forked from OSchip/llvm-project
[x86] auto-generate complete checks for tests; NFC
These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
This commit is contained in:
Sanjay Patel
parent
decfaca033
commit
d3173740fd
|
|
@ -1,25 +1,59 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
|
||||
|
||||
; CHECK: vcmpltps %ymm
|
||||
; CHECK-NOT: vucomiss
|
||||
define <8 x i32> @cmp00(<8 x float> %a, <8 x float> %b) nounwind readnone {
|
||||
define <8 x i32> @cmp00(<8 x float> %a, <8 x float> %b) nounwind {
|
||||
; CHECK-LABEL: cmp00:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vcmpltps %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = fcmp olt <8 x float> %a, %b
|
||||
%s = sext <8 x i1> %bincmp to <8 x i32>
|
||||
ret <8 x i32> %s
|
||||
}
|
||||
|
||||
; CHECK: vcmpltpd %ymm
|
||||
; CHECK-NOT: vucomisd
|
||||
define <4 x i64> @cmp01(<4 x double> %a, <4 x double> %b) nounwind readnone {
|
||||
define <4 x i64> @cmp01(<4 x double> %a, <4 x double> %b) nounwind {
|
||||
; CHECK-LABEL: cmp01:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vcmpltpd %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = fcmp olt <4 x double> %a, %b
|
||||
%s = sext <4 x i1> %bincmp to <4 x i64>
|
||||
ret <4 x i64> %s
|
||||
}
|
||||
|
||||
declare void @scale() nounwind uwtable
|
||||
declare void @scale() nounwind
|
||||
|
||||
; CHECK: vucomisd
|
||||
define void @render() nounwind uwtable {
|
||||
define void @render() nounwind {
|
||||
; CHECK-LABEL: render:
|
||||
; CHECK: # BB#0: # %entry
|
||||
; CHECK-NEXT: pushq %rbx
|
||||
; CHECK-NEXT: xorl %eax, %eax
|
||||
; CHECK-NEXT: testb %al, %al
|
||||
; CHECK-NEXT: jne .LBB2_6
|
||||
; CHECK-NEXT: # BB#1: # %for.cond5.preheader
|
||||
; CHECK-NEXT: xorl %ebx, %ebx
|
||||
; CHECK-NEXT: jmp .LBB2_2
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB2_5: # %if.then
|
||||
; CHECK-NEXT: # in Loop: Header=BB2_2 Depth=1
|
||||
; CHECK-NEXT: callq scale
|
||||
; CHECK-NEXT: .LBB2_2: # %for.cond5
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; CHECK-NEXT: testb %bl, %bl
|
||||
; CHECK-NEXT: jne .LBB2_2
|
||||
; CHECK-NEXT: # BB#3: # %for.cond5
|
||||
; CHECK-NEXT: # in Loop: Header=BB2_2 Depth=1
|
||||
; CHECK-NEXT: testb %bl, %bl
|
||||
; CHECK-NEXT: je .LBB2_2
|
||||
; CHECK-NEXT: # BB#4: # %for.body33
|
||||
; CHECK-NEXT: # in Loop: Header=BB2_2 Depth=1
|
||||
; CHECK-NEXT: vucomisd {{\.LCPI.*}}, %xmm0
|
||||
; CHECK-NEXT: jne .LBB2_5
|
||||
; CHECK-NEXT: jp .LBB2_5
|
||||
; CHECK-NEXT: jmp .LBB2_2
|
||||
; CHECK-NEXT: .LBB2_6: # %for.end52
|
||||
; CHECK-NEXT: popq %rbx
|
||||
; CHECK-NEXT: retq
|
||||
entry:
|
||||
br i1 undef, label %for.cond5, label %for.end52
|
||||
|
||||
|
|
@ -42,89 +76,113 @@ for.end52:
|
|||
ret void
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpgtd %xmm
|
||||
; CHECK-NEXT: vpcmpgtd %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <8 x i32> @int256-cmp(<8 x i32> %i, <8 x i32> %j) nounwind readnone {
|
||||
define <8 x i32> @int256_cmp(<8 x i32> %i, <8 x i32> %j) nounwind {
|
||||
; CHECK-LABEL: int256_cmp:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpgtd %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp slt <8 x i32> %i, %j
|
||||
%x = sext <8 x i1> %bincmp to <8 x i32>
|
||||
ret <8 x i32> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpgtq %xmm
|
||||
; CHECK-NEXT: vpcmpgtq %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <4 x i64> @v4i64-cmp(<4 x i64> %i, <4 x i64> %j) nounwind readnone {
|
||||
define <4 x i64> @v4i64_cmp(<4 x i64> %i, <4 x i64> %j) nounwind {
|
||||
; CHECK-LABEL: v4i64_cmp:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpgtq %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp slt <4 x i64> %i, %j
|
||||
%x = sext <4 x i1> %bincmp to <4 x i64>
|
||||
ret <4 x i64> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpgtw %xmm
|
||||
