diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2019-05-04 12:46:32 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2019-05-04 12:46:32 +0000 |
| commit | 5ab41a7a0552690e9f7ca657bee1d0507baaddfb (patch) | |
| tree | 27306d4c26bb538f05725642b079697fb77cb068 /llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll | |
| parent | 55dc751ef7ad3df0b7870fa0d3851d5b0225213b (diff) | |
| download | bcm5719-llvm-5ab41a7a0552690e9f7ca657bee1d0507baaddfb.tar.gz bcm5719-llvm-5ab41a7a0552690e9f7ca657bee1d0507baaddfb.zip | |
[CodeGenPrepare] limit overflow intrinsic matching to a single basic block (2nd try)
This is a subset of the original commit from rL359879
which was reverted because it could crash when using the 'RemovedInstructions'
structure that enables delayed deletion of dead instructions. The motivating
compile-time win does not require that change though. We should get most of
that win from this change alone.
Using/updating a dominator tree to match math overflow patterns may be very
expensive in compile-time (because of the way CGP uses a DT), so just handle
the single-block case.
See post-commit thread for rL354298 for more details:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20190422/646276.html
Differential Revision: https://reviews.llvm.org/D61075
llvm-svn: 359969
Diffstat (limited to 'llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll')
| -rw-r--r-- | llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll | 9 |
1 files changed, 4 insertions, 5 deletions
diff --git a/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll b/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll index dc638425355..05389bfe8d0 100644 --- a/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll +++ b/llvm/test/Transforms/CodeGenPrepare/X86/optimizeSelect-DT.ll @@ -14,11 +14,10 @@ define i1 @PR41004(i32 %x, i32 %y, i32 %t1) { ; CHECK-NEXT: br label [[SELECT_END]] ; CHECK: select.end: ; CHECK-NEXT: [[MUL:%.*]] = phi i32 [ [[REM]], [[SELECT_TRUE_SINK]] ], [ 0, [[ENTRY:%.*]] ] -; CHECK-NEXT: [[TMP0:%.*]] = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 [[T1:%.*]], i32 1) -; CHECK-NEXT: [[MATH:%.*]] = extractvalue { i32, i1 } [[TMP0]], 0 -; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[TMP0]], 1 -; CHECK-NEXT: [[ADD:%.*]] = add i32 [[MATH]], [[MUL]] -; CHECK-NEXT: ret i1 [[OV]] +; CHECK-NEXT: [[NEG:%.*]] = add i32 [[T1:%.*]], -1 +; CHECK-NEXT: [[ADD:%.*]] = add i32 [[NEG]], [[MUL]] +; CHECK-NEXT: [[TOBOOL:%.*]] = icmp eq i32 [[T1]], 0 +; CHECK-NEXT: ret i1 [[TOBOOL]] ; entry: %rem = srem i32 %x, 2 |
