1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/CodeGen/X86/musttail.ll
Nirav Dave 6655b5e078 [DAGCombiner] If a TokenFactor would be merged into its user, consider the user later.
Summary:
A number of optimizations are inhibited by single-use TokenFactors not
being merged into the TokenFactor using it. This makes we consider if
we can do the merge immediately.

Most tests changes here are due to the change in visitation causing
minor reorderings and associated reassociation of paired memory
operations.

CodeGen tests with non-reordering changes:

  X86/aligned-variadic.ll -- memory-based add folded into stored leaq
  value.

  X86/constant-combiners.ll -- Optimizes out overlap between stores.

  X86/pr40631_deadstore_elision -- folds constant byte store into
  preceding quad word constant store.

Reviewers: RKSimon, craig.topper, spatel, efriedma, courbet

Reviewed By: courbet

Subscribers: dylanmckay, sdardis, nemanjai, jvesely, nhaehnle, javed.absar, eraman, hiraditya, kbarton, jrtc27, atanasyan, jsji, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59260

llvm-svn: 356068
2019-03-13 17:07:09 +00:00

91 lines
2.3 KiB
LLVM

; RUN: llc -mtriple=i686-- < %s | FileCheck %s
; RUN: llc -mtriple=i686-- -O0 < %s | FileCheck %s
; RUN: llc -mtriple=i686-- -disable-tail-calls < %s | FileCheck %s
declare void @t1_callee(i8*)
define void @t1(i32* %a) {
; CHECK-LABEL: t1:
; CHECK: jmp {{_?}}t1_callee
%b = bitcast i32* %a to i8*
musttail call void @t1_callee(i8* %b)
ret void
}
declare i8* @t2_callee()
define i32* @t2() {
; CHECK-LABEL: t2:
; CHECK: jmp {{_?}}t2_callee
%v = musttail call i8* @t2_callee()
%w = bitcast i8* %v to i32*
ret i32* %w
}
; Complex frame layout: stack realignment with dynamic alloca.
define void @t3(i32 %n) alignstack(32) nounwind {
entry:
; CHECK: t3:
; CHECK: pushl %ebp
; CHECK: pushl %esi
; CHECK: andl $-32, %esp
; CHECK: movl %esp, %esi
; CHECK: popl %esi
; CHECK: popl %ebp
; CHECK-NEXT: jmp {{_?}}t3_callee
%a = alloca i8, i32 %n
call void @capture(i8* %a)
musttail call void @t3_callee(i32 %n) nounwind
ret void
}
declare void @capture(i8*)
declare void @t3_callee(i32)
; Test that we actually copy in and out stack arguments that aren't forwarded
; without modification.
define i32 @t4({}* %fn, i32 %n, i32 %r) {
; CHECK-LABEL: t4:
; CHECK: incl %[[r:.*]]
; CHECK: decl %[[n:.*]]
; CHECK-DAG: movl %[[r]], {{[0-9]+}}(%esp)
; CHECK-DAG: movl %[[n]], {{[0-9]+}}(%esp)
; CHECK: jmpl *%{{.*}}
entry:
%r1 = add i32 %r, 1
%n1 = sub i32 %n, 1
%fn_cast = bitcast {}* %fn to i32 ({}*, i32, i32)*
%r2 = musttail call i32 %fn_cast({}* %fn, i32 %n1, i32 %r1)
ret i32 %r2
}
; Combine the complex stack frame with the parameter modification.
define i32 @t5({}* %fn, i32 %n, i32 %r) alignstack(32) {
; CHECK-LABEL: t5:
; CHECK: pushl %ebp
; CHECK: movl %esp, %ebp
; CHECK: pushl %esi
; Align the stack.
; CHECK: andl $-32, %esp
; CHECK: movl %esp, %esi
; Modify the args.
; CHECK: incl %[[r:.*]]
; CHECK: decl %[[n:.*]]
; Store them through ebp, since that's the only stable arg pointer.
; CHECK-DAG: movl %[[r]], {{[0-9]+}}(%ebp)
; CHECK-DAG: movl %[[n]], {{[0-9]+}}(%ebp)
; Epilogue.
; CHECK: leal {{[-0-9]+}}(%ebp), %esp
; CHECK: popl %esi
; CHECK: popl %ebp
; CHECK: jmpl *%{{.*}}
entry:
%a = alloca i8, i32 %n
call void @capture(i8* %a)
%r1 = add i32 %r, 1
%n1 = sub i32 %n, 1
%fn_cast = bitcast {}* %fn to i32 ({}*, i32, i32)*
%r2 = musttail call i32 %fn_cast({}* %fn, i32 %n1, i32 %r1)
ret i32 %r2
}