forked from OSchip/llvm-project
4604 lines
180 KiB
LLVM
4604 lines
180 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=sse2 | FileCheck %s --check-prefixes=SSE,SSE2
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=sse4.2 | FileCheck %s --check-prefixes=SSE,SSE42
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx | FileCheck %s --check-prefixes=AVX,AVX1OR2,AVX1
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx2 | FileCheck %s --check-prefixes=AVX,AVX1OR2,AVX2
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx512f | FileCheck %s --check-prefixes=AVX,AVX512,AVX512F
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx512f,avx512dq,avx512vl | FileCheck %s --check-prefixes=AVX,AVX512,AVX512VL,AVX512VLDQ
|
|
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx512f,avx512bw,avx512vl | FileCheck %s --check-prefixes=AVX,AVX512,AVX512VL,AVX512VLBW
|
|
|
|
;
|
|
; vXf64
|
|
;
|
|
|
|
define <2 x double> @expandload_v2f64_v2i64(double* %base, <2 x double> %src0, <2 x i64> %trigger) {
|
|
; SSE2-LABEL: expandload_v2f64_v2i64:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,0,3,2]
|
|
; SSE2-NEXT: pand %xmm2, %xmm1
|
|
; SSE2-NEXT: movd %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB0_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB0_2: ## %else
|
|
; SSE2-NEXT: pextrw $4, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB0_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE2-NEXT: LBB0_4: ## %else2
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v2f64_v2i64:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqq %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB0_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB0_2: ## %else
|
|
; SSE42-NEXT: pextrb $8, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB0_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE42-NEXT: LBB0_4: ## %else2
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v2f64_v2i64:
|
|
; AVX1OR2: ## %bb.0:
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
|
|
; AVX1OR2-NEXT: vpextrb $0, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB0_2
|
|
; AVX1OR2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1OR2-NEXT: vmovlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB0_2: ## %else
|
|
; AVX1OR2-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB0_4
|
|
; AVX1OR2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1OR2-NEXT: vmovhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; AVX1OR2-NEXT: LBB0_4: ## %else2
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v2f64_v2i64:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
|
|
; AVX512F-NEXT: vptestnmq %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftlw $14, %k0, %k0
|
|
; AVX512F-NEXT: kshiftrw $14, %k0, %k1
|
|
; AVX512F-NEXT: vexpandpd (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: expandload_v2f64_v2i64:
|
|
; AVX512VL: ## %bb.0:
|
|
; AVX512VL-NEXT: vptestnmq %xmm1, %xmm1, %k1
|
|
; AVX512VL-NEXT: vexpandpd (%rdi), %xmm0 {%k1}
|
|
; AVX512VL-NEXT: retq
|
|
%mask = icmp eq <2 x i64> %trigger, zeroinitializer
|
|
%res = call <2 x double> @llvm.masked.expandload.v2f64(double* %base, <2 x i1> %mask, <2 x double> %src0)
|
|
ret <2 x double>%res
|
|
}
|
|
|
|
define <4 x double> @expandload_v4f64_v4i64(double* %base, <4 x double> %src0, <4 x i64> %trigger) {
|
|
; SSE2-LABEL: expandload_v4f64_v4i64:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pxor %xmm4, %xmm4
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm4
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm4[1,0,3,2]
|
|
; SSE2-NEXT: pand %xmm4, %xmm2
|
|
; SSE2-NEXT: movd %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB1_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB1_2: ## %else
|
|
; SSE2-NEXT: pextrw $4, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB1_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB1_4: ## %else2
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm3[1,0,3,2]
|
|
; SSE2-NEXT: pand %xmm3, %xmm2
|
|
; SSE2-NEXT: pextrw $0, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB1_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB1_6: ## %else6
|
|
; SSE2-NEXT: pextrw $4, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB1_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE2-NEXT: LBB1_8: ## %else10
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v4f64_v4i64:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm4, %xmm4
|
|
; SSE42-NEXT: pcmpeqq %xmm2, %xmm4
|
|
; SSE42-NEXT: pextrb $0, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB1_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB1_2: ## %else
|
|
; SSE42-NEXT: pextrb $8, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB1_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB1_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqq %xmm2, %xmm3
|
|
; SSE42-NEXT: pextrb $0, %xmm3, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB1_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB1_6: ## %else6
|
|
; SSE42-NEXT: pextrb $8, %xmm3, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB1_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE42-NEXT: LBB1_8: ## %else10
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: expandload_v4f64_v4i64:
|
|
; AVX1: ## %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm3
|
|
; AVX1-NEXT: vpextrb $0, %xmm3, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB1_2
|
|
; AVX1-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1-NEXT: vmovsd {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1],ymm0[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB1_2: ## %else
|
|
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm2
|
|
; AVX1-NEXT: vpextrb $8, %xmm2, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB1_4
|
|
; AVX1-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm2 = xmm0[0,1],mem[0,1]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB1_4: ## %else2
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
|
|
; AVX1-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpextrb $0, %xmm1, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB1_6
|
|
; AVX1-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
|
|
; AVX1-NEXT: vmovlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB1_6: ## %else6
|
|
; AVX1-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB1_8
|
|
; AVX1-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX1-NEXT: LBB1_8: ## %else10
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: expandload_v4f64_v4i64:
|
|
; AVX2: ## %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm3
|
|
; AVX2-NEXT: vpextrb $0, %xmm3, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB1_2
|
|
; AVX2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX2-NEXT: vmovq {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm3[0,1],ymm0[2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB1_2: ## %else
|
|
; AVX2-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm2
|
|
; AVX2-NEXT: vpextrb $8, %xmm2, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB1_4
|
|
; AVX2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm2 = xmm0[0,1],mem[0,1]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB1_4: ## %else2
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpextrb $0, %xmm1, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB1_6
|
|
; AVX2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
|
|
; AVX2-NEXT: vmovlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB1_6: ## %else6
|
|
; AVX2-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB1_8
|
|
; AVX2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
|
; AVX2-NEXT: LBB1_8: ## %else10
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v4f64_v4i64:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $ymm1 killed $ymm1 def $zmm1
|
|
; AVX512F-NEXT: ## kill: def $ymm0 killed $ymm0 def $zmm0
|
|
; AVX512F-NEXT: vptestnmq %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftlw $12, %k0, %k0
|
|
; AVX512F-NEXT: kshiftrw $12, %k0, %k1
|
|
; AVX512F-NEXT: vexpandpd (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $ymm0 killed $ymm0 killed $zmm0
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: expandload_v4f64_v4i64:
|
|
; AVX512VL: ## %bb.0:
|
|
; AVX512VL-NEXT: vptestnmq %ymm1, %ymm1, %k1
|
|
; AVX512VL-NEXT: vexpandpd (%rdi), %ymm0 {%k1}
|
|
; AVX512VL-NEXT: retq
|
|
%mask = icmp eq <4 x i64> %trigger, zeroinitializer
|
|
%res = call <4 x double> @llvm.masked.expandload.v4f64(double* %base, <4 x i1> %mask, <4 x double> %src0)
|
|
ret <4 x double>%res
|
|
}
|
|
|
|
define <8 x double> @expandload_v8f64_v8i1(double* %base, <8 x double> %src0, <8 x i1> %mask) {
|
|
; SSE2-LABEL: expandload_v8f64_v8i1:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: movd %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_2: ## %else
|
|
; SSE2-NEXT: shrl $16, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_4: ## %else2
|
|
; SSE2-NEXT: pextrw $2, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_6: ## %else6
|
|
; SSE2-NEXT: pextrw $3, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_8: ## %else10
|
|
; SSE2-NEXT: pextrw $4, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_10
|
|
; SSE2-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_10: ## %else14
|
|
; SSE2-NEXT: pextrw $5, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_12
|
|
; SSE2-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm2 = xmm2[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_12: ## %else18
|
|
; SSE2-NEXT: pextrw $6, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_14
|
|
; SSE2-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; SSE2-NEXT: addq $8, %rdi
|
|
; SSE2-NEXT: LBB2_14: ## %else22
|
|
; SSE2-NEXT: pextrw $7, %xmm4, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB2_16
|
|
; SSE2-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm3 = xmm3[0,1],mem[0,1]
|
|
; SSE2-NEXT: LBB2_16: ## %else26
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v8f64_v8i1:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pextrb $0, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_2: ## %else
|
|
; SSE42-NEXT: pextrb $2, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_4: ## %else2
|
|
; SSE42-NEXT: pextrb $4, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_6: ## %else6
|
|
; SSE42-NEXT: pextrb $6, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_8: ## %else10
|
|
; SSE42-NEXT: pextrb $8, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_10
|
|
; SSE42-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_10: ## %else14
|
|
; SSE42-NEXT: pextrb $10, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_12
|
|
; SSE42-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm2 = xmm2[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_12: ## %else18
|
|
; SSE42-NEXT: pextrb $12, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_14
|
|
; SSE42-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; SSE42-NEXT: addq $8, %rdi
|
|
; SSE42-NEXT: LBB2_14: ## %else22
|
|
; SSE42-NEXT: pextrb $14, %xmm4, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB2_16
|
|
; SSE42-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm3 = xmm3[0,1],mem[0,1]
|
|
; SSE42-NEXT: LBB2_16: ## %else26
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v8f64_v8i1:
|
|
; AVX1OR2: ## %bb.0:
|
|
; AVX1OR2-NEXT: vpextrb $0, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_2
|
|
; AVX1OR2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1OR2-NEXT: vmovsd {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1],ymm0[2,3,4,5,6,7]
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_2: ## %else
|
|
; AVX1OR2-NEXT: vpextrb $2, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_4
|
|
; AVX1OR2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1OR2-NEXT: vmovhps {{.*#+}} xmm3 = xmm0[0,1],mem[0,1]
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm0 = ymm3[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_4: ## %else2
|
|
; AVX1OR2-NEXT: vpextrb $4, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_6
|
|
; AVX1OR2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1OR2-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; AVX1OR2-NEXT: vmovlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_6: ## %else6
|
|
; AVX1OR2-NEXT: vpextrb $6, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_8
|
|
; AVX1OR2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1OR2-NEXT: vextractf128 $1, %ymm0, %xmm3
|
|
; AVX1OR2-NEXT: vmovhps {{.*#+}} xmm3 = xmm3[0,1],mem[0,1]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_8: ## %else10
|
|
; AVX1OR2-NEXT: vpextrb $8, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_10
|
|
; AVX1OR2-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX1OR2-NEXT: vmovsd {{.*#+}} xmm3 = mem[0],zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm1 = ymm3[0,1],ymm1[2,3,4,5,6,7]
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_10: ## %else14
|
|
; AVX1OR2-NEXT: vpextrb $10, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_12
|
|
; AVX1OR2-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX1OR2-NEXT: vmovhps {{.*#+}} xmm3 = xmm1[0,1],mem[0,1]
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm1 = ymm3[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_12: ## %else18
|
|
; AVX1OR2-NEXT: vpextrb $12, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_14
|
|
; AVX1OR2-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX1OR2-NEXT: vextractf128 $1, %ymm1, %xmm3
|
|
; AVX1OR2-NEXT: vmovlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm1
|
|
; AVX1OR2-NEXT: addq $8, %rdi
|
|
; AVX1OR2-NEXT: LBB2_14: ## %else22
|
|
; AVX1OR2-NEXT: vpextrb $14, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB2_16
|
|
; AVX1OR2-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX1OR2-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; AVX1OR2-NEXT: vmovhps {{.*#+}} xmm2 = xmm2[0,1],mem[0,1]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
|
; AVX1OR2-NEXT: LBB2_16: ## %else26
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v8f64_v8i1:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: vpmovsxwq %xmm1, %zmm1
|
|
; AVX512F-NEXT: vpsllq $63, %zmm1, %zmm1
|
|
; AVX512F-NEXT: vptestmq %zmm1, %zmm1, %k1
|
|
; AVX512F-NEXT: vexpandpd (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v8f64_v8i1:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: vpmovsxwd %xmm1, %ymm1
|
|
; AVX512VLDQ-NEXT: vpslld $31, %ymm1, %ymm1
|
|
; AVX512VLDQ-NEXT: vpmovd2m %ymm1, %k1
|
|
; AVX512VLDQ-NEXT: vexpandpd (%rdi), %zmm0 {%k1}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v8f64_v8i1:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: vpsllw $15, %xmm1, %xmm1
|
|
; AVX512VLBW-NEXT: vpmovw2m %xmm1, %k1
|
|
; AVX512VLBW-NEXT: vexpandpd (%rdi), %zmm0 {%k1}
|
|
; AVX512VLBW-NEXT: retq
|
|
%res = call <8 x double> @llvm.masked.expandload.v8f64(double* %base, <8 x i1> %mask, <8 x double> %src0)
|
|
ret <8 x double>%res
|
|
}
|
|
|
|
define <16 x double> @expandload_v16f64_v16i32(double* %base, <16 x double> %src0, <16 x i32> %trigger) {
|
|
; SSE2-LABEL: expandload_v16f64_v16i32:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: movq %rdi, %rax
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_2: ## %else
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_4: ## %else2
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_6: ## %else6
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_8: ## %else10
|
|
; SSE2-NEXT: pxor %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_10
|
|
; SSE2-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_10: ## %else14
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_12
|
|
; SSE2-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm2 = xmm2[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_12: ## %else18
|
|
; SSE2-NEXT: pxor %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_14
|
|
; SSE2-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_14: ## %else22
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_16
|
|
; SSE2-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm3 = xmm3[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_16: ## %else26
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_18
|
|
; SSE2-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm4 = mem[0,1],xmm4[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_18: ## %else30
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_20
|
|
; SSE2-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_20: ## %else34
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_22
|
|
; SSE2-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm5 = mem[0,1],xmm5[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_22: ## %else38
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_24
|
|
