forked from OSchip/llvm-project
[NFC][X86] Fix check prefixes and autogenerate fold-pcmpeqd-2.ll test
Being affected by (sub %x, c) -> (add %x, (sub 0, c)) patch in an uncertain way. llvm-svn: 361483
This commit is contained in:
Roman Lebedev
parent
28afd8dc71
commit
32d976bac1
|
|
@ -1,5 +1,6 @@
|
|||
; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=yonah -regalloc=basic | FileCheck %s
|
||||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -regalloc=basic | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=i386-apple-darwin -mcpu=yonah -regalloc=basic | FileCheck %s --check-prefixes=ALL,X32
|
||||
; RUN: llc < %s -mtriple=x86_64-apple-darwin -regalloc=basic | FileCheck %s --check-prefixes=ALL,X64
|
||||
|
||||
; This testcase should need to spill the -1 value on both x86-32 and x86-64,
|
||||
; so it shouldn't use pcmpeqd to materialize an all-ones vector; it
|
||||
|
|
@ -7,18 +8,177 @@
|
|||
;
|
||||
; RAGreedy defeats the test by splitting live ranges.
|
||||
|
||||
; Constant pool all-ones vector:
|
||||
; CHECK: .space 16,255
|
||||
|
||||
; No pcmpeqd instructions, everybody uses the constant pool.
|
||||
; CHECK-LABEL: program_1:
|
||||
; CHECK-NOT: pcmpeqd
|
||||
; There should be no pcmpeqd instructions, everybody should the constant pool.
|
||||
|
||||
%struct.__ImageExecInfo = type <{ <4 x i32>, <4 x float>, <2 x i64>, i8*, i8*, i8*, i32, i32, i32, i32, i32 }>
|
||||
%struct._cl_image_format_t = type <{ i32, i32, i32 }>
|
||||
%struct._image2d_t = type <{ i8*, %struct._cl_image_format_t, i32, i32, i32, i32, i32, i32 }>
|
||||
|
||||
define void @program_1(%struct._image2d_t* %dest, %struct._image2d_t* %t0, <4 x float> %p0, <4 x float> %p1, <4 x float> %p4, <4 x float> %p5, <4 x float> %p6) nounwind {
|
||||
; X32-LABEL: program_1:
|
||||
; X32: ## %bb.0: ## %entry
|
||||
; X32-NEXT: cmpl $0, 0
|
||||
; X32-NEXT: jle LBB0_2
|
||||
; X32-NEXT: ## %bb.1: ## %forcond
|
||||
; X32-NEXT: cmpl $0, 0
|
||||
; X32-NEXT: jg LBB0_3
|
||||
; X32-NEXT: LBB0_2: ## %ifthen
|
||||
; X32-NEXT: retl
|
||||
; X32-NEXT: LBB0_3: ## %forbody
|
||||
; X32-NEXT: pushl %esi
|
||||
; X32-NEXT: subl $88, %esp
|
||||
; X32-NEXT: movaps {{.*#+}} xmm1 = [1.28E+2,1.28E+2,1.28E+2,1.28E+2]
|
||||
; X32-NEXT: minps LCPI0_3, %xmm1
|
||||
; X32-NEXT: cvttps2dq %xmm1, %xmm0
|
||||
; X32-NEXT: cvtdq2ps %xmm0, %xmm0
|
||||
; X32-NEXT: subps %xmm0, %xmm1
|
||||
; X32-NEXT: movaps %xmm1, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: mulps LCPI0_3, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: addps LCPI0_1, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: mulps %xmm1, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: addps LCPI0_2, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movdqa {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: psubd LCPI0_4, %xmm0
|
||||
; X32-NEXT: movdqa %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: mulps LCPI0_3, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: xorps %xmm0, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: mulps %xmm0, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: mulps LCPI0_3, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: xorps %xmm0, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: cmpunordps %xmm0, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: minps LCPI0_3, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: xorps %xmm0, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[0-9]+}}(%esp)
|
||||
; X32-NEXT: movl $0, (%esp)
|
||||
; X32-NEXT: xorl %esi, %esi
|
||||
; X32-NEXT: xorps %xmm3, %xmm3
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: movdqa {{[-0-9]+}}(%e{{[sb]}}p), %xmm1 ## 16-byte Reload
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm2 ## 16-byte Reload
|
||||
; X32-NEXT: calll *%esi
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: minps LCPI0_3, %xmm0
|
||||
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: pxor %xmm1, %xmm1