; CHECK-NEXT: vpcmpgtw %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <16 x i16> @v16i16-cmp(<16 x i16> %i, <16 x i16> %j) nounwind readnone {
|
||||
define <16 x i16> @v16i16_cmp(<16 x i16> %i, <16 x i16> %j) nounwind {
|
||||
; CHECK-LABEL: v16i16_cmp:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vpcmpgtw %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpgtw %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp slt <16 x i16> %i, %j
|
||||
%x = sext <16 x i1> %bincmp to <16 x i16>
|
||||
ret <16 x i16> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpgtb %xmm
|
||||
; CHECK-NEXT: vpcmpgtb %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <32 x i8> @v32i8-cmp(<32 x i8> %i, <32 x i8> %j) nounwind readnone {
|
||||
define <32 x i8> @v32i8_cmp(<32 x i8> %i, <32 x i8> %j) nounwind {
|
||||
; CHECK-LABEL: v32i8_cmp:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vpcmpgtb %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpgtb %xmm0, %xmm1, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp slt <32 x i8> %i, %j
|
||||
%x = sext <32 x i1> %bincmp to <32 x i8>
|
||||
ret <32 x i8> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpeqd %xmm
|
||||
; CHECK-NEXT: vpcmpeqd %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <8 x i32> @int256-cmpeq(<8 x i32> %i, <8 x i32> %j) nounwind readnone {
|
||||
define <8 x i32> @int256_cmpeq(<8 x i32> %i, <8 x i32> %j) nounwind {
|
||||
; CHECK-LABEL: int256_cmpeq:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vpcmpeqd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp eq <8 x i32> %i, %j
|
||||
%x = sext <8 x i1> %bincmp to <8 x i32>
|
||||
ret <8 x i32> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpeqq %xmm
|
||||
; CHECK-NEXT: vpcmpeqq %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <4 x i64> @v4i64-cmpeq(<4 x i64> %i, <4 x i64> %j) nounwind readnone {
|
||||
define <4 x i64> @v4i64_cmpeq(<4 x i64> %i, <4 x i64> %j) nounwind {
|
||||
; CHECK-LABEL: v4i64_cmpeq:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vpcmpeqq %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp eq <4 x i64> %i, %j
|
||||
%x = sext <4 x i1> %bincmp to <4 x i64>
|
||||
ret <4 x i64> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpeqw %xmm
|
||||
; CHECK-NEXT: vpcmpeqw %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <16 x i16> @v16i16-cmpeq(<16 x i16> %i, <16 x i16> %j) nounwind readnone {
|
||||
define <16 x i16> @v16i16_cmpeq(<16 x i16> %i, <16 x i16> %j) nounwind {
|
||||
; CHECK-LABEL: v16i16_cmpeq:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vpcmpeqw %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp eq <16 x i16> %i, %j
|
||||
%x = sext <16 x i1> %bincmp to <16 x i16>
|
||||
ret <16 x i16> %x
|
||||
}
|
||||
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK: vextractf128 $1
|
||||
; CHECK-NEXT: vpcmpeqb %xmm
|
||||
; CHECK-NEXT: vpcmpeqb %xmm
|
||||
; CHECK-NEXT: vinsertf128 $1
|
||||
define <32 x i8> @v32i8-cmpeq(<32 x i8> %i, <32 x i8> %j) nounwind readnone {
|
||||
define <32 x i8> @v32i8_cmpeq(<32 x i8> %i, <32 x i8> %j) nounwind {
|
||||
; CHECK-LABEL: v32i8_cmpeq:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vpcmpeqb %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpcmpeqb %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%bincmp = icmp eq <32 x i8> %i, %j
|
||||
%x = sext <32 x i1> %bincmp to <32 x i8>
|
||||
ret <32 x i8> %x
|
||||
|
|
@ -132,17 +190,28 @@ define <32 x i8> @v32i8-cmpeq(<32 x i8> %i, <32 x i8> %j) nounwind readnone {
|
|||
|
||||
;; Scalar comparison
|
||||
|
||||
; CHECK: scalarcmpA
|
||||
; CHECK: vcmpeqsd
|
||||
define i32 @scalarcmpA() uwtable ssp {
|
||||
; CHECK-LABEL: scalarcmpA:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vxorpd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vcmpeqsd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vmovq %xmm0, %rax
|
||||
; CHECK-NEXT: andl $1, %eax
|
||||
; CHECK-NEXT: # kill: %EAX<def> %EAX<kill> %RAX<kill>
|
||||
; CHECK-NEXT: retq