; SSE2-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm5 = xmm5[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_24: ## %else42
|
|
; SSE2-NEXT: pxor %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_26
|
|
; SSE2-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_26: ## %else46
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_28
|
|
; SSE2-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm6 = xmm6[0,1],mem[0,1]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_28: ## %else50
|
|
; SSE2-NEXT: pxor %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_30
|
|
; SSE2-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE2-NEXT: movlps {{.*#+}} xmm7 = mem[0,1],xmm7[2,3]
|
|
; SSE2-NEXT: addq $8, %rsi
|
|
; SSE2-NEXT: LBB3_30: ## %else54
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB3_32
|
|
; SSE2-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE2-NEXT: movhps {{.*#+}} xmm7 = xmm7[0,1],mem[0,1]
|
|
; SSE2-NEXT: LBB3_32: ## %else58
|
|
; SSE2-NEXT: movaps %xmm0, (%rax)
|
|
; SSE2-NEXT: movaps %xmm1, 16(%rax)
|
|
; SSE2-NEXT: movaps %xmm2, 32(%rax)
|
|
; SSE2-NEXT: movaps %xmm3, 48(%rax)
|
|
; SSE2-NEXT: movaps %xmm4, 64(%rax)
|
|
; SSE2-NEXT: movaps %xmm5, 80(%rax)
|
|
; SSE2-NEXT: movaps %xmm6, 96(%rax)
|
|
; SSE2-NEXT: movaps %xmm7, 112(%rax)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v16f64_v16i32:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: movq %rdi, %rax
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_2: ## %else
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_6: ## %else6
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm1 = xmm1[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_8: ## %else10
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_10
|
|
; SSE42-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm2 = mem[0,1],xmm2[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_10: ## %else14
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_12
|
|
; SSE42-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm2 = xmm2[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_12: ## %else18
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_14
|
|
; SSE42-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm3 = mem[0,1],xmm3[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_14: ## %else22
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_16
|
|
; SSE42-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm3 = xmm3[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_16: ## %else26
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_18
|
|
; SSE42-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm4 = mem[0,1],xmm4[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_18: ## %else30
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_20
|
|
; SSE42-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_20: ## %else34
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_22
|
|
; SSE42-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm5 = mem[0,1],xmm5[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_22: ## %else38
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_24
|
|
; SSE42-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm5 = xmm5[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_24: ## %else42
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_26
|
|
; SSE42-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_26: ## %else46
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_28
|
|
; SSE42-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm6 = xmm6[0,1],mem[0,1]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_28: ## %else50
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_30
|
|
; SSE42-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE42-NEXT: movlps {{.*#+}} xmm7 = mem[0,1],xmm7[2,3]
|
|
; SSE42-NEXT: addq $8, %rsi
|
|
; SSE42-NEXT: LBB3_30: ## %else54
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB3_32
|
|
; SSE42-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE42-NEXT: movhps {{.*#+}} xmm7 = xmm7[0,1],mem[0,1]
|
|
; SSE42-NEXT: LBB3_32: ## %else58
|
|
; SSE42-NEXT: movaps %xmm0, (%rax)
|
|
; SSE42-NEXT: movaps %xmm1, 16(%rax)
|
|
; SSE42-NEXT: movaps %xmm2, 32(%rax)
|
|
; SSE42-NEXT: movaps %xmm3, 48(%rax)
|
|
; SSE42-NEXT: movaps %xmm4, 64(%rax)
|
|
; SSE42-NEXT: movaps %xmm5, 80(%rax)
|
|
; SSE42-NEXT: movaps %xmm6, 96(%rax)
|
|
; SSE42-NEXT: movaps %xmm7, 112(%rax)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: expandload_v16f64_v16i32:
|
|
; AVX1: ## %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm7
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpextrb $0, %xmm7, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_2
|
|
; AVX1-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1-NEXT: vmovsd {{.*#+}} xmm7 = mem[0],zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm7[0,1],ymm0[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_2: ## %else
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpextrb $1, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_4
|
|
; AVX1-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm6 = xmm0[0,1],mem[0,1]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_4: ## %else2
|
|
; AVX1-NEXT: vxorps %xmm6, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm7
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpextrb $2, %xmm7, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_6
|
|
; AVX1-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm7
|
|
; AVX1-NEXT: vmovlps {{.*#+}} xmm7 = mem[0,1],xmm7[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm7, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_6: ## %else6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpextrb $3, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_8
|
|
; AVX1-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm6
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm6 = xmm6[0,1],mem[0,1]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_8: ## %else10
|
|
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX1-NEXT: vpackssdw %xmm6, %xmm0, %xmm7
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX1-NEXT: vpextrb $4, %xmm7, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_10
|
|
; AVX1-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX1-NEXT: vmovsd {{.*#+}} xmm7 = mem[0],zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm7[0,1],ymm1[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_10: ## %else14
|
|
; AVX1-NEXT: vpackssdw %xmm6, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpextrb $5, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_12
|
|
; AVX1-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm6 = xmm1[0,1],mem[0,1]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm6[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_12: ## %else18
|
|
; AVX1-NEXT: vxorps %xmm6, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpextrb $6, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_14
|
|
; AVX1-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm6
|
|
; AVX1-NEXT: vmovlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_14: ## %else22
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_16
|
|
; AVX1-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_16: ## %else26
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm6
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpextrb $8, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_18
|
|
; AVX1-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX1-NEXT: vmovsd {{.*#+}} xmm6 = mem[0],zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm6[0,1],ymm2[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_18: ## %else30
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_20
|
|
; AVX1-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm4 = xmm2[0,1],mem[0,1]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_20: ## %else34
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm6
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpextrb $10, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_22
|
|
; AVX1-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm6
|
|
; AVX1-NEXT: vmovlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_22: ## %else38
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_24
|
|
; AVX1-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_24: ## %else42
|
|
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm4
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpextrb $12, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_26
|
|
; AVX1-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX1-NEXT: vmovsd {{.*#+}} xmm6 = mem[0],zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm6[0,1],ymm3[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_26: ## %else46
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $13, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_28
|
|
; AVX1-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm5 = xmm3[0,1],mem[0,1]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm5[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_28: ## %else50
|
|
; AVX1-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_30
|
|
; AVX1-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm5
|
|
; AVX1-NEXT: vmovlps {{.*#+}} xmm5 = mem[0,1],xmm5[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX1-NEXT: addq $8, %rdi
|
|
; AVX1-NEXT: LBB3_30: ## %else54
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB3_32
|
|
; AVX1-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
|
|
; AVX1-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX1-NEXT: LBB3_32: ## %else58
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: expandload_v16f64_v16i32:
|
|
; AVX2: ## %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm7
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm7, %xmm7
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX2-NEXT: vpextrb $0, %xmm7, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_2
|
|
; AVX2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX2-NEXT: vmovq {{.*#+}} xmm7 = mem[0],zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm7[0,1],ymm0[2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_2: ## %else
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpextrb $1, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_4
|
|
; AVX2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm6 = xmm0[0,1],mem[0,1]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_4: ## %else2
|
|
; AVX2-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm7
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm7, %xmm7
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX2-NEXT: vpextrb $2, %xmm7, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_6
|
|
; AVX2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm7
|
|
; AVX2-NEXT: vmovlps {{.*#+}} xmm7 = mem[0,1],xmm7[2,3]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm7, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_6: ## %else6
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpextrb $3, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_8
|
|
; AVX2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm6
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm6 = xmm6[0,1],mem[0,1]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm6, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_8: ## %else10
|
|
; AVX2-NEXT: vextracti128 $1, %ymm4, %xmm4
|
|
; AVX2-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm6
|
|
; AVX2-NEXT: vpackssdw %xmm6, %xmm0, %xmm7
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm7, %xmm7
|
|
; AVX2-NEXT: vpextrb $4, %xmm7, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_10
|
|
; AVX2-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX2-NEXT: vmovq {{.*#+}} xmm7 = mem[0],zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm7[0,1],ymm1[2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_10: ## %else14
|
|
; AVX2-NEXT: vpackssdw %xmm6, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpextrb $5, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_12
|
|
; AVX2-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm6 = xmm1[0,1],mem[0,1]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm6[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_12: ## %else18
|
|
; AVX2-NEXT: vpxor %xmm6, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpcmpeqd %xmm6, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpextrb $6, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_14
|
|
; AVX2-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm6
|
|
; AVX2-NEXT: vmovlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm6, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_14: ## %else22
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_16
|
|
; AVX2-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm4
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_16: ## %else26
|
|
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm6
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpextrb $8, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_18
|
|
; AVX2-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX2-NEXT: vmovq {{.*#+}} xmm6 = mem[0],zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm6[0,1],ymm2[2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_18: ## %else30
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_20
|
|
; AVX2-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm4 = xmm2[0,1],mem[0,1]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_20: ## %else34
|
|
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm6
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpextrb $10, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_22
|
|
; AVX2-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm6
|
|
; AVX2-NEXT: vmovlps {{.*#+}} xmm6 = mem[0,1],xmm6[2,3]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm6, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_22: ## %else38
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_24
|
|
; AVX2-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm4
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_24: ## %else42
|
|
; AVX2-NEXT: vextracti128 $1, %ymm5, %xmm4
|
|
; AVX2-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpextrb $12, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_26
|
|
; AVX2-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX2-NEXT: vmovq {{.*#+}} xmm6 = mem[0],zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm3 = ymm6[0,1],ymm3[2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_26: ## %else46
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $13, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_28
|
|
; AVX2-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm5 = xmm3[0,1],mem[0,1]
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm3 = ymm5[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_28: ## %else50
|
|
; AVX2-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_30
|
|
; AVX2-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm5
|
|
; AVX2-NEXT: vmovlps {{.*#+}} xmm5 = mem[0,1],xmm5[2,3]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX2-NEXT: addq $8, %rdi
|
|
; AVX2-NEXT: LBB3_30: ## %else54
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB3_32
|
|
; AVX2-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4
|
|
; AVX2-NEXT: vmovhps {{.*#+}} xmm4 = xmm4[0,1],mem[0,1]
|
|
; AVX2-NEXT: vinserti128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX2-NEXT: LBB3_32: ## %else58
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v16f64_v16i32:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: vextracti64x4 $1, %zmm2, %ymm3
|
|
; AVX512F-NEXT: vptestnmd %zmm3, %zmm3, %k1
|
|
; AVX512F-NEXT: vptestnmd %zmm2, %zmm2, %k2
|
|
; AVX512F-NEXT: vexpandpd (%rdi), %zmm0 {%k2}
|
|
; AVX512F-NEXT: kmovw %k2, %eax
|
|
; AVX512F-NEXT: movzbl %al, %eax
|
|
; AVX512F-NEXT: movl %eax, %ecx
|
|
; AVX512F-NEXT: shrl %ecx
|
|
; AVX512F-NEXT: andl $-43, %ecx
|
|
; AVX512F-NEXT: subl %ecx, %eax
|
|
; AVX512F-NEXT: movl %eax, %ecx
|
|
; AVX512F-NEXT: andl $858993459, %ecx ## imm = 0x33333333
|
|
; AVX512F-NEXT: shrl $2, %eax
|
|
; AVX512F-NEXT: andl $858993459, %eax ## imm = 0x33333333
|
|
; AVX512F-NEXT: addl %ecx, %eax
|
|
; AVX512F-NEXT: movl %eax, %ecx
|
|
; AVX512F-NEXT: shrl $4, %ecx
|
|
; AVX512F-NEXT: addl %eax, %ecx
|
|
; AVX512F-NEXT: andl $252645135, %ecx ## imm = 0xF0F0F0F
|
|
; AVX512F-NEXT: imull $16843009, %ecx, %eax ## imm = 0x1010101
|
|
; AVX512F-NEXT: shrl $24, %eax
|
|
; AVX512F-NEXT: vexpandpd (%rdi,%rax,8), %zmm1 {%k1}
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v16f64_v16i32:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: vextracti64x4 $1, %zmm2, %ymm3
|
|
; AVX512VLDQ-NEXT: vptestnmd %ymm3, %ymm3, %k1
|
|
; AVX512VLDQ-NEXT: vptestnmd %ymm2, %ymm2, %k2
|
|
; AVX512VLDQ-NEXT: kmovb %k2, %eax
|
|
