maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LICM/lcssa-ssa-promoter.ll

78 lines
2.3 KiB
LLVM
Raw Normal View History

[LPM] Apply a really big hammer to fix PR18688 by recursively reforming LCSSA when we promote to SSA registers inside of LICM. Currently, this is actually necessary. The promotion logic in LICM uses SSAUpdater which doesn't understand how to place LCSSA PHI nodes. Teaching it to do so would be a very significant undertaking. It may be worthwhile and I've left a FIXME about this in the code as well as starting a thread on llvmdev to try to figure out the right long-term solution. For now, the PR needs to be fixed. Short of using the promition SSAUpdater to place both the LCSSA PHI nodes and the promoted PHI nodes, I don't see a cleaner or cheaper way of achieving this. Fortunately, LCSSA is relatively lazy and sparse -- it should only update instructions which need it. We can also skip the recursive variant when we don't promote to SSA values. llvm-svn: 200612
2014-02-01 21:35:14 +08:00
; RUN: opt -S -basicaa -licm < %s | FileCheck %s
[LICM] Report successful hoist/sink/promotion Differential Revision: https://reviews.llvm.org/D27938 llvm-svn: 291646
2017-01-11 12:39:35 +08:00
; RUN: opt -aa-pipeline=basic-aa -passes='require<aa>,require<targetir>,require<scalar-evolution>,require<opt-remark-emit>,loop(licm)' -S %s| FileCheck %s
[LPM] Apply a really big hammer to fix PR18688 by recursively reforming LCSSA when we promote to SSA registers inside of LICM. Currently, this is actually necessary. The promotion logic in LICM uses SSAUpdater which doesn't understand how to place LCSSA PHI nodes. Teaching it to do so would be a very significant undertaking. It may be worthwhile and I've left a FIXME about this in the code as well as starting a thread on llvmdev to try to figure out the right long-term solution. For now, the PR needs to be fixed. Short of using the promition SSAUpdater to place both the LCSSA PHI nodes and the promoted PHI nodes, I don't see a cleaner or cheaper way of achieving this. Fortunately, LCSSA is relatively lazy and sparse -- it should only update instructions which need it. We can also skip the recursive variant when we don't promote to SSA values. llvm-svn: 200612
2014-02-01 21:35:14 +08:00
;
; Manually validate LCSSA form is preserved even after SSAUpdater is used to
; promote things in the loop bodies.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@x = common global i32 0, align 4
@y = common global i32 0, align 4
define void @PR18688() {
; CHECK-LABEL: @PR18688(
entry:
br i1 undef, label %return, label %outer.preheader
outer.preheader:
br label %outer.header
; CHECK: outer.preheader:
; CHECK: br label %outer.header
outer.header:
store i32 0, i32* @x, align 4
br i1 undef, label %outer.latch, label %inner.preheader
; CHECK: outer.header:
; CHECK-NEXT: br i1 undef, label %outer.latch, label %inner.preheader
inner.preheader:
br label %inner.header
; CHECK: inner.preheader:
; CHECK-NEXT: br label %inner.header
inner.header:
br i1 undef, label %inner.body.rhs, label %inner.latch
; CHECK: inner.header:
; CHECK-NEXT: %[[PHI0:[^,]+]] = phi i32 [ %{{[^,]+}}, %inner.latch ], [ 0, %inner.preheader ]
; CHECK-NEXT: br i1 undef, label %inner.body.rhs, label %inner.latch
inner.body.rhs:
store i32 0, i32* @x, align 4
br label %inner.latch
; CHECK: inner.body.rhs:
; CHECK-NEXT: br label %inner.latch
inner.latch:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%y_val = load i32, i32* @y, align 4
[LPM] Apply a really big hammer to fix PR18688 by recursively reforming LCSSA when we promote to SSA registers inside of LICM. Currently, this is actually necessary. The promotion logic in LICM uses SSAUpdater which doesn't understand how to place LCSSA PHI nodes. Teaching it to do so would be a very significant undertaking. It may be worthwhile and I've left a FIXME about this in the code as well as starting a thread on llvmdev to try to figure out the right long-term solution. For now, the PR needs to be fixed. Short of using the promition SSAUpdater to place both the LCSSA PHI nodes and the promoted PHI nodes, I don't see a cleaner or cheaper way of achieving this. Fortunately, LCSSA is relatively lazy and sparse -- it should only update instructions which need it. We can also skip the recursive variant when we don't promote to SSA values. llvm-svn: 200612
2014-02-01 21:35:14 +08:00
%icmp = icmp eq i32 %y_val, 0
br i1 %icmp, label %inner.exit, label %inner.header
; CHECK: inner.latch:
; CHECK-NEXT: %[[PHI1:[^,]+]] = phi i32 [ 0, %inner.body.rhs ], [ %[[PHI0]], %inner.header ]
; CHECK-NEXT: br i1 %{{[^,]+}}, label %inner.exit, label %inner.header
inner.exit:
br label %outer.latch
; CHECK: inner.exit:
; CHECK-NEXT: %[[INNER_LCSSA:[^,]+]] = phi i32 [ %[[PHI1]], %inner.latch ]
; CHECK-NEXT: br label %outer.latch
outer.latch:
br i1 undef, label %outer.exit, label %outer.header
; CHECK: outer.latch:
; CHECK-NEXT: %[[PHI2:[^,]+]] = phi i32 [ %[[INNER_LCSSA]], %inner.exit ], [ 0, %outer.header ]
; CHECK-NEXT: br i1 {{.*}}, label %outer.exit, label %outer.header
outer.exit:
br label %return
; CHECK: outer.exit:
; CHECK-NEXT: %[[OUTER_LCSSA:[^,]+]] = phi i32 [ %[[PHI2]], %outer.latch ]
; CHECK-NEXT: store i32 %[[OUTER_LCSSA]]
; CHECK-NEXT: br label %return
return:
ret void
}