|
||||
%cmp29 = fcmp oeq double undef, 0.000000e+00
|
||||
%res = zext i1 %cmp29 to i32
|
||||
ret i32 %res
|
||||
}
|
||||
|
||||
; CHECK: scalarcmpB
|
||||
; CHECK: vcmpeqss
|
||||
define i32 @scalarcmpB() uwtable ssp {
|
||||
; CHECK-LABEL: scalarcmpB:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vcmpeqss %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vmovd %xmm0, %eax
|
||||
; CHECK-NEXT: andl $1, %eax
|
||||
; CHECK-NEXT: retq
|
||||
%cmp29 = fcmp oeq float undef, 0.000000e+00
|
||||
%res = zext i1 %cmp29 to i32
|
||||
ret i32 %res
|
||||
|
|
|
|||
|
|
@ -1,13 +1,62 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
||||
; RUN: llc -O0 < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s -check-prefix=CHECK_O0
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,slow-unaligned-mem-32 | FileCheck %s
|
||||
; RUN: llc -O0 < %s -mtriple=x86_64-unknown-unknown -mattr=avx,slow-unaligned-mem-32 | FileCheck %s -check-prefix=CHECK_O0
|
||||
|
||||
; CHECK: vmovaps
|
||||
; CHECK: vmovaps
|
||||
; CHECK: vmovaps
|
||||
; CHECK: vmovaps
|
||||
; CHECK: vmovaps
|
||||
; CHECK: vmovaps
|
||||
define void @test_256_load(double* nocapture %d, float* nocapture %f, <4 x i64>* nocapture %i) nounwind uwtable ssp {
|
||||
define void @test_256_load(double* nocapture %d, float* nocapture %f, <4 x i64>* nocapture %i) nounwind {
|
||||
; CHECK-LABEL: test_256_load:
|
||||
; CHECK: # BB#0: # %entry
|
||||
; CHECK-NEXT: pushq %r15
|
||||
; CHECK-NEXT: pushq %r14
|
||||
; CHECK-NEXT: pushq %rbx
|
||||
; CHECK-NEXT: subq $96, %rsp
|
||||
; CHECK-NEXT: movq %rdx, %r14
|
||||
; CHECK-NEXT: movq %rsi, %r15
|
||||
; CHECK-NEXT: movq %rdi, %rbx
|
||||
; CHECK-NEXT: vmovaps (%rbx), %ymm0
|
||||
; CHECK-NEXT: vmovups %ymm0, {{[0-9]+}}(%rsp) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps (%r15), %ymm1
|
||||
; CHECK-NEXT: vmovups %ymm1, {{[0-9]+}}(%rsp) # 32-byte Spill
|
||||
; CHECK-NEXT: vmovaps (%r14), %ymm2
|
||||
; CHECK-NEXT: vmovups %ymm2, (%rsp) # 32-byte Spill
|
||||
; CHECK-NEXT: callq dummy
|
||||
; CHECK-NEXT: vmovups {{[0-9]+}}(%rsp), %ymm0 # 32-byte Reload
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%rbx)
|
||||
; CHECK-NEXT: vmovups {{[0-9]+}}(%rsp), %ymm0 # 32-byte Reload
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%r15)
|
||||
; CHECK-NEXT: vmovups (%rsp), %ymm0 # 32-byte Reload
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%r14)
|
||||
; CHECK-NEXT: addq $96, %rsp
|
||||
; CHECK-NEXT: popq %rbx
|
||||
; CHECK-NEXT: popq %r14
|
||||
; CHECK-NEXT: popq %r15
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: test_256_load:
|
||||
; CHECK_O0: # BB#0: # %entry
|
||||
; CHECK_O0-NEXT: subq $152, %rsp
|
||||
; CHECK_O0-NEXT: vmovapd (%rdi), %ymm0
|
||||
; CHECK_O0-NEXT: vmovaps (%rsi), %ymm1
|
||||
; CHECK_O0-NEXT: vmovdqa (%rdx), %ymm2
|
||||
; CHECK_O0-NEXT: vmovups %ymm0, {{[0-9]+}}(%rsp) # 32-byte Spill
|
||||
; CHECK_O0-NEXT: vmovups %ymm1, {{[0-9]+}}(%rsp) # 32-byte Spill
|
||||
; CHECK_O0-NEXT: vmovups %ymm2, {{[0-9]+}}(%rsp) # 32-byte Spill
|
||||
; CHECK_O0-NEXT: movq %rsi, {{[0-9]+}}(%rsp) # 8-byte Spill
|
||||
; CHECK_O0-NEXT: movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
|
||||
; CHECK_O0-NEXT: movq %rdx, {{[0-9]+}}(%rsp) # 8-byte Spill
|
||||
; CHECK_O0-NEXT: callq dummy
|
||||
; CHECK_O0-NEXT: movq {{[0-9]+}}(%rsp), %rdx # 8-byte Reload
|
||||
; CHECK_O0-NEXT: vmovups {{[0-9]+}}(%rsp), %ymm0 # 32-byte Reload
|
||||
; CHECK_O0-NEXT: vmovapd %ymm0, (%rdx)
|
||||
; CHECK_O0-NEXT: movq {{[0-9]+}}(%rsp), %rsi # 8-byte Reload
|
||||
; CHECK_O0-NEXT: vmovups {{[0-9]+}}(%rsp), %ymm1 # 32-byte Reload
|
||||
; CHECK_O0-NEXT: vmovaps %ymm1, (%rsi)
|
||||
; CHECK_O0-NEXT: movq {{[0-9]+}}(%rsp), %rdi # 8-byte Reload
|
||||
; CHECK_O0-NEXT: vmovups {{[0-9]+}}(%rsp), %ymm2 # 32-byte Reload
|
||||
; CHECK_O0-NEXT: vmovdqa %ymm2, (%rdi)
|
||||
; CHECK_O0-NEXT: addq $152, %rsp
|
||||
; CHECK_O0-NEXT: vzeroupper
