mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-01 08:23:21 +01:00
14be19cf1e
getelementptr-seteq.ll into:
define i1 @test(i64 %X, %S* %P) {
%C = icmp eq i64 %X, -1 ; <i1> [#uses=1]
ret i1 %C
}
instead of:
define i1 @test(i64 %X, %S* %P) {
%A.idx.mask = and i64 %X, 4611686018427387903 ; <i64> [#uses=1]
%C = icmp eq i64 %A.idx.mask, 4611686018427387903 ; <i1> [#uses=1]
ret i1 %C
}
And fixes the second half of PR2235. This speeds up the insertion sort
case by 45%, from 1.12s to 0.77s. In practice, this will significantly
speed up for loops structured like:
for (double *P = Base + N; P != Base; --P)
...
Which happens frequently for C++ iterators.
llvm-svn: 50079
14 lines
353 B
LLVM
14 lines
353 B
LLVM
; Test folding of constantexpr geps into normal geps.
|
|
; RUN: llvm-as < %s | opt -instcombine | llvm-dis | grep {icmp eq i64 %X, -1}
|
|
; PR2235
|
|
|
|
%S = type { i32, [ 100 x i32] }
|
|
|
|
define i1 @test(i64 %X, %S* %P) {
|
|
%A = getelementptr %S* %P, i32 0, i32 1, i64 %X
|
|
%B = getelementptr %S* %P, i32 0, i32 0
|
|
%C = icmp eq i32* %A, %B
|
|
ret i1 %C
|
|
}
|
|
|