; AVX512VLDQ-NEXT: movl %eax, %ecx
|
|
; AVX512VLDQ-NEXT: shrl %ecx
|
|
; AVX512VLDQ-NEXT: andl $-43, %ecx
|
|
; AVX512VLDQ-NEXT: subl %ecx, %eax
|
|
; AVX512VLDQ-NEXT: movl %eax, %ecx
|
|
; AVX512VLDQ-NEXT: andl $858993459, %ecx ## imm = 0x33333333
|
|
; AVX512VLDQ-NEXT: shrl $2, %eax
|
|
; AVX512VLDQ-NEXT: andl $858993459, %eax ## imm = 0x33333333
|
|
; AVX512VLDQ-NEXT: addl %ecx, %eax
|
|
; AVX512VLDQ-NEXT: movl %eax, %ecx
|
|
; AVX512VLDQ-NEXT: shrl $4, %ecx
|
|
; AVX512VLDQ-NEXT: addl %eax, %ecx
|
|
; AVX512VLDQ-NEXT: andl $252645135, %ecx ## imm = 0xF0F0F0F
|
|
; AVX512VLDQ-NEXT: imull $16843009, %ecx, %eax ## imm = 0x1010101
|
|
; AVX512VLDQ-NEXT: shrl $24, %eax
|
|
; AVX512VLDQ-NEXT: vexpandpd (%rdi,%rax,8), %zmm1 {%k1}
|
|
; AVX512VLDQ-NEXT: vexpandpd (%rdi), %zmm0 {%k2}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v16f64_v16i32:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: vextracti64x4 $1, %zmm2, %ymm3
|
|
; AVX512VLBW-NEXT: vptestnmd %ymm3, %ymm3, %k1
|
|
; AVX512VLBW-NEXT: vptestnmd %ymm2, %ymm2, %k2
|
|
; AVX512VLBW-NEXT: vexpandpd (%rdi), %zmm0 {%k2}
|
|
; AVX512VLBW-NEXT: kmovd %k2, %eax
|
|
; AVX512VLBW-NEXT: movzbl %al, %eax
|
|
; AVX512VLBW-NEXT: movl %eax, %ecx
|
|
; AVX512VLBW-NEXT: shrl %ecx
|
|
; AVX512VLBW-NEXT: andl $-43, %ecx
|
|
; AVX512VLBW-NEXT: subl %ecx, %eax
|
|
; AVX512VLBW-NEXT: movl %eax, %ecx
|
|
; AVX512VLBW-NEXT: andl $858993459, %ecx ## imm = 0x33333333
|
|
; AVX512VLBW-NEXT: shrl $2, %eax
|
|
; AVX512VLBW-NEXT: andl $858993459, %eax ## imm = 0x33333333
|
|
; AVX512VLBW-NEXT: addl %ecx, %eax
|
|
; AVX512VLBW-NEXT: movl %eax, %ecx
|
|
; AVX512VLBW-NEXT: shrl $4, %ecx
|
|
; AVX512VLBW-NEXT: addl %eax, %ecx
|
|
; AVX512VLBW-NEXT: andl $252645135, %ecx ## imm = 0xF0F0F0F
|
|
; AVX512VLBW-NEXT: imull $16843009, %ecx, %eax ## imm = 0x1010101
|
|
; AVX512VLBW-NEXT: shrl $24, %eax
|
|
; AVX512VLBW-NEXT: vexpandpd (%rdi,%rax,8), %zmm1 {%k1}
|
|
; AVX512VLBW-NEXT: retq
|
|
%mask = icmp eq <16 x i32> %trigger, zeroinitializer
|
|
%res = call <16 x double> @llvm.masked.expandload.v16f64(double* %base, <16 x i1> %mask, <16 x double> %src0)
|
|
ret <16 x double> %res
|
|
}
|
|
|
|
;
|
|
; vXf32
|
|
;
|
|
|
|
define <2 x float> @expandload_v2f32_v2i1(float* %base, <2 x float> %src0, <2 x i32> %trigger) {
|
|
; SSE2-LABEL: expandload_v2f32_v2i1:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,0,3,2]
|
|
; SSE2-NEXT: pand %xmm2, %xmm1
|
|
; SSE2-NEXT: movd %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB4_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rdi
|
|
; SSE2-NEXT: LBB4_2: ## %else
|
|
; SSE2-NEXT: pextrw $4, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB4_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[2,3]
|
|
; SSE2-NEXT: movaps %xmm1, %xmm0
|
|
; SSE2-NEXT: LBB4_4: ## %else2
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v2f32_v2i1:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
|
|
; SSE42-NEXT: pcmpeqq %xmm2, %xmm1
|
|
; SSE42-NEXT: pextrb $0, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB4_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm2[0,1],xmm0[2,3,4,5,6,7]
|
|
; SSE42-NEXT: addq $4, %rdi
|
|
; SSE42-NEXT: LBB4_2: ## %else
|
|
; SSE42-NEXT: pextrb $8, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB4_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; SSE42-NEXT: LBB4_4: ## %else2
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: expandload_v2f32_v2i1:
|
|
; AVX1: ## %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
|
|
; AVX1-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
|
|
; AVX1-NEXT: vpextrb $0, %xmm1, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB4_2
|
|
; AVX1-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1-NEXT: vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm2[0,1],xmm0[2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB4_2: ## %else
|
|
; AVX1-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB4_4
|
|
; AVX1-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX1-NEXT: LBB4_4: ## %else2
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: expandload_v2f32_v2i1:
|
|
; AVX2: ## %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3]
|
|
; AVX2-NEXT: vpcmpeqq %xmm2, %xmm1, %xmm1
|
|
; AVX2-NEXT: vpextrb $0, %xmm1, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB4_2
|
|
; AVX2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX2-NEXT: vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB4_2: ## %else
|
|
; AVX2-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB4_4
|
|
; AVX2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX2-NEXT: LBB4_4: ## %else2
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v2f32_v2i1:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3]
|
|
; AVX512F-NEXT: vptestnmq %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftlw $14, %k0, %k0
|
|
; AVX512F-NEXT: kshiftrw $14, %k0, %k1
|
|
; AVX512F-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: expandload_v2f32_v2i1:
|
|
; AVX512VL: ## %bb.0:
|
|
; AVX512VL-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3]
|
|
; AVX512VL-NEXT: vptestnmq %xmm1, %xmm1, %k1
|
|
; AVX512VL-NEXT: vexpandps (%rdi), %xmm0 {%k1}
|
|
; AVX512VL-NEXT: retq
|
|
%mask = icmp eq <2 x i32> %trigger, zeroinitializer
|
|
%res = call <2 x float> @llvm.masked.expandload.v2f32(float* %base, <2 x i1> %mask, <2 x float> %src0)
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define <4 x float> @expandload_v4f32_const(float* %base, <4 x float> %src0) {
|
|
; SSE2-LABEL: expandload_v4f32_const:
|
|
; SSE2: ## %bb.0: ## %cond.load
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm2[0,0]
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm0[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm2[0,2]
|
|
; SSE2-NEXT: movaps %xmm1, %xmm0
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v4f32_const:
|
|
; SSE42: ## %bb.0: ## %cond.load
|
|
; SSE42-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v4f32_const:
|
|
; AVX1OR2: ## %bb.0: ## %cond.load
|
|
; AVX1OR2-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v4f32_const:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
|
|
; AVX512F-NEXT: movw $7, %ax
|
|
; AVX512F-NEXT: kmovw %eax, %k1
|
|
; AVX512F-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v4f32_const:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: movb $7, %al
|
|
; AVX512VLDQ-NEXT: kmovw %eax, %k1
|
|
; AVX512VLDQ-NEXT: vexpandps (%rdi), %xmm0 {%k1}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v4f32_const:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: movb $7, %al
|
|
; AVX512VLBW-NEXT: kmovd %eax, %k1
|
|
; AVX512VLBW-NEXT: vexpandps (%rdi), %xmm0 {%k1}
|
|
; AVX512VLBW-NEXT: retq
|
|
%res = call <4 x float> @llvm.masked.expandload.v4f32(float* %base, <4 x i1> <i1 true, i1 true, i1 true, i1 false>, <4 x float> %src0)
|
|
ret <4 x float>%res
|
|
}
|
|
|
|
define <16 x float> @expandload_v16f32_const(float* %base, <16 x float> %src0) {
|
|
; SSE2-LABEL: expandload_v16f32_const:
|
|
; SSE2: ## %bb.0: ## %cond.load
|
|
; SSE2-NEXT: movups (%rdi), %xmm0
|
|
; SSE2-NEXT: movups 16(%rdi), %xmm1
|
|
; SSE2-NEXT: movss {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,0],xmm5[0,0]
|
|
; SSE2-NEXT: movss {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm2[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[2,0],xmm5[0,2]
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm2[0,0]
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm3[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[2,0],xmm2[0,2]
|
|
; SSE2-NEXT: movaps %xmm4, %xmm2
|
|
; SSE2-NEXT: movaps %xmm5, %xmm3
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v16f32_const:
|
|
; SSE42: ## %bb.0: ## %cond.load
|
|
; SSE42-NEXT: movups (%rdi), %xmm0
|
|
; SSE42-NEXT: movups 16(%rdi), %xmm1
|
|
; SSE42-NEXT: movss {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm2 = xmm4[0],xmm2[1,2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; SSE42-NEXT: movss {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm3 = xmm4[0],xmm3[1,2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm3 = xmm3[0,1],mem[0],xmm3[3]
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v16f32_const:
|
|
; AVX1OR2: ## %bb.0: ## %cond.load
|
|
; AVX1OR2-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0],ymm0[1,2,3,4,5,6,7]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1OR2-NEXT: vmovsd {{.*#+}} xmm2 = mem[0],zero
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
|
; AVX1OR2-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0],ymm1[1,2,3,4,5,6,7]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm1[0],mem[0],xmm1[2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} ymm2 = ymm2[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1OR2-NEXT: vextractf128 $1, %ymm1, %xmm1
|
|
; AVX1OR2-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; AVX1OR2-NEXT: vblendps {{.*#+}} xmm1 = xmm3[0],xmm1[1,2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v16f32_const:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: movw $30719, %ax ## imm = 0x77FF
|
|
; AVX512F-NEXT: kmovw %eax, %k1
|
|
; AVX512F-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v16f32_const:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: movw $30719, %ax ## imm = 0x77FF
|
|
; AVX512VLDQ-NEXT: kmovw %eax, %k1
|
|
; AVX512VLDQ-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v16f32_const:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: movw $30719, %ax ## imm = 0x77FF
|
|
; AVX512VLBW-NEXT: kmovd %eax, %k1
|
|
; AVX512VLBW-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512VLBW-NEXT: retq
|
|
%res = call <16 x float> @llvm.masked.expandload.v16f32(float* %base, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <16 x float> %src0)
|
|
ret <16 x float>%res
|
|
}
|
|
|
|
define <16 x float> @expandload_v16f32_const_undef(float* %base) {
|
|
; SSE2-LABEL: expandload_v16f32_const_undef:
|
|
; SSE2: ## %bb.0: ## %cond.load
|
|
; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
|
|
; SSE2-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm0[0]
|
|
; SSE2-NEXT: movups (%rdi), %xmm0
|
|
; SSE2-NEXT: movups 16(%rdi), %xmm1
|
|
; SSE2-NEXT: movups 44(%rdi), %xmm3
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v16f32_const_undef:
|
|
; SSE42: ## %bb.0: ## %cond.load
|
|
; SSE42-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; SSE42-NEXT: movups (%rdi), %xmm0
|
|
; SSE42-NEXT: movups 16(%rdi), %xmm1
|
|
; SSE42-NEXT: movups 44(%rdi), %xmm3
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v16f32_const_undef:
|
|
; AVX1OR2: ## %bb.0: ## %cond.load
|
|
; AVX1OR2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX1OR2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; AVX1OR2-NEXT: vinsertf128 $1, 44(%rdi), %ymm0, %ymm1
|
|
; AVX1OR2-NEXT: vmovups (%rdi), %ymm0
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v16f32_const_undef:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: movw $-2049, %ax ## imm = 0xF7FF
|
|
; AVX512F-NEXT: kmovw %eax, %k1
|
|
; AVX512F-NEXT: vexpandps (%rdi), %zmm0 {%k1} {z}
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v16f32_const_undef:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: movw $-2049, %ax ## imm = 0xF7FF
|
|
; AVX512VLDQ-NEXT: kmovw %eax, %k1
|
|
; AVX512VLDQ-NEXT: vexpandps (%rdi), %zmm0 {%k1} {z}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v16f32_const_undef:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: movw $-2049, %ax ## imm = 0xF7FF
|
|
; AVX512VLBW-NEXT: kmovd %eax, %k1
|
|
; AVX512VLBW-NEXT: vexpandps (%rdi), %zmm0 {%k1} {z}
|
|
; AVX512VLBW-NEXT: retq
|
|
%res = call <16 x float> @llvm.masked.expandload.v16f32(float* %base, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 false, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
|
|
ret <16 x float>%res
|
|
}
|
|
|
|
|
|
define <32 x float> @expandload_v32f32_v32i32(float* %base, <32 x float> %src0, <32 x i32> %trigger) {
|
|
; SSE2-LABEL: expandload_v32f32_v32i32:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: movq %rdi, %rax
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pxor %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm0 = xmm10[0],xmm0[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_2: ## %else
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm0[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[2,0],xmm0[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm8, %xmm0
|
|
; SSE2-NEXT: LBB8_4: ## %else2
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm0[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm8[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_6: ## %else6
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm0[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm9[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_8: ## %else10
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_10
|
|
; SSE2-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm1 = xmm10[0],xmm1[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_10: ## %else14
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_12
|
|
; SSE2-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm1[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[2,0],xmm1[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm9, %xmm1
|
|
; SSE2-NEXT: LBB8_12: ## %else18
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_14
|
|
; SSE2-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm1[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm9[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_14: ## %else22
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_16
|
|
; SSE2-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm1[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm8[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_16: ## %else26
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_18
|
|
; SSE2-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm10[0],xmm2[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_18: ## %else30
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_20
|
|
; SSE2-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm2[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[2,0],xmm2[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm8, %xmm2
|
|
; SSE2-NEXT: LBB8_20: ## %else34
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_22
|
|
; SSE2-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm2[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm8[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_22: ## %else38
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_24
|
|
; SSE2-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm2[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,1],xmm9[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_24: ## %else42
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_26
|
|
; SSE2-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm3 = xmm10[0],xmm3[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_26: ## %else46
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_28
|
|
; SSE2-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm3[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[2,0],xmm3[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm9, %xmm3
|
|
; SSE2-NEXT: LBB8_28: ## %else50
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_30
|
|
; SSE2-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm3[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,1],xmm9[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_30: ## %else54
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_32
|
|
; SSE2-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm3[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,1],xmm8[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_32: ## %else58
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_34
|
|
; SSE2-NEXT: ## %bb.33: ## %cond.load61
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm4 = xmm10[0],xmm4[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_34: ## %else62
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_36
|
|
; SSE2-NEXT: ## %bb.35: ## %cond.load65
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm4[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[2,0],xmm4[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm8, %xmm4
|
|
; SSE2-NEXT: LBB8_36: ## %else66
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_38
|
|
; SSE2-NEXT: ## %bb.37: ## %cond.load69
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm4[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,1],xmm8[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_38: ## %else70
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_40
|
|
; SSE2-NEXT: ## %bb.39: ## %cond.load73
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm4[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,1],xmm9[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_40: ## %else74