|
||||
; CHECK_O0-NEXT: retq
|
||||
entry:
|
||||
%0 = bitcast double* %d to <4 x double>*
|
||||
%tmp1.i = load <4 x double>, <4 x double>* %0, align 32
|
||||
|
|
@ -27,62 +76,115 @@ declare void @dummy(<4 x double>, <8 x float>, <4 x i64>)
|
|||
;; The two tests below check that we must fold load + scalar_to_vector
|
||||
;; + ins_subvec+ zext into only a single vmovss or vmovsd or vinsertps from memory
|
||||
|
||||
; CHECK: mov00
|
||||
define <8 x float> @mov00(<8 x float> %v, float * %ptr) nounwind {
|
||||
; CHECK-LABEL: mov00:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: mov00:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM1
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm1
|
||||
; CHECK_O0-NEXT: vxorps %ymm2, %ymm2, %ymm2
|
||||
; CHECK_O0-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm2[1,2,3,4,5,6,7]
|
||||
; CHECK_O0-NEXT: retq
|
||||
%val = load float, float* %ptr
|
||||
; CHECK: vmovss (%
|
||||
%i0 = insertelement <8 x float> zeroinitializer, float %val, i32 0
|
||||
ret <8 x float> %i0
|
||||
; CHECK: ret
|
||||
}
|
||||
|
||||
; CHECK: mov01
|
||||
define <4 x double> @mov01(<4 x double> %v, double * %ptr) nounwind {
|
||||
; CHECK-LABEL: mov01:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: mov01:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM1
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm1
|
||||
; CHECK_O0-NEXT: vxorps %ymm2, %ymm2, %ymm2
|
||||
; CHECK_O0-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0],ymm2[1,2,3]
|
||||
; CHECK_O0-NEXT: retq
|
||||
%val = load double, double* %ptr
|
||||
; CHECK: vmovsd (%
|
||||
%i0 = insertelement <4 x double> zeroinitializer, double %val, i32 0
|
||||
ret <4 x double> %i0
|
||||
; CHECK: ret
|
||||
}
|
||||
|
||||
; CHECK: vmovaps %ymm
|
||||
define void @storev16i16(<16 x i16> %a) nounwind {
|
||||
; CHECK-LABEL: storev16i16:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%rax)
|
||||
;
|
||||
; CHECK_O0-LABEL: storev16i16:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: # implicit-def: %RAX
|
||||
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rax)
|
||||
store <16 x i16> %a, <16 x i16>* undef, align 32
|
||||
unreachable
|
||||
}
|
||||
|
||||
; CHECK: storev16i16_01
|
||||
; CHECK: vextractf128
|
||||
; CHECK: vmovups %xmm
|
||||
define void @storev16i16_01(<16 x i16> %a) nounwind {
|
||||
; CHECK-LABEL: storev16i16_01:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, (%rax)
|
||||
; CHECK-NEXT: vmovups %xmm0, (%rax)
|
||||
;
|
||||
; CHECK_O0-LABEL: storev16i16_01:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: # implicit-def: %RAX
|
||||
; CHECK_O0-NEXT: vmovdqu %ymm0, (%rax)
|
||||
store <16 x i16> %a, <16 x i16>* undef, align 4
|
||||
unreachable
|
||||
}
|
||||
|
||||
; CHECK: storev32i8
|
||||
; CHECK: vmovaps %ymm
|
||||
define void @storev32i8(<32 x i8> %a) nounwind {
|
||||
; CHECK-LABEL: storev32i8:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%rax)
|
||||
;
|
||||
; CHECK_O0-LABEL: storev32i8:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: # implicit-def: %RAX
|
||||
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rax)
|
||||
store <32 x i8> %a, <32 x i8>* undef, align 32
|
||||
unreachable
|
||||
}
|
||||
|
||||
; CHECK: storev32i8_01
|
||||
; CHECK: vextractf128
|
||||
; CHECK: vmovups %xmm
|
||||
define void @storev32i8_01(<32 x i8> %a) nounwind {
|
||||
; CHECK-LABEL: storev32i8_01:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, (%rax)
|
||||
; CHECK-NEXT: vmovups %xmm0, (%rax)
|
||||
;
|
||||
; CHECK_O0-LABEL: storev32i8_01:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: # implicit-def: %RAX
|
||||
; CHECK_O0-NEXT: vmovdqu %ymm0, (%rax)
|
||||
store <32 x i8> %a, <32 x i8>* undef, align 4
|
||||
unreachable
|
||||
}
|
||||
|
||||
; It is faster to make two saves, if the data is already in XMM registers. For
|
||||
; example, after making an integer operation.
