This patch fixes pr39098.
For the attached test case, CombineZExtLogicopShiftLoad can optimize it to
t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
t58: i64 = srl t57, Constant:i8<1>
t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64
But later visitANDLike transforms it to
t25: i64 = Constant<1099511627775>
t35: i64 = Constant<0>
t0: ch = EntryToken
t57: i64,ch = load<(load 4 from `i40* undef`, align 8), zext from i32> t0, undef:i64, undef:i64
t61: i32 = truncate t57
t63: i32 = srl t61, Constant:i8<1>
t64: i32 = and t63, Constant:i32<524287>
t65: i64 = zero_extend t64
t58: i64 = srl t57, Constant:i8<1>
t60: i64 = and t58, Constant:i64<524287>
t29: ch = store<(store 5 into `i40* undef`, align 8), trunc to i40> t57:1, t60, undef:i64, undef:i64
And it triggers CombineZExtLogicopShiftLoad again, causes a dead loop.
Both forms should generate same instructions, CombineZExtLogicopShiftLoad generated IR looks cleaner. But it looks more difficult to prevent visitANDLike to do the transform, so I prevent CombineZExtLogicopShiftLoad to do the transform if the ZExt is free.
Differential Revision: https://reviews.llvm.org/D57491
llvm-svn: 352792
21 lines
597 B
LLVM
21 lines
597 B
LLVM
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
|
|
|
|
define dso_local void @test_cancel2(i40* %p1, i40* %p2) {
|
|
; CHECK: # %entry
|
|
; CHECK-NEXT: movl (%rdi), %eax
|
|
; CHECK-NEXT: shrl %eax
|
|
; CHECK-NEXT: andl $524287, %eax
|
|
; CHECK-NEXT: movl %eax, (%rsi)
|
|
; CHECK-NEXT: movb $0, 4(%rsi)
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%0 = load i40, i40* %p1, align 8
|
|
%shl414 = shl i40 %0, 19
|
|
%unsclear415 = and i40 %shl414, 549755813887
|
|
%shr416 = lshr i40 %unsclear415, 20
|
|
%unsclear417 = and i40 %shr416, 549755813887
|
|
store i40 %unsclear417, i40* %p2, align 8
|
|
ret void
|
|
}
|
|
|