mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 12:43:36 +01:00
edf99b5e43
When possible (e.g. internal linkage), strip preallocated attribute off parameters/arguments. This requires removing the "preallocated" operand bundle from the call site, replacing @llvm.call.preallocated.arg() with an alloca and a bitcast to i8*, and removing the @llvm.call.preallocated.setup(). Since @llvm.call.preallocated.arg() can be called multiple times with the same arg index, we create an alloca per arg index. We add a @llvm.stacksave() where the @llvm.call.preallocated.setup() was and a @llvm.stackrestore() after the preallocated call to prevent the stack from blowing up. This is valid because the argument would normally not exist on the stack after the call before the transformation. This does not currently handle all possible preallocated calls. We will need to figure out where to put @llvm.stackrestore() in the cases where there is no obvious place to put it, for example conditional preallocated calls, invokes. This sort of transformation may need to be moved to somewhere more accessible to accomodate similar transformations (like inlining) in the future. Reviewers: efriedma, hans Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D80951
89 lines
3.5 KiB
LLVM
89 lines
3.5 KiB
LLVM
; RUN: opt < %s -globalopt -S | FileCheck %s
|
|
|
|
declare token @llvm.call.preallocated.setup(i32)
|
|
declare i8* @llvm.call.preallocated.arg(token, i32)
|
|
declare i32 @__CxxFrameHandler3(...)
|
|
|
|
; Don't touch functions with any musttail calls
|
|
define internal i32 @preallocated_musttail(i32* preallocated(i32) %p) {
|
|
; CHECK-LABEL: define internal i32 @preallocated_musttail(i32* preallocated(i32) %p)
|
|
%rv = load i32, i32* %p
|
|
ret i32 %rv
|
|
}
|
|
|
|
define i32 @call_preallocated_musttail(i32* preallocated(i32) %a) {
|
|
%r = musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
|
|
ret i32 %r
|
|
}
|
|
; CHECK-LABEL: define i32 @call_preallocated_musttail(i32* preallocated(i32) %a)
|
|
; CHECK: musttail call i32 @preallocated_musttail(i32* preallocated(i32) %a)
|
|
|
|
define i32 @call_preallocated_musttail_without_musttail() {
|
|
%c = call token @llvm.call.preallocated.setup(i32 1)
|
|
%N = call i8* @llvm.call.preallocated.arg(token %c, i32 0) preallocated(i32)
|
|
%n = bitcast i8* %N to i32*
|
|
%r = call i32 @preallocated_musttail(i32* preallocated(i32) %n) ["preallocated"(token %c)]
|
|
ret i32 %r
|
|
}
|
|
; CHECK-LABEL: define i32 @call_preallocated_musttail_without_musttail()
|
|
; CHECK: call i32 @preallocated_musttail(i32* preallocated(i32) %n)
|
|
|
|
; Check that only one alloca per preallocated arg
|
|
define internal i32 @preallocated(i32* preallocated(i32) %a) {
|
|
; CHECK-LABEL: define internal fastcc i32 @preallocated(i32* %a)
|
|
%rv = load i32, i32* %a
|
|
ret i32 %rv
|
|
}
|
|
|
|
declare void @foo(i8*)
|
|
|
|
define i32 @call_preallocated_multiple_args() {
|
|
; CHECK-LABEL: define i32 @call_preallocated_multiple_args()
|
|
; CHECK-NEXT: [[SS:%[0-9a-zA-Z_]+]] = call i8* @llvm.stacksave()
|
|
; CHECK-NEXT: [[ARG0:%[0-9a-zA-Z_]+]] = alloca i32
|
|
; CHECK-NEXT: [[ARG1:%[0-9a-zA-Z_]+]] = bitcast i32* [[ARG0]] to i8*
|
|
; CHECK-NEXT: call void @foo(i8* [[ARG1]])
|
|
; CHECK-NEXT: call void @foo(i8* [[ARG1]])
|
|
; CHECK-NEXT: call void @foo(i8* [[ARG1]])
|
|
; CHECK-NEXT: [[ARG2:%[0-9a-zA-Z_]+]] = bitcast i8* [[ARG1]] to i32*
|
|
; CHECK-NEXT: call fastcc i32 @preallocated(i32* [[ARG2]])
|
|
; CHECK-NEXT: call void @llvm.stackrestore(i8* [[SS]])
|
|
; CHECK-NEXT: ret
|
|
%c = call token @llvm.call.preallocated.setup(i32 1)
|
|
%a1 = call i8* @llvm.call.preallocated.arg(token %c, i32 0) preallocated(i32)
|
|
call void @foo(i8* %a1)
|
|
%a2 = call i8* @llvm.call.preallocated.arg(token %c, i32 0) preallocated(i32)
|
|
call void @foo(i8* %a2)
|
|
%a3 = call i8* @llvm.call.preallocated.arg(token %c, i32 0) preallocated(i32)
|
|
call void @foo(i8* %a3)
|
|
%b = bitcast i8* %a3 to i32*
|
|
%r = call i32 @preallocated(i32* preallocated(i32) %b) ["preallocated"(token %c)]
|
|
ret i32 %r
|
|
}
|
|
|
|
; Don't touch functions with any invokes
|
|
define internal i32 @preallocated_invoke(i32* preallocated(i32) %p) {
|
|
; CHECK-LABEL: define internal i32 @preallocated_invoke(i32* preallocated(i32) %p)
|
|
%rv = load i32, i32* %p
|
|
ret i32 %rv
|
|
}
|
|
|
|
define i32 @call_preallocated_invoke() personality i8* bitcast (i32 (...)* @__CxxFrameHandler3 to i8*) {
|
|
%c = call token @llvm.call.preallocated.setup(i32 1)
|
|
%a = call i8* @llvm.call.preallocated.arg(token %c, i32 0) preallocated(i32)
|
|
%b = bitcast i8* %a to i32*
|
|
%r = invoke i32 @preallocated_invoke(i32* preallocated(i32) %b) ["preallocated"(token %c)]
|
|
to label %conta unwind label %contb
|
|
conta:
|
|
ret i32 %r
|
|
contb:
|
|
%s = catchswitch within none [label %catch] unwind to caller
|
|
catch:
|
|
%p = catchpad within %s []
|
|
catchret from %p to label %cont
|
|
cont:
|
|
ret i32 42
|
|
}
|
|
; CHECK-LABEL: define i32 @call_preallocated_invoke()
|
|
; CHECK: invoke i32 @preallocated_invoke(i32* preallocated(i32) %b)
|