|
||||
; CHECK: _double_save
|
||||
; CHECK-NOT: vinsertf128 $1
|
||||
; CHECK-NOT: vinsertf128 $0
|
||||
; CHECK: vmovaps %xmm
|
||||
; CHECK: vmovaps %xmm
|
||||
define void @double_save(<4 x i32> %A, <4 x i32> %B, <8 x i32>* %P) nounwind ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: double_save:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps %xmm1, 16(%rdi)
|
||||
; CHECK-NEXT: vmovaps %xmm0, (%rdi)
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: double_save:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM2
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
|
||||
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
|
||||
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
|
||||
; CHECK_O0-NEXT: vzeroupper
|
||||
; CHECK_O0-NEXT: retq
|
||||
%Z = shufflevector <4 x i32>%A, <4 x i32>%B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
store <8 x i32> %Z, <8 x i32>* %P, align 16
|
||||
ret void
|
||||
|
|
@ -90,60 +192,127 @@ entry:
|
|||
|
||||
declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x i32>, <8 x float>) nounwind
|
||||
|
||||
; CHECK_O0: _f_f
|
||||
; CHECK-O0: vmovss LCPI
|
||||
; CHECK-O0: vxorps %xmm
|
||||
; CHECK-O0: vmovss %xmm
|
||||
define void @f_f() nounwind {
|
||||
; CHECK-LABEL: f_f:
|
||||
; CHECK: # BB#0: # %allocas
|
||||
; CHECK-NEXT: xorl %eax, %eax
|
||||
; CHECK-NEXT: testb %al, %al
|
||||
; CHECK-NEXT: jne .LBB8_2
|
||||
; CHECK-NEXT: # BB#1: # %cif_mask_all
|
||||
; CHECK-NEXT: .LBB8_2: # %cif_mask_mixed
|
||||
; CHECK-NEXT: xorl %eax, %eax
|
||||
; CHECK-NEXT: testb %al, %al
|
||||
; CHECK-NEXT: jne .LBB8_4
|
||||
; CHECK-NEXT: # BB#3: # %cif_mixed_test_all
|
||||
; CHECK-NEXT: movl $-1, %eax
|
||||
; CHECK-NEXT: vmovd %eax, %xmm0
|
||||
; CHECK-NEXT: vmaskmovps %ymm0, %ymm0, (%rax)
|
||||
; CHECK-NEXT: .LBB8_4: # %cif_mixed_test_any_check
|
||||
;
|
||||
; CHECK_O0-LABEL: f_f:
|
||||
; CHECK_O0: # BB#0: # %allocas
|
||||
; CHECK_O0-NEXT: # implicit-def: %AL
|
||||
; CHECK_O0-NEXT: testb $1, %al
|
||||
; CHECK_O0-NEXT: jne .LBB8_1
|
||||
; CHECK_O0-NEXT: jmp .LBB8_2
|
||||
; CHECK_O0-NEXT: .LBB8_1: # %cif_mask_all
|
||||
; CHECK_O0-NEXT: .LBB8_2: # %cif_mask_mixed
|
||||
; CHECK_O0-NEXT: # implicit-def: %AL
|
||||
; CHECK_O0-NEXT: testb $1, %al
|
||||
; CHECK_O0-NEXT: jne .LBB8_3
|
||||
; CHECK_O0-NEXT: jmp .LBB8_4
|
||||
; CHECK_O0-NEXT: .LBB8_3: # %cif_mixed_test_all
|
||||
; CHECK_O0-NEXT: movl $-1, %eax
|
||||
; CHECK_O0-NEXT: vmovd %eax, %xmm0
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm1
|
||||
; CHECK_O0-NEXT: # implicit-def: %RCX
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM2
|
||||
; CHECK_O0-NEXT: vmaskmovps %ymm2, %ymm1, (%rcx)
|
||||
; CHECK_O0-NEXT: .LBB8_4: # %cif_mixed_test_any_check
|
||||
allocas:
|
||||
br i1 undef, label %cif_mask_all, label %cif_mask_mixed
|
||||
|
||||
cif_mask_all: ; preds = %allocas
|
||||
cif_mask_all:
|
||||
unreachable
|
||||
|
||||
cif_mask_mixed: ; preds = %allocas
|
||||
cif_mask_mixed:
|
||||
br i1 undef, label %cif_mixed_test_all, label %cif_mixed_test_any_check
|
||||
|
||||
cif_mixed_test_all: ; preds = %cif_mask_mixed
|
||||
cif_mixed_test_all:
|
||||
call void @llvm.x86.avx.maskstore.ps.256(i8* undef, <8 x i32> <i32 -1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, <8 x float> undef) nounwind
|
||||
unreachable
|
||||
|
||||
cif_mixed_test_any_check: ; preds = %cif_mask_mixed
|
||||
cif_mixed_test_any_check:
|
||||
unreachable
|
||||
}
|
||||
|
||||
; CHECK: add8i32
|
||||
; CHECK: vmovups
|
||||
; CHECK: vmovups
|
||||
; CHECK-NOT: vinsertf128
|
||||
; CHECK-NOT: vextractf128
|
||||
; CHECK: vmovups
|
||||
; CHECK: vmovups
|
||||
define void @add8i32(<8 x i32>* %ret, <8 x i32>* %bp) nounwind {
|
||||
; CHECK-LABEL: add8i32:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovups (%rsi), %xmm0
|
||||
; CHECK-NEXT: vmovups 16(%rsi), %xmm1
|
||||
; CHECK-NEXT: vmovups %xmm1, 16(%rdi)
|
||||
; CHECK-NEXT: vmovups %xmm0, (%rdi)
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: add8i32:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: vmovdqu (%rsi), %xmm0
|
||||
; CHECK_O0-NEXT: vmovdqu 16(%rsi), %xmm1
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM2
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
|
||||
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
|
||||
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
|
||||
; CHECK_O0-NEXT: vzeroupper
|
||||
; CHECK_O0-NEXT: retq
|
||||
%b = load <8 x i32>, <8 x i32>* %bp, align 1
|
||||
%x = add <8 x i32> zeroinitializer, %b
|
||||
store <8 x i32> %x, <8 x i32>* %ret, align 1
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: add4i64a64
|
||||
; CHECK: vmovaps ({{.*}}), %ymm{{.*}}
|
||||
; CHECK: vmovaps %ymm{{.*}}, ({{.*}})
|
||||
define void @add4i64a64(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
|
||||
; CHECK-LABEL: add4i64a64:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps (%rsi), %ymm0
|
||||
; CHECK-NEXT: vmovaps %ymm0, (%rdi)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: add4i64a64:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: vmovaps (%rsi), %ymm0
|
||||
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rdi)
|
||||
; CHECK_O0-NEXT: vzeroupper
|
||||
; CHECK_O0-NEXT: retq
|
||||
%b = load <4 x i64>, <4 x i64>* %bp, align 64
|
||||
%x = add <4 x i64> zeroinitializer, %b
|
||||
store <4 x i64> %x, <4 x i64>* %ret, align 64
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: add4i64a16
|
||||
; CHECK: vmovaps {{.*}}({{.*}}), %xmm{{.*}}
|
||||
; CHECK: vmovaps {{.*}}({{.*}}), %xmm{{.*}}