|
||||
; X32-NEXT: psubd {{[-0-9]+}}(%e{{[sb]}}p), %xmm1 ## 16-byte Folded Reload
|
||||
; X32-NEXT: movdqa {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: psubd LCPI0_4, %xmm0
|
||||
; X32-NEXT: movdqa %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: movdqa {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: por %xmm1, %xmm0
|
||||
; X32-NEXT: movdqa %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
|
||||
; X32-NEXT: pxor %xmm0, %xmm0
|
||||
; X32-NEXT: movdqa %xmm0, {{[0-9]+}}(%esp)
|
||||
; X32-NEXT: movl $0, (%esp)
|
||||
; X32-NEXT: xorps %xmm3, %xmm3
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm1 ## 16-byte Reload
|
||||
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm2 ## 16-byte Reload
|
||||
; X32-NEXT: calll *%esi
|
||||
; X32-NEXT: ud2
|
||||
;
|
||||
; X64-LABEL: program_1:
|
||||
; X64: ## %bb.0: ## %entry
|
||||
; X64-NEXT: cmpl $0, 0
|
||||
; X64-NEXT: jle LBB0_2
|
||||
; X64-NEXT: ## %bb.1: ## %forcond
|
||||
; X64-NEXT: cmpl $0, 0
|
||||
; X64-NEXT: jg LBB0_3
|
||||
; X64-NEXT: LBB0_2: ## %ifthen
|
||||
; X64-NEXT: retq
|
||||
; X64-NEXT: LBB0_3: ## %forbody
|
||||
; X64-NEXT: pushq %rbx
|
||||
; X64-NEXT: subq $64, %rsp
|
||||
; X64-NEXT: xorps %xmm0, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps {{.*#+}} xmm1 = [1.28E+2,1.28E+2,1.28E+2,1.28E+2]
|
||||
; X64-NEXT: minps {{.*}}(%rip), %xmm1
|
||||
; X64-NEXT: cvttps2dq %xmm1, %xmm0
|
||||
; X64-NEXT: cvtdq2ps %xmm0, %xmm0
|
||||
; X64-NEXT: subps %xmm0, %xmm1
|
||||
; X64-NEXT: movaps %xmm1, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: mulps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: addps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: mulps %xmm1, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: addps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movdqa (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: psubd {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movdqa %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: mulps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: xorps %xmm0, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: mulps %xmm0, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: mulps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: xorps %xmm0, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: cmpunordps %xmm0, %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: minps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: xorl %ebx, %ebx
|
||||
; X64-NEXT: xorps %xmm3, %xmm3
|
||||
; X64-NEXT: xorps %xmm4, %xmm4
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 ## 16-byte Reload
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 ## 16-byte Reload
|
||||
; X64-NEXT: xorl %edi, %edi
|
||||
; X64-NEXT: callq *%rbx
|
||||
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: minps {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
|
||||
; X64-NEXT: movdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: psubd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Folded Reload
|
||||
; X64-NEXT: movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: psubd {{.*}}(%rip), %xmm0
|
||||
; X64-NEXT: movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: orps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Folded Reload
|
||||
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
|
||||
; X64-NEXT: xorps %xmm3, %xmm3
|
||||
; X64-NEXT: xorps %xmm4, %xmm4
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
|
||||
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 ## 16-byte Reload
|
||||
; X64-NEXT: movaps (%rsp), %xmm2 ## 16-byte Reload
|
||||
; X64-NEXT: xorl %edi, %edi
|
||||
; X64-NEXT: callq *%rbx
|
||||
; X64-NEXT: ud2
|
||||
entry:
|
||||
%tmp3.i = load i32, i32* null ; <i32> [#uses=1]
|
||||
%cmp = icmp slt i32 0, %tmp3.i ; <i1> [#uses=1]
|
||||
|
|
|
|||
Loading…
Reference in New Issue