eax
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512VL-LABEL: icmp_v64i8_v64i1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vptestnmb %zmm0, %zmm0, %k0
; AVX512VL-NEXT: kshiftrq $32, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $16, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $8, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $4, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $2, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kshiftrq $1, %k0, %k1
; AVX512VL-NEXT: kandq %k1, %k0, %k0
; AVX512VL-NEXT: kmovd %k0, %eax
; AVX512VL-NEXT: # kill: def $al killed $al killed $eax
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
%a = icmp eq <64 x i8> %0, zeroinitializer
%b = call i1 @llvm.experimental.vector.reduce.and.v64i1(<64 x i1> %a)
ret i1 %b
}
declare i1 @llvm.experimental.vector.reduce.and.v2i1(<2 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.v4i1(<4 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.v8i1(<8 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.v16i1(<16 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.v32i1(<32 x i1>)
declare i1 @llvm.experimental.vector.reduce.and.v64i1(<64 x i1>)