mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 04:22:57 +02:00
54e8749794
This pass implements whole program optimization of virtual calls in cases where we know (via bitset information) that the list of callees is fixed. This includes the following: - Single implementation devirtualization: if a virtual call has a single possible callee, replace all calls with a direct call to that callee. - Virtual constant propagation: if the virtual function's return type is an integer <=64 bits and all possible callees are readnone, for each class and each list of constant arguments: evaluate the function, store the return value alongside the virtual table, and rewrite each virtual call as a load from the virtual table. - Uniform return value optimization: if the conditions for virtual constant propagation hold and each function returns the same constant value, replace each virtual call with that constant. - Unique return value optimization for i1 return values: if the conditions for virtual constant propagation hold and a single vtable's function returns 0, or a single vtable's function returns 1, replace each virtual call with a comparison of the vptr against that vtable's address. Differential Revision: http://reviews.llvm.org/D16795 llvm-svn: 260312
38 lines
1.0 KiB
LLVM
38 lines
1.0 KiB
LLVM
; RUN: opt -S -wholeprogramdevirt %s | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
@vt1 = global [1 x i8*] [i8* bitcast (i32 ()* @vf1 to i8*)]
|
|
@vt2 = global [1 x i8*] [i8* bitcast (i32 ()* @vf2 to i8*)]
|
|
|
|
define i32 @vf1() readnone {
|
|
ret i32 1
|
|
}
|
|
|
|
define i32 @vf2() readnone {
|
|
ret i32 2
|
|
}
|
|
|
|
; CHECK: define i32 @call
|
|
define i32 @call(i8* %obj) {
|
|
%vtableptr = bitcast i8* %obj to [1 x i8*]**
|
|
%vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr
|
|
%vtablei8 = bitcast [1 x i8*]* %vtable to i8*
|
|
%p = call i1 @llvm.bitset.test(i8* %vtablei8, metadata !"bitset")
|
|
call void @llvm.assume(i1 %p)
|
|
%fptrptr = getelementptr [1 x i8*], [1 x i8*]* %vtable, i32 0, i32 0
|
|
%fptr = load i8*, i8** %fptrptr
|
|
%fptr_casted = bitcast i8* %fptr to i32 ()*
|
|
; CHECK: call i32 %
|
|
%result = call i32 %fptr_casted()
|
|
ret i32 %result
|
|
}
|
|
|
|
declare i1 @llvm.bitset.test(i8*, metadata)
|
|
declare void @llvm.assume(i1)
|
|
|
|
!0 = !{!"bitset", [1 x i8*]* @vt1, i32 0}
|
|
!1 = !{!"bitset", [1 x i8*]* @vt2, i32 0}
|
|
!llvm.bitsets = !{!0}
|