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_42
|
|
; SSE2-NEXT: ## %bb.41: ## %cond.load77
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm5 = xmm10[0],xmm5[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_42: ## %else78
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_44
|
|
; SSE2-NEXT: ## %bb.43: ## %cond.load81
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm5[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[2,0],xmm5[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm9, %xmm5
|
|
; SSE2-NEXT: LBB8_44: ## %else82
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_46
|
|
; SSE2-NEXT: ## %bb.45: ## %cond.load85
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm5[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,1],xmm9[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_46: ## %else86
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_48
|
|
; SSE2-NEXT: ## %bb.47: ## %cond.load89
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm5[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,1],xmm8[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_48: ## %else90
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: movd %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_50
|
|
; SSE2-NEXT: ## %bb.49: ## %cond.load93
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm6 = xmm10[0],xmm6[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_50: ## %else94
|
|
; SSE2-NEXT: pextrw $2, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_52
|
|
; SSE2-NEXT: ## %bb.51: ## %cond.load97
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm6[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[2,0],xmm6[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm8, %xmm6
|
|
; SSE2-NEXT: LBB8_52: ## %else98
|
|
; SSE2-NEXT: xorps %xmm8, %xmm8
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: pextrw $4, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_54
|
|
; SSE2-NEXT: ## %bb.53: ## %cond.load101
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm6[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,1],xmm8[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_54: ## %else102
|
|
; SSE2-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE2-NEXT: pextrw $6, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_56
|
|
; SSE2-NEXT: ## %bb.55: ## %cond.load105
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm6[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,1],xmm9[2,0]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_56: ## %else106
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE2-NEXT: movd %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_58
|
|
; SSE2-NEXT: ## %bb.57: ## %cond.load109
|
|
; SSE2-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm7 = xmm10[0],xmm7[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_58: ## %else110
|
|
; SSE2-NEXT: pextrw $2, %xmm9, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_60
|
|
; SSE2-NEXT: ## %bb.59: ## %cond.load113
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm7[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[2,0],xmm7[2,3]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: movaps %xmm9, %xmm7
|
|
; SSE2-NEXT: LBB8_60: ## %else114
|
|
; SSE2-NEXT: xorps %xmm9, %xmm9
|
|
; SSE2-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE2-NEXT: pextrw $4, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_62
|
|
; SSE2-NEXT: ## %bb.61: ## %cond.load117
|
|
; SSE2-NEXT: movss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,0],xmm7[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,1],xmm9[0,2]
|
|
; SSE2-NEXT: addq $4, %rsi
|
|
; SSE2-NEXT: LBB8_62: ## %else118
|
|
; SSE2-NEXT: pextrw $6, %xmm8, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB8_64
|
|
; SSE2-NEXT: ## %bb.63: ## %cond.load121
|
|
; SSE2-NEXT: movss {{.*#+}} xmm8 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,0],xmm7[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,1],xmm8[2,0]
|
|
; SSE2-NEXT: LBB8_64: ## %else122
|
|
; SSE2-NEXT: movaps %xmm0, (%rax)
|
|
; SSE2-NEXT: movaps %xmm1, 16(%rax)
|
|
; SSE2-NEXT: movaps %xmm2, 32(%rax)
|
|
; SSE2-NEXT: movaps %xmm3, 48(%rax)
|
|
; SSE2-NEXT: movaps %xmm4, 64(%rax)
|
|
; SSE2-NEXT: movaps %xmm5, 80(%rax)
|
|
; SSE2-NEXT: movaps %xmm6, 96(%rax)
|
|
; SSE2-NEXT: movaps %xmm7, 112(%rax)
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v32f32_v32i32:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: movq %rdi, %rax
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm0 = xmm10[0],xmm0[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_2: ## %else
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_6: ## %else6
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_8: ## %else10
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_10
|
|
; SSE42-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm1 = xmm10[0],xmm1[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_10: ## %else14
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_12
|
|
; SSE42-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm1 = xmm1[0],mem[0],xmm1[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_12: ## %else18
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_14
|
|
; SSE42-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_14: ## %else22
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_16
|
|
; SSE42-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm1 = xmm1[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_16: ## %else26
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_18
|
|
; SSE42-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm2 = xmm10[0],xmm2[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_18: ## %else30
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_20
|
|
; SSE42-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0],mem[0],xmm2[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_20: ## %else34
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_22
|
|
; SSE42-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0,1],mem[0],xmm2[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_22: ## %else38
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_24
|
|
; SSE42-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm2 = xmm2[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_24: ## %else42
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_26
|
|
; SSE42-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm3 = xmm10[0],xmm3[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_26: ## %else46
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_28
|
|
; SSE42-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm3 = xmm3[0],mem[0],xmm3[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_28: ## %else50
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_30
|
|
; SSE42-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm3 = xmm3[0,1],mem[0],xmm3[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_30: ## %else54
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_32
|
|
; SSE42-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm3 = xmm3[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_32: ## %else58
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_34
|
|
; SSE42-NEXT: ## %bb.33: ## %cond.load61
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm4 = xmm10[0],xmm4[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_34: ## %else62
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_36
|
|
; SSE42-NEXT: ## %bb.35: ## %cond.load65
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_36: ## %else66
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_38
|
|
; SSE42-NEXT: ## %bb.37: ## %cond.load69
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm4 = xmm4[0,1],mem[0],xmm4[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_38: ## %else70
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_40
|
|
; SSE42-NEXT: ## %bb.39: ## %cond.load73
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_40: ## %else74
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_42
|
|
; SSE42-NEXT: ## %bb.41: ## %cond.load77
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm5 = xmm10[0],xmm5[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_42: ## %else78
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_44
|
|
; SSE42-NEXT: ## %bb.43: ## %cond.load81
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm5 = xmm5[0],mem[0],xmm5[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_44: ## %else82
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_46
|
|
; SSE42-NEXT: ## %bb.45: ## %cond.load85
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_46: ## %else86
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_48
|
|
; SSE42-NEXT: ## %bb.47: ## %cond.load89
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm5 = xmm5[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_48: ## %else90
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $0, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_50
|
|
; SSE42-NEXT: ## %bb.49: ## %cond.load93
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm6 = xmm10[0],xmm6[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_50: ## %else94
|
|
; SSE42-NEXT: pextrb $4, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_52
|
|
; SSE42-NEXT: ## %bb.51: ## %cond.load97
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm6 = xmm6[0],mem[0],xmm6[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_52: ## %else98
|
|
; SSE42-NEXT: pxor %xmm8, %xmm8
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $8, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_54
|
|
; SSE42-NEXT: ## %bb.53: ## %cond.load101
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm6 = xmm6[0,1],mem[0],xmm6[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_54: ## %else102
|
|
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
|
; SSE42-NEXT: pextrb $12, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_56
|
|
; SSE42-NEXT: ## %bb.55: ## %cond.load105
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm6 = xmm6[0,1,2],mem[0]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_56: ## %else106
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm8, %xmm9
|
|
; SSE42-NEXT: pextrb $0, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_58
|
|
; SSE42-NEXT: ## %bb.57: ## %cond.load109
|
|
; SSE42-NEXT: movss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; SSE42-NEXT: blendps {{.*#+}} xmm7 = xmm10[0],xmm7[1,2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_58: ## %else110
|
|
; SSE42-NEXT: pextrb $4, %xmm9, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_60
|
|
; SSE42-NEXT: ## %bb.59: ## %cond.load113
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm7 = xmm7[0],mem[0],xmm7[2,3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_60: ## %else114
|
|
; SSE42-NEXT: pxor %xmm9, %xmm9
|
|
; SSE42-NEXT: pcmpeqd %xmm9, %xmm8
|
|
; SSE42-NEXT: pextrb $8, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_62
|
|
; SSE42-NEXT: ## %bb.61: ## %cond.load117
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm7 = xmm7[0,1],mem[0],xmm7[3]
|
|
; SSE42-NEXT: addq $4, %rsi
|
|
; SSE42-NEXT: LBB8_62: ## %else118
|
|
; SSE42-NEXT: pextrb $12, %xmm8, %ecx
|
|
; SSE42-NEXT: testb $1, %cl
|
|
; SSE42-NEXT: je LBB8_64
|
|
; SSE42-NEXT: ## %bb.63: ## %cond.load121
|
|
; SSE42-NEXT: insertps {{.*#+}} xmm7 = xmm7[0,1,2],mem[0]
|
|
; SSE42-NEXT: LBB8_64: ## %else122
|
|
; SSE42-NEXT: movaps %xmm0, (%rax)
|
|
; SSE42-NEXT: movaps %xmm1, 16(%rax)
|
|
; SSE42-NEXT: movaps %xmm2, 32(%rax)
|
|
; SSE42-NEXT: movaps %xmm3, 48(%rax)
|
|
; SSE42-NEXT: movaps %xmm4, 64(%rax)
|
|
; SSE42-NEXT: movaps %xmm5, 80(%rax)
|
|
; SSE42-NEXT: movaps %xmm6, 96(%rax)
|
|
; SSE42-NEXT: movaps %xmm7, 112(%rax)
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1-LABEL: expandload_v32f32_v32i32:
|
|
; AVX1: ## %bb.0:
|
|
; AVX1-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm9
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm9, %xmm9
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm9, %xmm9
|
|
; AVX1-NEXT: vpextrb $0, %xmm9, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_2
|
|
; AVX1-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1-NEXT: vmovss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0],ymm0[1,2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_2: ## %else
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm8
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpextrb $1, %xmm8, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_4
|
|
; AVX1-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm8 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm8[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_4: ## %else2
|
|
; AVX1-NEXT: vxorps %xmm8, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm9
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm9, %xmm9
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm9, %xmm9
|
|
; AVX1-NEXT: vpextrb $2, %xmm9, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_6
|
|
; AVX1-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm9 = xmm0[0,1],mem[0],xmm0[3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_6: ## %else6
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm8
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpextrb $3, %xmm8, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_8
|
|
; AVX1-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm8 = xmm0[0,1,2],mem[0]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm8[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_8: ## %else10
|
|
; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm8
|
|
; AVX1-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm9
|
|
; AVX1-NEXT: vpackssdw %xmm9, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $4, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_10
|
|
; AVX1-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX1-NEXT: vmovd {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm4 = xmm10[0,1],xmm4[2,3,4,5,6,7]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_10: ## %else14
|
|
; AVX1-NEXT: vpackssdw %xmm9, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $5, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_12
|
|
; AVX1-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_12: ## %else18
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpackssdw %xmm8, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $6, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_14
|
|
; AVX1-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],mem[0],xmm4[3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_14: ## %else22
|
|
; AVX1-NEXT: vpackssdw %xmm8, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_16
|
|
; AVX1-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_16: ## %else26
|
|
; AVX1-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $8, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_18
|
|
; AVX1-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX1-NEXT: vmovss {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0],ymm1[1,2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_18: ## %else30
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_20
|
|
; AVX1-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0],mem[0],xmm1[2,3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_20: ## %else34
|
|
; AVX1-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $10, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_22
|
|
; AVX1-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0,1],mem[0],xmm1[3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_22: ## %else38
|
|
; AVX1-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_24
|
|
; AVX1-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0,1,2],mem[0]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_24: ## %else42
|
|
; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm8
|
|
; AVX1-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm8, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $12, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_26
|
|
; AVX1-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX1-NEXT: vmovd {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm4 = xmm9[0,1],xmm4[2,3,4,5,6,7]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_26: ## %else46
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $13, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_28
|
|
; AVX1-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_28: ## %else50
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_30
|
|
; AVX1-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_30: ## %else54
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_32
|
|
; AVX1-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_32: ## %else58
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpextrb $0, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_34
|
|
; AVX1-NEXT: ## %bb.33: ## %cond.load61
|
|
; AVX1-NEXT: vmovss {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm5[0],ymm2[1,2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_34: ## %else62
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $1, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_36
|
|
; AVX1-NEXT: ## %bb.35: ## %cond.load65
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm2[0],mem[0],xmm2[2,3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_36: ## %else66
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpextrb $2, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_38
|
|
; AVX1-NEXT: ## %bb.37: ## %cond.load69
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm2[0,1],mem[0],xmm2[3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm5[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_38: ## %else70
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $3, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_40
|
|
; AVX1-NEXT: ## %bb.39: ## %cond.load73
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm2[0,1,2],mem[0]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_40: ## %else74
|
|
; AVX1-NEXT: vextractf128 $1, %ymm6, %xmm8
|
|
; AVX1-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm8, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX1-NEXT: vpextrb $4, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_42
|
|
; AVX1-NEXT: ## %bb.41: ## %cond.load77
|
|
; AVX1-NEXT: vmovss {{.*#+}} xmm6 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vblendps {{.*#+}} xmm4 = xmm6[0],xmm4[1,2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_42: ## %else78
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $5, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_44
|
|
; AVX1-NEXT: ## %bb.43: ## %cond.load81
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_44: ## %else82
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpextrb $6, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_46
|
|
; AVX1-NEXT: ## %bb.45: ## %cond.load85
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm5
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_46: ## %else86
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_48
|
|
; AVX1-NEXT: ## %bb.47: ## %cond.load89
|
|
; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_48: ## %else90
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $8, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_50
|
|
; AVX1-NEXT: ## %bb.49: ## %cond.load93
|
|
; AVX1-NEXT: vmovss {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm5[0],ymm3[1,2,3,4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_50: ## %else94
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_52
|
|
; AVX1-NEXT: ## %bb.51: ## %cond.load97
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm3[0],mem[0],xmm3[2,3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_52: ## %else98
|
|
; AVX1-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $10, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_54
|
|
; AVX1-NEXT: ## %bb.53: ## %cond.load101
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm3[0,1],mem[0],xmm3[3]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm5[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_54: ## %else102
|
|
; AVX1-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_56
|
|
; AVX1-NEXT: ## %bb.55: ## %cond.load105
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm3[0,1,2],mem[0]
|
|
; AVX1-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_56: ## %else106
|
|
; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm4
|
|
; AVX1-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm5
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX1-NEXT: vpextrb $12, %xmm6, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_58
|
|
; AVX1-NEXT: ## %bb.57: ## %cond.load109
|
|
; AVX1-NEXT: vmovd {{.*#+}} xmm6 = mem[0],zero,zero,zero
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm7
|
|
; AVX1-NEXT: vpblendw {{.*#+}} xmm6 = xmm6[0,1],xmm7[2,3,4,5,6,7]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm3, %ymm3
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_58: ## %else110
|
|
; AVX1-NEXT: vpackssdw %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $13, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_60
|
|
; AVX1-NEXT: ## %bb.59: ## %cond.load113
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm5
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],mem[0],xmm5[2,3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_60: ## %else114
|
|
; AVX1-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX1-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm4
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX1-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_62
|
|
; AVX1-NEXT: ## %bb.61: ## %cond.load117
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm5
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX1-NEXT: addq $4, %rdi
|
|
; AVX1-NEXT: LBB8_62: ## %else118
|
|
; AVX1-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX1-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX1-NEXT: testb $1, %al
|
|
; AVX1-NEXT: je LBB8_64
|
|
; AVX1-NEXT: ## %bb.63: ## %cond.load121
|
|
; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm4
|
|
; AVX1-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX1-NEXT: LBB8_64: ## %else122
|
|
; AVX1-NEXT: retq
|
|
;
|
|
; AVX2-LABEL: expandload_v32f32_v32i32:
|
|
; AVX2: ## %bb.0:
|
|
; AVX2-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm9
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm9, %xmm9
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm9, %xmm9
|
|
; AVX2-NEXT: vpextrb $0, %xmm9, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_2
|
|
; AVX2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX2-NEXT: vmovd {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm9[0],ymm0[1,2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_2: ## %else
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm8
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpextrb $1, %xmm8, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_4
|
|
; AVX2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm8 = xmm0[0],mem[0],xmm0[2,3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm8[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_4: ## %else2
|
|
; AVX2-NEXT: vxorps %xmm8, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm9
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm9, %xmm9
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm9, %xmm9
|
|
; AVX2-NEXT: vpextrb $2, %xmm9, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_6
|
|
; AVX2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm9 = xmm0[0,1],mem[0],xmm0[3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm9[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_6: ## %else6
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm4, %xmm8
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpextrb $3, %xmm8, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_8
|
|
; AVX2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm8 = xmm0[0,1,2],mem[0]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm8[0,1,2,3],ymm0[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_8: ## %else10
|
|
; AVX2-NEXT: vextracti128 $1, %ymm4, %xmm8
|
|
; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm9
|
|
; AVX2-NEXT: vpackssdw %xmm9, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $4, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_10
|
|
; AVX2-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX2-NEXT: vmovss {{.*#+}} xmm10 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX2-NEXT: vblendps {{.*#+}} xmm4 = xmm10[0],xmm4[1,2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_10: ## %else14
|
|
; AVX2-NEXT: vpackssdw %xmm9, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $5, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_12
|
|
; AVX2-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_12: ## %else18
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpackssdw %xmm8, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $6, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_14
|
|
; AVX2-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],mem[0],xmm4[3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_14: ## %else22
|
|
; AVX2-NEXT: vpackssdw %xmm8, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_16
|
|
; AVX2-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_16: ## %else26
|
|
; AVX2-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $8, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_18
|
|
; AVX2-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX2-NEXT: vmovd {{.*#+}} xmm4 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm4[0],ymm1[1,2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_18: ## %else30
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_20
|
|
; AVX2-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0],mem[0],xmm1[2,3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_20: ## %else34
|
|
; AVX2-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $10, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_22
|
|
; AVX2-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0,1],mem[0],xmm1[3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_22: ## %else38
|
|
; AVX2-NEXT: vpcmpeqd %xmm8, %xmm5, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_24
|
|
; AVX2-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm1[0,1,2],mem[0]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_24: ## %else42
|
|
; AVX2-NEXT: vextracti128 $1, %ymm5, %xmm8
|
|
; AVX2-NEXT: vpxor %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm8, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $12, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_26
|
|
; AVX2-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX2-NEXT: vmovss {{.*#+}} xmm9 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX2-NEXT: vblendps {{.*#+}} xmm4 = xmm9[0],xmm4[1,2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_26: ## %else46
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $13, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_28
|
|
; AVX2-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_28: ## %else50
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_30
|
|
; AVX2-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm5
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm5, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_30: ## %else54
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_32
|
|
; AVX2-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_32: ## %else58
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpextrb $0, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_34
|
|
; AVX2-NEXT: ## %bb.33: ## %cond.load61
|
|
; AVX2-NEXT: vmovd {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm5[0],ymm2[1,2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_34: ## %else62
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $1, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_36
|
|
; AVX2-NEXT: ## %bb.35: ## %cond.load65
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm2[0],mem[0],xmm2[2,3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_36: ## %else66
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpextrb $2, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_38
|
|
; AVX2-NEXT: ## %bb.37: ## %cond.load69
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm2[0,1],mem[0],xmm2[3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm5[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_38: ## %else70
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm6, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $3, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_40
|
|
; AVX2-NEXT: ## %bb.39: ## %cond.load73
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm2[0,1,2],mem[0]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_40: ## %else74
|
|
; AVX2-NEXT: vextracti128 $1, %ymm6, %xmm8
|
|
; AVX2-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm8, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm6, %xmm6
|
|
; AVX2-NEXT: vpextrb $4, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_42
|
|
; AVX2-NEXT: ## %bb.41: ## %cond.load77
|
|
; AVX2-NEXT: vmovss {{.*#+}} xmm6 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX2-NEXT: vblendps {{.*#+}} xmm4 = xmm6[0],xmm4[1,2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_42: ## %else78
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $5, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_44
|
|
; AVX2-NEXT: ## %bb.43: ## %cond.load81
|
|
; AVX2-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],mem[0],xmm4[2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_44: ## %else82
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm8, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpextrb $6, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_46
|
|
; AVX2-NEXT: ## %bb.45: ## %cond.load85
|
|
; AVX2-NEXT: vextractf128 $1, %ymm2, %xmm5
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm5, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_46: ## %else86
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpextrb $7, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_48
|
|
; AVX2-NEXT: ## %bb.47: ## %cond.load89
|
|
; AVX2-NEXT: vextractf128 $1, %ymm2, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm2, %ymm2
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_48: ## %else90
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $8, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_50
|
|
; AVX2-NEXT: ## %bb.49: ## %cond.load93
|
|
; AVX2-NEXT: vmovd {{.*#+}} xmm5 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vpblendd {{.*#+}} ymm3 = ymm5[0],ymm3[1,2,3,4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_50: ## %else94
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $9, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_52
|
|
; AVX2-NEXT: ## %bb.51: ## %cond.load97
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm3[0],mem[0],xmm3[2,3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_52: ## %else98
|
|
; AVX2-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $10, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_54
|
|
; AVX2-NEXT: ## %bb.53: ## %cond.load101
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm3[0,1],mem[0],xmm3[3]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm5[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_54: ## %else102
|
|
; AVX2-NEXT: vpcmpeqd %xmm4, %xmm7, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm0, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $11, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_56
|
|
; AVX2-NEXT: ## %bb.55: ## %cond.load105
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm3[0,1,2],mem[0]
|
|
; AVX2-NEXT: vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_56: ## %else106
|
|
; AVX2-NEXT: vextracti128 $1, %ymm7, %xmm4
|
|
; AVX2-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm5
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpacksswb %xmm6, %xmm0, %xmm6
|
|
; AVX2-NEXT: vpextrb $12, %xmm6, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_58
|
|
; AVX2-NEXT: ## %bb.57: ## %cond.load109
|
|
; AVX2-NEXT: vmovss {{.*#+}} xmm6 = mem[0],zero,zero,zero
|
|
; AVX2-NEXT: vextractf128 $1, %ymm3, %xmm7
|
|
; AVX2-NEXT: vblendps {{.*#+}} xmm6 = xmm6[0],xmm7[1,2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm6, %ymm3, %ymm3
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_58: ## %else110
|
|
; AVX2-NEXT: vpackssdw %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $13, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_60
|
|
; AVX2-NEXT: ## %bb.59: ## %cond.load113
|
|
; AVX2-NEXT: vextractf128 $1, %ymm3, %xmm5
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],mem[0],xmm5[2,3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_60: ## %else114
|
|
; AVX2-NEXT: vxorps %xmm5, %xmm5, %xmm5
|
|
; AVX2-NEXT: vpcmpeqd %xmm5, %xmm4, %xmm4
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpacksswb %xmm5, %xmm0, %xmm5
|
|
; AVX2-NEXT: vpextrb $14, %xmm5, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_62
|
|
; AVX2-NEXT: ## %bb.61: ## %cond.load117
|
|
; AVX2-NEXT: vextractf128 $1, %ymm3, %xmm5
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],mem[0],xmm5[3]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm5, %ymm3, %ymm3
|
|
; AVX2-NEXT: addq $4, %rdi
|
|
; AVX2-NEXT: LBB8_62: ## %else118
|
|
; AVX2-NEXT: vpackssdw %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpacksswb %xmm4, %xmm0, %xmm4
|
|
; AVX2-NEXT: vpextrb $15, %xmm4, %eax
|
|
; AVX2-NEXT: testb $1, %al
|
|
; AVX2-NEXT: je LBB8_64
|
|
; AVX2-NEXT: ## %bb.63: ## %cond.load121
|
|
; AVX2-NEXT: vextractf128 $1, %ymm3, %xmm4
|
|
; AVX2-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1,2],mem[0]
|
|
; AVX2-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
|
|
; AVX2-NEXT: LBB8_64: ## %else122
|
|
; AVX2-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: expandload_v32f32_v32i32:
|
|
; AVX512: ## %bb.0:
|
|
; AVX512-NEXT: vptestnmd %zmm3, %zmm3, %k2
|
|
; AVX512-NEXT: vptestnmd %zmm2, %zmm2, %k1
|
|
; AVX512-NEXT: kmovw %k1, %eax
|
|
; AVX512-NEXT: movl %eax, %ecx
|
|
; AVX512-NEXT: shrl %ecx
|
|
; AVX512-NEXT: andl $21845, %ecx ## imm = 0x5555
|
|
; AVX512-NEXT: subl %ecx, %eax
|
|
; AVX512-NEXT: movl %eax, %ecx
|
|
; AVX512-NEXT: andl $858993459, %ecx ## imm = 0x33333333
|
|
; AVX512-NEXT: shrl $2, %eax
|
|
; AVX512-NEXT: andl $858993459, %eax ## imm = 0x33333333
|
|
; AVX512-NEXT: addl %ecx, %eax
|
|
; AVX512-NEXT: movl %eax, %ecx
|
|
; AVX512-NEXT: shrl $4, %ecx
|
|
; AVX512-NEXT: addl %eax, %ecx
|
|
; AVX512-NEXT: andl $252645135, %ecx ## imm = 0xF0F0F0F
|
|
; AVX512-NEXT: imull $16843009, %ecx, %eax ## imm = 0x1010101
|
|
; AVX512-NEXT: shrl $24, %eax
|
|
; AVX512-NEXT: vexpandps (%rdi,%rax,4), %zmm1 {%k2}
|
|
; AVX512-NEXT: vexpandps (%rdi), %zmm0 {%k1}
|
|
; AVX512-NEXT: retq
|
|
%mask = icmp eq <32 x i32> %trigger, zeroinitializer
|
|
%res = call <32 x float> @llvm.masked.expandload.v32f32(float* %base, <32 x i1> %mask, <32 x float> %src0)
|
|
ret <32 x float> %res
|
|
}
|
|
|
|
;
|
|
; vXi64
|
|
;
|
|
|
|
define <2 x i64> @expandload_v2i64_const(i64* %base, <2 x i64> %src0) {
|
|
; SSE2-LABEL: expandload_v2i64_const:
|
|
; SSE2: ## %bb.0: ## %else
|
|
; SSE2-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
|
; SSE2-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v2i64_const:
|
|
; SSE42: ## %bb.0: ## %else
|
|
; SSE42-NEXT: pinsrq $1, (%rdi), %xmm0
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v2i64_const:
|
|
; AVX1OR2: ## %bb.0: ## %else
|
|
; AVX1OR2-NEXT: vpinsrq $1, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v2i64_const:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
|
|
; AVX512F-NEXT: movb $2, %al
|
|
; AVX512F-NEXT: kmovw %eax, %k1
|
|
; AVX512F-NEXT: vpexpandq (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v2i64_const:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: movb $2, %al
|
|
; AVX512VLDQ-NEXT: kmovw %eax, %k1
|
|
; AVX512VLDQ-NEXT: vpexpandq (%rdi), %xmm0 {%k1}
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v2i64_const:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: movb $2, %al
|
|
; AVX512VLBW-NEXT: kmovd %eax, %k1
|
|
; AVX512VLBW-NEXT: vpexpandq (%rdi), %xmm0 {%k1}
|
|
; AVX512VLBW-NEXT: retq
|
|
%res = call <2 x i64> @llvm.masked.expandload.v2i64(i64* %base, <2 x i1> <i1 false, i1 true>, <2 x i64> %src0)
|
|
ret <2 x i64>%res
|
|
}
|
|
|
|
;
|
|
; vXi32
|
|
;
|
|
|
|
define <4 x i32> @expandload_v4i32_v4i32(i32* %base, <4 x i32> %src0, <4 x i32> %trigger) {
|
|
; SSE2-LABEL: expandload_v4i32_v4i32:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE2-NEXT: movd %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB10_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: movss {{.*#+}} xmm0 = xmm3[0],xmm0[1,2,3]
|
|
; SSE2-NEXT: addq $4, %rdi
|
|
; SSE2-NEXT: LBB10_2: ## %else
|
|
; SSE2-NEXT: pextrw $2, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB10_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm0[0,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm0[2,3]
|
|
; SSE2-NEXT: addq $4, %rdi
|
|
; SSE2-NEXT: movaps %xmm2, %xmm0
|
|
; SSE2-NEXT: LBB10_4: ## %else2
|
|
; SSE2-NEXT: xorps %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSE2-NEXT: pextrw $4, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB10_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm0[3,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm2[0,2]
|
|
; SSE2-NEXT: addq $4, %rdi
|
|
; SSE2-NEXT: LBB10_6: ## %else6
|
|
; SSE2-NEXT: pextrw $6, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB10_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[2,0]
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,0]
|
|
; SSE2-NEXT: LBB10_8: ## %else10
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v4i32_v4i32:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqd %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB10_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: pinsrd $0, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $4, %rdi
|
|
; SSE42-NEXT: LBB10_2: ## %else
|
|
; SSE42-NEXT: pextrb $4, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB10_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: pinsrd $1, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $4, %rdi
|
|
; SSE42-NEXT: LBB10_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqd %xmm2, %xmm1
|
|
; SSE42-NEXT: pextrb $8, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB10_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: pinsrd $2, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $4, %rdi
|
|
; SSE42-NEXT: LBB10_6: ## %else6
|
|
; SSE42-NEXT: pextrb $12, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB10_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: pinsrd $3, (%rdi), %xmm0
|
|
; SSE42-NEXT: LBB10_8: ## %else10
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v4i32_v4i32:
|
|
; AVX1OR2: ## %bb.0:
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqd %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $0, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB10_2
|
|
; AVX1OR2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1OR2-NEXT: vpinsrd $0, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $4, %rdi
|
|
; AVX1OR2-NEXT: LBB10_2: ## %else
|
|
; AVX1OR2-NEXT: vpextrb $4, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB10_4
|
|
; AVX1OR2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1OR2-NEXT: vpinsrd $1, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $4, %rdi
|
|
; AVX1OR2-NEXT: LBB10_4: ## %else2
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqd %xmm2, %xmm1, %xmm1
|
|
; AVX1OR2-NEXT: vpextrb $8, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB10_6
|
|
; AVX1OR2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1OR2-NEXT: vpinsrd $2, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $4, %rdi
|
|
; AVX1OR2-NEXT: LBB10_6: ## %else6
|
|
; AVX1OR2-NEXT: vpextrb $12, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB10_8
|
|
; AVX1OR2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1OR2-NEXT: vpinsrd $3, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: LBB10_8: ## %else10
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v4i32_v4i32:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
|
|
; AVX512F-NEXT: vptestnmd %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftlw $12, %k0, %k0
|
|
; AVX512F-NEXT: kshiftrw $12, %k0, %k1
|
|
; AVX512F-NEXT: vpexpandd (%rdi), %zmm0 {%k1}
|
|
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VL-LABEL: expandload_v4i32_v4i32:
|
|
; AVX512VL: ## %bb.0:
|
|
; AVX512VL-NEXT: vptestnmd %xmm1, %xmm1, %k1
|
|
; AVX512VL-NEXT: vpexpandd (%rdi), %xmm0 {%k1}
|
|
; AVX512VL-NEXT: retq
|
|
%mask = icmp eq <4 x i32> %trigger, zeroinitializer
|
|
%res = call <4 x i32> @llvm.masked.expandload.v4i32(i32* %base, <4 x i1> %mask, <4 x i32> %src0)
|
|
ret <4 x i32>%res
|
|
}
|
|
|
|
;
|
|
; vXi16
|
|
;
|
|
|
|
define <8 x i16> @expandload_v8i16_v8i16(i16* %base, <8 x i16> %src0, <8 x i16> %trigger) {
|
|
; SSE2-LABEL: expandload_v8i16_v8i16:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE2-NEXT: movd %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: pinsrw $0, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_2: ## %else
|
|
; SSE2-NEXT: shrl $16, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: pinsrw $1, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_4: ## %else2
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $2, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: pinsrw $2, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_6: ## %else6
|
|
; SSE2-NEXT: pextrw $3, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: pinsrw $3, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_8: ## %else10
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $4, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_10
|
|
; SSE2-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE2-NEXT: pinsrw $4, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_10: ## %else14
|
|
; SSE2-NEXT: pextrw $5, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_12
|
|
; SSE2-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE2-NEXT: pinsrw $5, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_12: ## %else18
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqw %xmm2, %xmm1
|
|
; SSE2-NEXT: pextrw $6, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_14
|
|
; SSE2-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE2-NEXT: pinsrw $6, (%rdi), %xmm0
|
|
; SSE2-NEXT: addq $2, %rdi
|
|
; SSE2-NEXT: LBB11_14: ## %else22
|
|
; SSE2-NEXT: pextrw $7, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB11_16
|
|
; SSE2-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE2-NEXT: pinsrw $7, (%rdi), %xmm0
|
|
; SSE2-NEXT: LBB11_16: ## %else26
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v8i16_v8i16:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: pinsrw $0, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_2: ## %else
|
|
; SSE42-NEXT: pextrb $2, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: pinsrw $1, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $4, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: pinsrw $2, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_6: ## %else6
|
|
; SSE42-NEXT: pextrb $6, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: pinsrw $3, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_8: ## %else10
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqw %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $8, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_10
|
|
; SSE42-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE42-NEXT: pinsrw $4, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_10: ## %else14
|
|
; SSE42-NEXT: pextrb $10, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_12
|
|
; SSE42-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE42-NEXT: pinsrw $5, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_12: ## %else18
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqw %xmm2, %xmm1
|
|
; SSE42-NEXT: pextrb $12, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_14
|
|
; SSE42-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE42-NEXT: pinsrw $6, (%rdi), %xmm0
|
|
; SSE42-NEXT: addq $2, %rdi
|
|
; SSE42-NEXT: LBB11_14: ## %else22
|
|
; SSE42-NEXT: pextrb $14, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB11_16
|
|
; SSE42-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE42-NEXT: pinsrw $7, (%rdi), %xmm0
|
|
; SSE42-NEXT: LBB11_16: ## %else26
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v8i16_v8i16:
|
|
; AVX1OR2: ## %bb.0:
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $0, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_2
|
|
; AVX1OR2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1OR2-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_2: ## %else
|
|
; AVX1OR2-NEXT: vpextrb $2, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_4
|
|
; AVX1OR2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1OR2-NEXT: vpinsrw $1, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_4: ## %else2
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $4, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_6
|
|
; AVX1OR2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1OR2-NEXT: vpinsrw $2, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_6: ## %else6
|
|
; AVX1OR2-NEXT: vpextrb $6, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_8
|
|
; AVX1OR2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1OR2-NEXT: vpinsrw $3, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_8: ## %else10
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $8, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_10
|
|
; AVX1OR2-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX1OR2-NEXT: vpinsrw $4, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_10: ## %else14
|
|
; AVX1OR2-NEXT: vpextrb $10, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_12
|
|
; AVX1OR2-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX1OR2-NEXT: vpinsrw $5, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_12: ## %else18
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm1
|
|
; AVX1OR2-NEXT: vpextrb $12, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_14
|
|
; AVX1OR2-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX1OR2-NEXT: vpinsrw $6, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: addq $2, %rdi
|
|
; AVX1OR2-NEXT: LBB11_14: ## %else22
|
|
; AVX1OR2-NEXT: vpextrb $14, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB11_16
|
|
; AVX1OR2-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX1OR2-NEXT: vpinsrw $7, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: LBB11_16: ## %else26
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v8i16_v8i16:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxwq %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmq %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_2
|
|
; AVX512F-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512F-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_2: ## %else
|
|
; AVX512F-NEXT: kshiftrw $1, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_4
|
|
; AVX512F-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512F-NEXT: vpinsrw $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_4: ## %else2
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxwq %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmq %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_6
|
|
; AVX512F-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512F-NEXT: vpinsrw $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_6: ## %else6
|
|
; AVX512F-NEXT: kshiftrw $3, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_8
|
|
; AVX512F-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512F-NEXT: vpinsrw $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_8: ## %else10
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxwq %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmq %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_10
|
|
; AVX512F-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512F-NEXT: vpinsrw $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_10: ## %else14
|
|
; AVX512F-NEXT: kshiftrw $5, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_12
|
|
; AVX512F-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512F-NEXT: vpinsrw $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_12: ## %else18
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm1
|
|
; AVX512F-NEXT: vpmovsxwq %xmm1, %zmm1
|
|
; AVX512F-NEXT: vptestmq %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftrw $6, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_14
|
|
; AVX512F-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512F-NEXT: vpinsrw $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: addq $2, %rdi
|
|
; AVX512F-NEXT: LBB11_14: ## %else22
|
|
; AVX512F-NEXT: kshiftrw $7, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB11_16
|
|
; AVX512F-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512F-NEXT: vpinsrw $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: LBB11_16: ## %else26
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v8i16_v8i16:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxwd %xmm2, %ymm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %ymm2, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_2
|
|
; AVX512VLDQ-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512VLDQ-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_2: ## %else
|
|
; AVX512VLDQ-NEXT: kshiftrb $1, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_4
|
|
; AVX512VLDQ-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512VLDQ-NEXT: vpinsrw $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_4: ## %else2
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxwd %xmm2, %ymm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %ymm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrb $2, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_6
|
|
; AVX512VLDQ-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512VLDQ-NEXT: vpinsrw $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_6: ## %else6
|
|
; AVX512VLDQ-NEXT: kshiftrb $3, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_8
|
|
; AVX512VLDQ-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512VLDQ-NEXT: vpinsrw $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_8: ## %else10
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxwd %xmm2, %ymm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %ymm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrb $4, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_10
|
|
; AVX512VLDQ-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512VLDQ-NEXT: vpinsrw $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_10: ## %else14
|
|
; AVX512VLDQ-NEXT: kshiftrb $5, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_12
|
|
; AVX512VLDQ-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512VLDQ-NEXT: vpinsrw $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_12: ## %else18
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqw %xmm2, %xmm1, %xmm1
|
|
; AVX512VLDQ-NEXT: vpmovsxwd %xmm1, %ymm1
|
|
; AVX512VLDQ-NEXT: vpmovd2m %ymm1, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrb $6, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_14
|
|
; AVX512VLDQ-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512VLDQ-NEXT: vpinsrw $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: addq $2, %rdi
|
|
; AVX512VLDQ-NEXT: LBB11_14: ## %else22
|
|
; AVX512VLDQ-NEXT: kshiftrb $7, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB11_16
|
|
; AVX512VLDQ-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512VLDQ-NEXT: vpinsrw $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: LBB11_16: ## %else26
|
|
; AVX512VLDQ-NEXT: vzeroupper
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v8i16_v8i16:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: vptestnmw %xmm1, %xmm1, %k0
|
|
; AVX512VLBW-NEXT: kmovd %k0, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_2
|
|
; AVX512VLBW-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512VLBW-NEXT: vpinsrw $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_2: ## %else
|
|
; AVX512VLBW-NEXT: kshiftrw $1, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_4
|
|
; AVX512VLBW-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512VLBW-NEXT: vpinsrw $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_4: ## %else2
|
|
; AVX512VLBW-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_6
|
|
; AVX512VLBW-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512VLBW-NEXT: vpinsrw $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_6: ## %else6
|
|
; AVX512VLBW-NEXT: kshiftrw $3, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_8
|
|
; AVX512VLBW-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512VLBW-NEXT: vpinsrw $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_8: ## %else10
|
|
; AVX512VLBW-NEXT: kshiftrw $4, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_10
|
|
; AVX512VLBW-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512VLBW-NEXT: vpinsrw $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_10: ## %else14
|
|
; AVX512VLBW-NEXT: kshiftrw $5, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_12
|
|
; AVX512VLBW-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512VLBW-NEXT: vpinsrw $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_12: ## %else18
|
|
; AVX512VLBW-NEXT: kshiftrw $6, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_14
|
|
; AVX512VLBW-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512VLBW-NEXT: vpinsrw $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: addq $2, %rdi
|
|
; AVX512VLBW-NEXT: LBB11_14: ## %else22
|
|
; AVX512VLBW-NEXT: kshiftrw $7, %k0, %k0
|
|
; AVX512VLBW-NEXT: kmovd %k0, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB11_16
|
|
; AVX512VLBW-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512VLBW-NEXT: vpinsrw $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: LBB11_16: ## %else26
|
|
; AVX512VLBW-NEXT: retq
|
|
%mask = icmp eq <8 x i16> %trigger, zeroinitializer
|
|
%res = call <8 x i16> @llvm.masked.expandload.v8i16(i16* %base, <8 x i1> %mask, <8 x i16> %src0)
|
|
ret <8 x i16>%res
|
|
}
|
|
|
|
;
|
|
; vXi8
|
|
;
|
|
|
|
define <16 x i8> @expandload_v16i8_v16i8(i8* %base, <16 x i8> %src0, <16 x i8> %trigger) {
|
|
; SSE2-LABEL: expandload_v16i8_v16i8:
|
|
; SSE2: ## %bb.0:
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: movd %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_2
|
|
; SSE2-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_2: ## %else
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_4
|
|
; SSE2-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: psllw $8, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_4: ## %else2
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: movd %xmm2, %eax
|
|
; SSE2-NEXT: movl %eax, %ecx
|
|
; SSE2-NEXT: shrl $16, %ecx
|
|
; SSE2-NEXT: testb $1, %cl
|
|
; SSE2-NEXT: je LBB12_6
|
|
; SSE2-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,0,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pslld $16, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_6: ## %else6
|
|
; SSE2-NEXT: shrl $24, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_8
|
|
; SSE2-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,0,255,255,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: pslld $24, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_8: ## %else10
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $2, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_10
|
|
; SSE2-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,0,255,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,0,1,1]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_10: ## %else14
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_12
|
|
; SSE2-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,0,255,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: psllq $40, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_12: ## %else18
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $3, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_14
|
|
; SSE2-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,0,255,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: psllq $48, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_14: ## %else22
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_16
|
|
; SSE2-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,0,255,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: psllq $56, %xmm3
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_16: ## %else26
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $4, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_18
|
|
; SSE2-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,0,255,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,1,0,1]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_18: ## %else30
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_20
|
|
; SSE2-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,0,255,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1,2,3,4,5,6]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_20: ## %else34
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $5, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_22
|
|
; SSE2-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,0,255,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1,2,3,4,5]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_22: ## %else38
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_24
|
|
; SSE2-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1,2,3,4]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_24: ## %else42
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE2-NEXT: pextrw $6, %xmm2, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_26
|
|
; SSE2-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,0,255,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm3
|
|
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,1,2,0]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_26: ## %else46
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_28
|
|
; SSE2-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255]
|
|
; SSE2-NEXT: pand %xmm2, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm3
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1,2]
|
|
; SSE2-NEXT: pandn %xmm3, %xmm2
|
|
; SSE2-NEXT: por %xmm2, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_28: ## %else50
|
|
; SSE2-NEXT: pxor %xmm2, %xmm2
|
|
; SSE2-NEXT: pcmpeqb %xmm2, %xmm1
|
|
; SSE2-NEXT: pextrw $7, %xmm1, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_30
|
|
; SSE2-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255]
|
|
; SSE2-NEXT: pand %xmm1, %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %ecx
|
|
; SSE2-NEXT: movd %ecx, %xmm2
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0,1]
|
|
; SSE2-NEXT: pandn %xmm2, %xmm1
|
|
; SSE2-NEXT: por %xmm1, %xmm0
|
|
; SSE2-NEXT: incq %rdi
|
|
; SSE2-NEXT: LBB12_30: ## %else54
|
|
; SSE2-NEXT: shrl $8, %eax
|
|
; SSE2-NEXT: testb $1, %al
|
|
; SSE2-NEXT: je LBB12_32
|
|
; SSE2-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
|
; SSE2-NEXT: movzbl (%rdi), %eax
|
|
; SSE2-NEXT: movd %eax, %xmm1
|
|
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0]
|
|
; SSE2-NEXT: por %xmm1, %xmm0
|
|
; SSE2-NEXT: LBB12_32: ## %else58
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE42-LABEL: expandload_v16i8_v16i8:
|
|
; SSE42: ## %bb.0:
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_2
|
|
; SSE42-NEXT: ## %bb.1: ## %cond.load
|
|
; SSE42-NEXT: pinsrb $0, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_2: ## %else
|
|
; SSE42-NEXT: pextrb $1, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_4
|
|
; SSE42-NEXT: ## %bb.3: ## %cond.load1
|
|
; SSE42-NEXT: pinsrb $1, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_4: ## %else2
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $2, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_6
|
|
; SSE42-NEXT: ## %bb.5: ## %cond.load5
|
|
; SSE42-NEXT: pinsrb $2, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_6: ## %else6
|
|
; SSE42-NEXT: pextrb $3, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_8
|
|
; SSE42-NEXT: ## %bb.7: ## %cond.load9
|
|
; SSE42-NEXT: pinsrb $3, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_8: ## %else10
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $4, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_10
|
|
; SSE42-NEXT: ## %bb.9: ## %cond.load13
|
|
; SSE42-NEXT: pinsrb $4, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_10: ## %else14
|
|
; SSE42-NEXT: pextrb $5, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_12
|
|
; SSE42-NEXT: ## %bb.11: ## %cond.load17
|
|
; SSE42-NEXT: pinsrb $5, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_12: ## %else18
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $6, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_14
|
|
; SSE42-NEXT: ## %bb.13: ## %cond.load21
|
|
; SSE42-NEXT: pinsrb $6, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_14: ## %else22
|
|
; SSE42-NEXT: pextrb $7, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_16
|
|
; SSE42-NEXT: ## %bb.15: ## %cond.load25
|
|
; SSE42-NEXT: pinsrb $7, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_16: ## %else26
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $8, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_18
|
|
; SSE42-NEXT: ## %bb.17: ## %cond.load29
|
|
; SSE42-NEXT: pinsrb $8, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_18: ## %else30
|
|
; SSE42-NEXT: pextrb $9, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_20
|
|
; SSE42-NEXT: ## %bb.19: ## %cond.load33
|
|
; SSE42-NEXT: pinsrb $9, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_20: ## %else34
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $10, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_22
|
|
; SSE42-NEXT: ## %bb.21: ## %cond.load37
|
|
; SSE42-NEXT: pinsrb $10, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_22: ## %else38
|
|
; SSE42-NEXT: pextrb $11, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_24
|
|
; SSE42-NEXT: ## %bb.23: ## %cond.load41
|
|
; SSE42-NEXT: pinsrb $11, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_24: ## %else42
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm1, %xmm2
|
|
; SSE42-NEXT: pextrb $12, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_26
|
|
; SSE42-NEXT: ## %bb.25: ## %cond.load45
|
|
; SSE42-NEXT: pinsrb $12, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_26: ## %else46
|
|
; SSE42-NEXT: pextrb $13, %xmm2, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_28
|
|
; SSE42-NEXT: ## %bb.27: ## %cond.load49
|
|
; SSE42-NEXT: pinsrb $13, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_28: ## %else50
|
|
; SSE42-NEXT: pxor %xmm2, %xmm2
|
|
; SSE42-NEXT: pcmpeqb %xmm2, %xmm1
|
|
; SSE42-NEXT: pextrb $14, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_30
|
|
; SSE42-NEXT: ## %bb.29: ## %cond.load53
|
|
; SSE42-NEXT: pinsrb $14, (%rdi), %xmm0
|
|
; SSE42-NEXT: incq %rdi
|
|
; SSE42-NEXT: LBB12_30: ## %else54
|
|
; SSE42-NEXT: pextrb $15, %xmm1, %eax
|
|
; SSE42-NEXT: testb $1, %al
|
|
; SSE42-NEXT: je LBB12_32
|
|
; SSE42-NEXT: ## %bb.31: ## %cond.load57
|
|
; SSE42-NEXT: pinsrb $15, (%rdi), %xmm0
|
|
; SSE42-NEXT: LBB12_32: ## %else58
|
|
; SSE42-NEXT: retq
|
|
;
|
|
; AVX1OR2-LABEL: expandload_v16i8_v16i8:
|
|
; AVX1OR2: ## %bb.0:
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $0, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_2
|
|
; AVX1OR2-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX1OR2-NEXT: vpinsrb $0, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_2: ## %else
|
|
; AVX1OR2-NEXT: vpextrb $1, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_4
|
|
; AVX1OR2-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX1OR2-NEXT: vpinsrb $1, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_4: ## %else2
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $2, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_6
|
|
; AVX1OR2-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX1OR2-NEXT: vpinsrb $2, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_6: ## %else6
|
|
; AVX1OR2-NEXT: vpextrb $3, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_8
|
|
; AVX1OR2-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX1OR2-NEXT: vpinsrb $3, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_8: ## %else10
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $4, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_10
|
|
; AVX1OR2-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX1OR2-NEXT: vpinsrb $4, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_10: ## %else14
|
|
; AVX1OR2-NEXT: vpextrb $5, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_12
|
|
; AVX1OR2-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX1OR2-NEXT: vpinsrb $5, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_12: ## %else18
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $6, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_14
|
|
; AVX1OR2-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX1OR2-NEXT: vpinsrb $6, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_14: ## %else22
|
|
; AVX1OR2-NEXT: vpextrb $7, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_16
|
|
; AVX1OR2-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX1OR2-NEXT: vpinsrb $7, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_16: ## %else26
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $8, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_18
|
|
; AVX1OR2-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX1OR2-NEXT: vpinsrb $8, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_18: ## %else30
|
|
; AVX1OR2-NEXT: vpextrb $9, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_20
|
|
; AVX1OR2-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX1OR2-NEXT: vpinsrb $9, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_20: ## %else34
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $10, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_22
|
|
; AVX1OR2-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX1OR2-NEXT: vpinsrb $10, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_22: ## %else38
|
|
; AVX1OR2-NEXT: vpextrb $11, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_24
|
|
; AVX1OR2-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX1OR2-NEXT: vpinsrb $11, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_24: ## %else42
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX1OR2-NEXT: vpextrb $12, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_26
|
|
; AVX1OR2-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX1OR2-NEXT: vpinsrb $12, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_26: ## %else46
|