|
||||
; CHECK: vmovaps %xmm{{.*}}, {{.*}}({{.*}})
|
||||
; CHECK: vmovaps %xmm{{.*}}, {{.*}}({{.*}})
|
||||
define void @add4i64a16(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
|
||||
; CHECK-LABEL: add4i64a16:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps (%rsi), %xmm0
|
||||
; CHECK-NEXT: vmovaps 16(%rsi), %xmm1
|
||||
; CHECK-NEXT: vmovaps %xmm1, 16(%rdi)
|
||||
; CHECK-NEXT: vmovaps %xmm0, (%rdi)
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; CHECK_O0-LABEL: add4i64a16:
|
||||
; CHECK_O0: # BB#0:
|
||||
; CHECK_O0-NEXT: vmovdqa (%rsi), %xmm0
|
||||
; CHECK_O0-NEXT: vmovdqa 16(%rsi), %xmm1
|
||||
; CHECK_O0-NEXT: # implicit-def: %YMM2
|
||||
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
|
||||
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
|
||||
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
|
||||
; CHECK_O0-NEXT: vzeroupper
|
||||
; CHECK_O0-NEXT: retq
|
||||
%b = load <4 x i64>, <4 x i64>* %bp, align 16
|
||||
%x = add <4 x i64> zeroinitializer, %b
|
||||
store <4 x i64> %x, <4 x i64>* %ret, align 16
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,57 +1,84 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s
|
||||
|
||||
; CHECK: vunpckhps
|
||||
define <8 x float> @unpackhips(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhips:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhps {{.*#+}} ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
|
||||
ret <8 x float> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpckhpd
|
||||
define <4 x double> @unpackhipd(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhipd:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
||||
ret <4 x double> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklps
|
||||
define <8 x float> @unpacklops(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklops:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
|
||||
ret <8 x float> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklpd
|
||||
define <4 x double> @unpacklopd(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklopd:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
||||
ret <4 x double> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK-NOT: vunpcklps %ymm
|
||||
define <8 x float> @unpacklops-not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
define <8 x float> @unpacklops_not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
; CHECK-LABEL: unpacklops_not:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; CHECK-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
|
||||
ret <8 x float> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK-NOT: vunpcklpd %ymm
|
||||
define <4 x double> @unpacklopd-not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
define <4 x double> @unpacklopd_not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
; CHECK-LABEL: unpacklopd_not:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm0[1],xmm1[1]
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
|
||||
ret <4 x double> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK-NOT: vunpckhps %ymm
|
||||
define <8 x float> @unpackhips-not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
define <8 x float> @unpackhips_not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
||||
; CHECK-LABEL: unpackhips_not:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[u,2,u,3,u,4,u,5]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[2,u,3,u,4,u,5,u]
|
||||
; CHECK-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13>
|
||||
ret <8 x float> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK-NOT: vunpckhpd %ymm
|
||||
define <4 x double> @unpackhipd-not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
define <4 x double> @unpackhipd_not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
||||
; CHECK-LABEL: unpackhipd_not:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm1
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; CHECK-NEXT: vunpckhpd {{.*#+}} xmm2 = xmm0[1],xmm1[1]
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
|
||||
ret <4 x double> %shuffle.i
|
||||
}
|
||||
|
|
@ -60,102 +87,135 @@ entry:
|
|||
;;;; Unpack versions using the fp unit for int unpacking
|
||||
;;;;
|
||||
|
||||
; CHECK: vunpckhps
|
||||
define <8 x i32> @unpackhips1(<8 x i32> %src1, <8 x i32> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhips1:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhps {{.*#+}} ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x i32> %src1, <8 x i32> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
|
||||
ret <8 x i32> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpckhps (%
|
||||
define <8 x i32> @unpackhips2(<8 x i32>* %src1, <8 x i32>* %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhips2:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps (%rdi), %ymm0
|
||||
; CHECK-NEXT: vunpckhps {{.*#+}} ymm0 = ymm0[2],mem[2],ymm0[3],mem[3],ymm0[6],mem[6],ymm0[7],mem[7]
|
||||
; CHECK-NEXT: retq
|
||||
%a = load <8 x i32>, <8 x i32>* %src1
|
||||
%b = load <8 x i32>, <8 x i32>* %src2
|
||||
%shuffle.i = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
|
||||
ret <8 x i32> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpckhpd
|
||||
define <4 x i64> @unpackhipd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhipd1:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x i64> %src1, <4 x i64> %src2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
||||
ret <4 x i64> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpckhpd (%
|
||||
define <4 x i64> @unpackhipd2(<4 x i64>* %src1, <4 x i64>* %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhipd2:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovapd (%rdi), %ymm0
|
||||
; CHECK-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm0[1],mem[1],ymm0[3],mem[3]
|
||||
; CHECK-NEXT: retq
|
||||
%a = load <4 x i64>, <4 x i64>* %src1
|
||||
%b = load <4 x i64>, <4 x i64>* %src2
|
||||
%shuffle.i = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
||||
ret <4 x i64> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklps
|
||||
define <8 x i32> @unpacklops1(<8 x i32> %src1, <8 x i32> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklops1:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <8 x i32> %src1, <8 x i32> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
|
||||
ret <8 x i32> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklps (%
|
||||
define <8 x i32> @unpacklops2(<8 x i32>* %src1, <8 x i32>* %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklops2:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovaps (%rdi), %ymm0
|
||||
; CHECK-NEXT: vunpcklps {{.*#+}} ymm0 = ymm0[0],mem[0],ymm0[1],mem[1],ymm0[4],mem[4],ymm0[5],mem[5]
|
||||
; CHECK-NEXT: retq
|
||||
%a = load <8 x i32>, <8 x i32>* %src1
|
||||
%b = load <8 x i32>, <8 x i32>* %src2
|
||||
%shuffle.i = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
|
||||
ret <8 x i32> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklpd
|
||||
define <4 x i64> @unpacklopd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklopd1:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <4 x i64> %src1, <4 x i64> %src2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
||||
ret <4 x i64> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vunpcklpd (%
|
||||
define <4 x i64> @unpacklopd2(<4 x i64>* %src1, <4 x i64>* %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklopd2:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vmovapd (%rdi), %ymm0
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} ymm0 = ymm0[0],mem[0],ymm0[2],mem[2]
|
||||
; CHECK-NEXT: retq
|
||||
%a = load <4 x i64>, <4 x i64>* %src1
|
||||
%b = load <4 x i64>, <4 x i64>* %src2
|
||||
%shuffle.i = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
||||
ret <4 x i64> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vpunpckhwd
|
||||
; CHECK: vpunpckhwd
|
||||
; CHECK: vinsertf128
|
||||
define <16 x i16> @unpackhwd_undef(<16 x i16> %src1) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhwd_undef:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm0[4,4,5,5,6,6,7,7]
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; CHECK-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <16 x i16> %src1, <16 x i16> %src1, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
|
||||
ret <16 x i16> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vpunpcklwd
|
||||
; CHECK: vpunpcklwd
|
||||
; CHECK: vinsertf128
|
||||
define <16 x i16> @unpacklwd_undef(<16 x i16> %src1) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklwd_undef:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm0[0,0,1,1,2,2,3,3]
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; CHECK-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <16 x i16> %src1, <16 x i16> %src1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27>
|
||||
ret <16 x i16> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vpunpckhbw
|
||||
; CHECK: vpunpckhbw
|
||||
; CHECK: vinsertf128
|
||||
define <32 x i8> @unpackhbw_undef(<32 x i8> %src1, <32 x i8> %src2) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpackhbw_undef:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vpunpckhbw {{.*#+}} xmm1 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; CHECK-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <32 x i8> %src1, <32 x i8> %src1, <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
|
||||
ret <32 x i8> %shuffle.i
|
||||
}
|
||||
|
||||
; CHECK: vpunpcklbw
|
||||
; CHECK: vpunpcklbw
|
||||
; CHECK: vinsertf128
|
||||
define <32 x i8> @unpacklbw_undef(<32 x i8> %src1) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: unpacklbw_undef:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vpunpcklbw {{.*#+}} xmm1 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; CHECK-NEXT: vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle.i = shufflevector <32 x i8> %src1, <32 x i8> %src1, <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
|
||||
ret <32 x i8> %shuffle.i
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -1,30 +1,37 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s
|
||||
|
||||
; CHECK-LABEL: A:
|
||||
; CHECK-NOT: vunpck
|
||||
; CHECK: vinsertf128 $1
|
||||
define <8 x float> @A(<8 x float> %a) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: A:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 8, i32 8, i32 8, i32 8, i32 0, i32 1, i32 2, i32 3>
|
||||
ret <8 x float> %shuffle
|
||||
}
|
||||
|
||||
; CHECK-LABEL: B:
|
||||
; CHECK-NOT: vunpck
|
||||
; CHECK: vinsertf128 $1
|
||||
define <4 x double> @B(<4 x double> %a) nounwind uwtable readnone ssp {
|
||||
entry:
|
||||
; CHECK-LABEL: B:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%shuffle = shufflevector <4 x double> %a, <4 x double> undef, <4 x i32> <i32 4, i32 4, i32 0, i32 1>
|
||||
ret <4 x double> %shuffle
|
||||
}
|
||||
|
||||
declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone
|
||||
|
||||
declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone
|
||||
|
||||
; Just check that no crash happens
|
||||