|
; AVX1OR2-NEXT: vpextrb $13, %xmm2, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_28
|
|
; AVX1OR2-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX1OR2-NEXT: vpinsrb $13, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_28: ## %else50
|
|
; AVX1OR2-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX1OR2-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1
|
|
; AVX1OR2-NEXT: vpextrb $14, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_30
|
|
; AVX1OR2-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX1OR2-NEXT: vpinsrb $14, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: incq %rdi
|
|
; AVX1OR2-NEXT: LBB12_30: ## %else54
|
|
; AVX1OR2-NEXT: vpextrb $15, %xmm1, %eax
|
|
; AVX1OR2-NEXT: testb $1, %al
|
|
; AVX1OR2-NEXT: je LBB12_32
|
|
; AVX1OR2-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX1OR2-NEXT: vpinsrb $15, (%rdi), %xmm0, %xmm0
|
|
; AVX1OR2-NEXT: LBB12_32: ## %else58
|
|
; AVX1OR2-NEXT: retq
|
|
;
|
|
; AVX512F-LABEL: expandload_v16i8_v16i8:
|
|
; AVX512F: ## %bb.0:
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_2
|
|
; AVX512F-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512F-NEXT: vpinsrb $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_2: ## %else
|
|
; AVX512F-NEXT: kshiftrw $1, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_4
|
|
; AVX512F-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512F-NEXT: vpinsrb $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_4: ## %else2
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_6
|
|
; AVX512F-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512F-NEXT: vpinsrb $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_6: ## %else6
|
|
; AVX512F-NEXT: kshiftrw $3, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_8
|
|
; AVX512F-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512F-NEXT: vpinsrb $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_8: ## %else10
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $4, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_10
|
|
; AVX512F-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512F-NEXT: vpinsrb $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_10: ## %else14
|
|
; AVX512F-NEXT: kshiftrw $5, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_12
|
|
; AVX512F-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512F-NEXT: vpinsrb $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_12: ## %else18
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $6, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_14
|
|
; AVX512F-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512F-NEXT: vpinsrb $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_14: ## %else22
|
|
; AVX512F-NEXT: kshiftrw $7, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_16
|
|
; AVX512F-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512F-NEXT: vpinsrb $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_16: ## %else26
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $8, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_18
|
|
; AVX512F-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX512F-NEXT: vpinsrb $8, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_18: ## %else30
|
|
; AVX512F-NEXT: kshiftrw $9, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_20
|
|
; AVX512F-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX512F-NEXT: vpinsrb $9, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_20: ## %else34
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $10, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_22
|
|
; AVX512F-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX512F-NEXT: vpinsrb $10, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_22: ## %else38
|
|
; AVX512F-NEXT: kshiftrw $11, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_24
|
|
; AVX512F-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX512F-NEXT: vpinsrb $11, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_24: ## %else42
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k0
|
|
; AVX512F-NEXT: kshiftrw $12, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_26
|
|
; AVX512F-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX512F-NEXT: vpinsrb $12, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_26: ## %else46
|
|
; AVX512F-NEXT: kshiftrw $13, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_28
|
|
; AVX512F-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX512F-NEXT: vpinsrb $13, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_28: ## %else50
|
|
; AVX512F-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512F-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1
|
|
; AVX512F-NEXT: vpmovsxbd %xmm1, %zmm1
|
|
; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k0
|
|
; AVX512F-NEXT: kshiftrw $14, %k0, %k1
|
|
; AVX512F-NEXT: kmovw %k1, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_30
|
|
; AVX512F-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX512F-NEXT: vpinsrb $14, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: incq %rdi
|
|
; AVX512F-NEXT: LBB12_30: ## %else54
|
|
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
|
|
; AVX512F-NEXT: kmovw %k0, %eax
|
|
; AVX512F-NEXT: testb $1, %al
|
|
; AVX512F-NEXT: je LBB12_32
|
|
; AVX512F-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX512F-NEXT: vpinsrb $15, (%rdi), %xmm0, %xmm0
|
|
; AVX512F-NEXT: LBB12_32: ## %else58
|
|
; AVX512F-NEXT: vzeroupper
|
|
; AVX512F-NEXT: retq
|
|
;
|
|
; AVX512VLDQ-LABEL: expandload_v16i8_v16i8:
|
|
; AVX512VLDQ: ## %bb.0:
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_2
|
|
; AVX512VLDQ-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512VLDQ-NEXT: vpinsrb $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_2: ## %else
|
|
; AVX512VLDQ-NEXT: kshiftrw $1, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_4
|
|
; AVX512VLDQ-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512VLDQ-NEXT: vpinsrb $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_4: ## %else2
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_6
|
|
; AVX512VLDQ-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512VLDQ-NEXT: vpinsrb $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_6: ## %else6
|
|
; AVX512VLDQ-NEXT: kshiftrw $3, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_8
|
|
; AVX512VLDQ-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512VLDQ-NEXT: vpinsrb $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_8: ## %else10
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $4, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_10
|
|
; AVX512VLDQ-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512VLDQ-NEXT: vpinsrb $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_10: ## %else14
|
|
; AVX512VLDQ-NEXT: kshiftrw $5, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_12
|
|
; AVX512VLDQ-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512VLDQ-NEXT: vpinsrb $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_12: ## %else18
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $6, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_14
|
|
; AVX512VLDQ-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512VLDQ-NEXT: vpinsrb $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_14: ## %else22
|
|
; AVX512VLDQ-NEXT: kshiftrw $7, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_16
|
|
; AVX512VLDQ-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512VLDQ-NEXT: vpinsrb $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_16: ## %else26
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $8, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_18
|
|
; AVX512VLDQ-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX512VLDQ-NEXT: vpinsrb $8, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_18: ## %else30
|
|
; AVX512VLDQ-NEXT: kshiftrw $9, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_20
|
|
; AVX512VLDQ-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX512VLDQ-NEXT: vpinsrb $9, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_20: ## %else34
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $10, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_22
|
|
; AVX512VLDQ-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX512VLDQ-NEXT: vpinsrb $10, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_22: ## %else38
|
|
; AVX512VLDQ-NEXT: kshiftrw $11, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_24
|
|
; AVX512VLDQ-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX512VLDQ-NEXT: vpinsrb $11, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_24: ## %else42
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm2
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm2, %zmm2
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm2, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $12, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_26
|
|
; AVX512VLDQ-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX512VLDQ-NEXT: vpinsrb $12, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_26: ## %else46
|
|
; AVX512VLDQ-NEXT: kshiftrw $13, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_28
|
|
; AVX512VLDQ-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX512VLDQ-NEXT: vpinsrb $13, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_28: ## %else50
|
|
; AVX512VLDQ-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
|
; AVX512VLDQ-NEXT: vpcmpeqb %xmm2, %xmm1, %xmm1
|
|
; AVX512VLDQ-NEXT: vpmovsxbd %xmm1, %zmm1
|
|
; AVX512VLDQ-NEXT: vpmovd2m %zmm1, %k0
|
|
; AVX512VLDQ-NEXT: kshiftrw $14, %k0, %k1
|
|
; AVX512VLDQ-NEXT: kmovw %k1, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_30
|
|
; AVX512VLDQ-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX512VLDQ-NEXT: vpinsrb $14, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: incq %rdi
|
|
; AVX512VLDQ-NEXT: LBB12_30: ## %else54
|
|
; AVX512VLDQ-NEXT: kshiftrw $15, %k0, %k0
|
|
; AVX512VLDQ-NEXT: kmovw %k0, %eax
|
|
; AVX512VLDQ-NEXT: testb $1, %al
|
|
; AVX512VLDQ-NEXT: je LBB12_32
|
|
; AVX512VLDQ-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX512VLDQ-NEXT: vpinsrb $15, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLDQ-NEXT: LBB12_32: ## %else58
|
|
; AVX512VLDQ-NEXT: vzeroupper
|
|
; AVX512VLDQ-NEXT: retq
|
|
;
|
|
; AVX512VLBW-LABEL: expandload_v16i8_v16i8:
|
|
; AVX512VLBW: ## %bb.0:
|
|
; AVX512VLBW-NEXT: vptestnmb %xmm1, %xmm1, %k0
|
|
; AVX512VLBW-NEXT: kmovd %k0, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_2
|
|
; AVX512VLBW-NEXT: ## %bb.1: ## %cond.load
|
|
; AVX512VLBW-NEXT: vpinsrb $0, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_2: ## %else
|
|
; AVX512VLBW-NEXT: kshiftrw $1, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_4
|
|
; AVX512VLBW-NEXT: ## %bb.3: ## %cond.load1
|
|
; AVX512VLBW-NEXT: vpinsrb $1, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_4: ## %else2
|
|
; AVX512VLBW-NEXT: kshiftrw $2, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_6
|
|
; AVX512VLBW-NEXT: ## %bb.5: ## %cond.load5
|
|
; AVX512VLBW-NEXT: vpinsrb $2, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_6: ## %else6
|
|
; AVX512VLBW-NEXT: kshiftrw $3, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_8
|
|
; AVX512VLBW-NEXT: ## %bb.7: ## %cond.load9
|
|
; AVX512VLBW-NEXT: vpinsrb $3, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_8: ## %else10
|
|
; AVX512VLBW-NEXT: kshiftrw $4, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_10
|
|
; AVX512VLBW-NEXT: ## %bb.9: ## %cond.load13
|
|
; AVX512VLBW-NEXT: vpinsrb $4, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_10: ## %else14
|
|
; AVX512VLBW-NEXT: kshiftrw $5, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_12
|
|
; AVX512VLBW-NEXT: ## %bb.11: ## %cond.load17
|
|
; AVX512VLBW-NEXT: vpinsrb $5, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_12: ## %else18
|
|
; AVX512VLBW-NEXT: kshiftrw $6, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_14
|
|
; AVX512VLBW-NEXT: ## %bb.13: ## %cond.load21
|
|
; AVX512VLBW-NEXT: vpinsrb $6, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_14: ## %else22
|
|
; AVX512VLBW-NEXT: kshiftrw $7, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_16
|
|
; AVX512VLBW-NEXT: ## %bb.15: ## %cond.load25
|
|
; AVX512VLBW-NEXT: vpinsrb $7, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_16: ## %else26
|
|
; AVX512VLBW-NEXT: kshiftrw $8, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_18
|
|
; AVX512VLBW-NEXT: ## %bb.17: ## %cond.load29
|
|
; AVX512VLBW-NEXT: vpinsrb $8, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_18: ## %else30
|
|
; AVX512VLBW-NEXT: kshiftrw $9, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_20
|
|
; AVX512VLBW-NEXT: ## %bb.19: ## %cond.load33
|
|
; AVX512VLBW-NEXT: vpinsrb $9, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_20: ## %else34
|
|
; AVX512VLBW-NEXT: kshiftrw $10, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_22
|
|
; AVX512VLBW-NEXT: ## %bb.21: ## %cond.load37
|
|
; AVX512VLBW-NEXT: vpinsrb $10, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_22: ## %else38
|
|
; AVX512VLBW-NEXT: kshiftrw $11, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_24
|
|
; AVX512VLBW-NEXT: ## %bb.23: ## %cond.load41
|
|
; AVX512VLBW-NEXT: vpinsrb $11, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_24: ## %else42
|
|
; AVX512VLBW-NEXT: kshiftrw $12, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_26
|
|
; AVX512VLBW-NEXT: ## %bb.25: ## %cond.load45
|
|
; AVX512VLBW-NEXT: vpinsrb $12, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_26: ## %else46
|
|
; AVX512VLBW-NEXT: kshiftrw $13, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_28
|
|
; AVX512VLBW-NEXT: ## %bb.27: ## %cond.load49
|
|
; AVX512VLBW-NEXT: vpinsrb $13, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_28: ## %else50
|
|
; AVX512VLBW-NEXT: kshiftrw $14, %k0, %k1
|
|
; AVX512VLBW-NEXT: kmovd %k1, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_30
|
|
; AVX512VLBW-NEXT: ## %bb.29: ## %cond.load53
|
|
; AVX512VLBW-NEXT: vpinsrb $14, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: incq %rdi
|
|
; AVX512VLBW-NEXT: LBB12_30: ## %else54
|
|
; AVX512VLBW-NEXT: kshiftrw $15, %k0, %k0
|
|
; AVX512VLBW-NEXT: kmovd %k0, %eax
|
|
; AVX512VLBW-NEXT: testb $1, %al
|
|
; AVX512VLBW-NEXT: je LBB12_32
|
|
; AVX512VLBW-NEXT: ## %bb.31: ## %cond.load57
|
|
; AVX512VLBW-NEXT: vpinsrb $15, (%rdi), %xmm0, %xmm0
|
|
; AVX512VLBW-NEXT: LBB12_32: ## %else58
|
|
; AVX512VLBW-NEXT: retq
|
|
%mask = icmp eq <16 x i8> %trigger, zeroinitializer
|
|
%res = call <16 x i8> @llvm.masked.expandload.v16i8(i8* %base, <16 x i1> %mask, <16 x i8> %src0)
|
|
ret <16 x i8>%res
|
|
}
|
|
|
|
declare <16 x double> @llvm.masked.expandload.v16f64(double*, <16 x i1>, <16 x double>)
|
|
declare <8 x double> @llvm.masked.expandload.v8f64(double*, <8 x i1>, <8 x double>)
|
|
declare <4 x double> @llvm.masked.expandload.v4f64(double*, <4 x i1>, <4 x double>)
|
|
declare <2 x double> @llvm.masked.expandload.v2f64(double*, <2 x i1>, <2 x double>)
|
|
declare <1 x double> @llvm.masked.expandload.v1f64(double*, <1 x i1>, <1 x double>)
|
|
|
|
declare <32 x float> @llvm.masked.expandload.v32f32(float*, <32 x i1>, <32 x float>)
|
|
declare <16 x float> @llvm.masked.expandload.v16f32(float*, <16 x i1>, <16 x float>)
|
|
declare <8 x float> @llvm.masked.expandload.v8f32(float*, <8 x i1>, <8 x float>)
|
|
declare <4 x float> @llvm.masked.expandload.v4f32(float*, <4 x i1>, <4 x float>)
|
|
declare <2 x float> @llvm.masked.expandload.v2f32(float*, <2 x i1>, <2 x float>)
|
|
|
|
declare <8 x i64> @llvm.masked.expandload.v8i64(i64*, <8 x i1>, <8 x i64>)
|
|
declare <4 x i64> @llvm.masked.expandload.v4i64(i64*, <4 x i1>, <4 x i64>)
|
|
declare <2 x i64> @llvm.masked.expandload.v2i64(i64*, <2 x i1>, <2 x i64>)
|
|
declare <1 x i64> @llvm.masked.expandload.v1i64(i64*, <1 x i1>, <1 x i64>)
|
|
|
|
declare <16 x i32> @llvm.masked.expandload.v16i32(i32*, <16 x i1>, <16 x i32>)
|
|
declare <8 x i32> @llvm.masked.expandload.v8i32(i32*, <8 x i1>, <8 x i32>)
|
|
declare <4 x i32> @llvm.masked.expandload.v4i32(i32*, <4 x i1>, <4 x i32>)
|
|
declare <2 x i32> @llvm.masked.expandload.v2i32(i32*, <2 x i1>, <2 x i32>)
|
|
|
|
declare <32 x i16> @llvm.masked.expandload.v32i16(i16*, <32 x i1>, <32 x i16>)
|
|
declare <16 x i16> @llvm.masked.expandload.v16i16(i16*, <16 x i1>, <16 x i16>)
|
|
declare <8 x i16> @llvm.masked.expandload.v8i16(i16*, <8 x i1>, <8 x i16>)
|
|
declare <4 x i16> @llvm.masked.expandload.v4i16(i16*, <4 x i1>, <4 x i16>)
|
|
|
|
declare <64 x i8> @llvm.masked.expandload.v64i8(i8*, <64 x i1>, <64 x i8>)
|
|
declare <32 x i8> @llvm.masked.expandload.v32i8(i8*, <32 x i1>, <32 x i8>)
|
|
declare <16 x i8> @llvm.masked.expandload.v16i8(i8*, <16 x i1>, <16 x i8>)
|
|
declare <8 x i8> @llvm.masked.expandload.v8i8(i8*, <8 x i1>, <8 x i8>)
|