; CHECK-LABEL: _insert_crash:
|
||||
define void @insert_crash() nounwind {
|
||||
; CHECK-LABEL: insert_crash:
|
||||
; CHECK: # BB#0: # %allocas
|
||||
; CHECK-NEXT: vxorpd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vminpd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vminsd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vcvtsd2ss %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,2,0]
|
||||
; CHECK-NEXT: vmovups %xmm0, (%rax)
|
||||
; CHECK-NEXT: retq
|
||||
allocas:
|
||||
%v1.i.i451 = shufflevector <4 x double> zeroinitializer, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
|
||||
%ret_0a.i.i.i452 = shufflevector <4 x double> %v1.i.i451, <4 x double> undef, <2 x i32> <i32 0, i32 1>
|
||||
|
|
@ -40,72 +47,87 @@ allocas:
|
|||
|
||||
;; DAG Combine must remove useless vinsertf128 instructions
|
||||
|
||||
; CHECK-LABEL: DAGCombineA:
|
||||
; CHECK-NOT: vinsertf128 $1
|
||||
define <4 x i32> @DAGCombineA(<4 x i32> %v1) nounwind readonly {
|
||||
%1 = shufflevector <4 x i32> %v1, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
%2 = shufflevector <8 x i32> %1, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
ret <4 x i32> %2
|
||||
; CHECK-LABEL: DAGCombineA:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: retq
|
||||
%t1 = shufflevector <4 x i32> %v1, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
%t2 = shufflevector <8 x i32> %t1, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
ret <4 x i32> %t2
|
||||
}
|
||||
|
||||
; CHECK-LABEL: DAGCombineB:
|
||||
; CHECK: vpaddd %xmm
|
||||
; CHECK-NOT: vinsertf128 $1
|
||||
; CHECK: vpaddd %xmm
|
||||
define <8 x i32> @DAGCombineB(<8 x i32> %v1, <8 x i32> %v2) nounwind readonly {
|
||||
%1 = add <8 x i32> %v1, %v2
|
||||
%2 = add <8 x i32> %1, %v1
|
||||
ret <8 x i32> %2
|
||||
; CHECK-LABEL: DAGCombineB:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpaddd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm1
|
||||
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%t1 = add <8 x i32> %v1, %v2
|
||||
%t2 = add <8 x i32> %t1, %v1
|
||||
ret <8 x i32> %t2
|
||||
}
|
||||
|
||||
; CHECK-LABEL: insert_undef_pd:
|
||||
define <4 x double> @insert_undef_pd(<4 x double> %a0, <2 x double> %a1) {
|
||||
; CHECK: vmovaps %ymm1, %ymm0
|
||||
; CHECK-LABEL: insert_undef_pd:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: # kill: %XMM1<def> %XMM1<kill> %YMM1<def>
|
||||
; CHECK-NEXT: vmovaps %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> undef, <2 x double> %a1, i8 0)
|
||||
ret <4 x double> %res
|
||||
}
|
||||
declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
|
||||
|
||||
|
||||
; CHECK-LABEL: insert_undef_ps:
|
||||
define <8 x float> @insert_undef_ps(<8 x float> %a0, <4 x float> %a1) {
|
||||
; CHECK: vmovaps %ymm1, %ymm0
|
||||
; CHECK-LABEL: insert_undef_ps:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: # kill: %XMM1<def> %XMM1<kill> %YMM1<def>
|
||||
; CHECK-NEXT: vmovaps %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %a1, i8 0)
|
||||
ret <8 x float> %res
|
||||
}
|
||||
declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
|
||||
|
||||
|
||||
; CHECK-LABEL: insert_undef_si:
|
||||
define <8 x i32> @insert_undef_si(<8 x i32> %a0, <4 x i32> %a1) {
|
||||
; CHECK: vmovaps %ymm1, %ymm0
|
||||
; CHECK-LABEL: insert_undef_si:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: # kill: %XMM1<def> %XMM1<kill> %YMM1<def>
|
||||
; CHECK-NEXT: vmovaps %ymm1, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> undef, <4 x i32> %a1, i8 0)
|
||||
ret <8 x i32> %res
|
||||
}
|
||||
declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
|
||||
|
||||
; rdar://10643481
|
||||
; CHECK-LABEL: vinsertf128_combine:
|
||||
define <8 x float> @vinsertf128_combine(float* nocapture %f) nounwind uwtable readonly ssp {
|
||||
; CHECK-NOT: vmovaps
|
||||
; CHECK: vinsertf128
|
||||
entry:
|
||||
; CHECK-LABEL: vinsertf128_combine:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vinsertf128 $1, 16(%rdi), %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%add.ptr = getelementptr inbounds float, float* %f, i64 4
|
||||
%0 = bitcast float* %add.ptr to <4 x float>*
|
||||
%1 = load <4 x float>, <4 x float>* %0, align 16
|
||||
%2 = tail call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %1, i8 1)
|
||||
ret <8 x float> %2
|
||||
%t0 = bitcast float* %add.ptr to <4 x float>*
|
||||
%t1 = load <4 x float>, <4 x float>* %t0, align 16
|
||||
%t2 = tail call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %t1, i8 1)
|
||||
ret <8 x float> %t2
|
||||
}
|
||||
|
||||
; rdar://11076953
|
||||
; CHECK-LABEL: vinsertf128_ucombine:
|
||||
define <8 x float> @vinsertf128_ucombine(float* nocapture %f) nounwind uwtable readonly ssp {
|
||||
; CHECK-NOT: vmovups
|
||||
; CHECK: vinsertf128
|
||||
entry:
|
||||
; CHECK-LABEL: vinsertf128_ucombine:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: vinsertf128 $1, 16(%rdi), %ymm0, %ymm0
|
||||
; CHECK-NEXT: retq
|
||||
%add.ptr = getelementptr inbounds float, float* %f, i64 4
|
||||
%0 = bitcast float* %add.ptr to <4 x float>*
|
||||
%1 = load <4 x float>, <4 x float>* %0, align 8
|
||||
%2 = tail call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %1, i8 1)
|
||||
ret <8 x float> %2
|
||||
%t0 = bitcast float* %add.ptr to <4 x float>*
|
||||
%t1 = load <4 x float>, <4 x float>* %t0, align 8
|
||||
%t2 = tail call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> undef, <4 x float> %t1, i8 1)
|
||||
ret <8 x float> %t2
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue