maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[CGP] Allow cycles during Phi traversal in OptimizaMemoryInst 

Allowing cycles in Phi traversal increases the scope of optimize memory instruction
in case we are in loop.

The added test shows an example of enabling optimization inside a loop.

Reviewers: loladiro, spatel, efriedma
Reviewed By: efriedma
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D35294

llvm-svn: 308419
This commit is contained in:
Serguei Katkov 2017-07-19 04:49:17 +00:00
parent bb83558f00
commit 4ea855ebe5
2 changed files with 45 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/lib/CodeGen/CodeGenPrepare.cpp
View File

@ -4278,11 +4278,17 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
Value *V = worklist.back();
worklist.pop_back();
// Break use-def graph loops.
if (!Visited.insert(V).second) {
AddrModeFound = false;
break;
}
// We allow traversing cyclic Phi nodes.
// In case of success after this loop we ensure that traversing through
// Phi nodes ends up with all cases to compute address of the form
// BaseGV + Base + Scale * Index + Offset
// where Scale and Offset are constans and BaseGV, Base and Index
// are exactly the same Values in all cases.
// It means that BaseGV, Scale and Offset dominate our memory instruction
// and have the same value as they had in address computation represented
// as Phi. So we can safely sink address computation to memory instruction.
if (!Visited.insert(V).second)
continue;
// For a PHI node, push all of its incoming values.
if (PHINode *P = dyn_cast<PHINode>(V)) {

35
llvm/test/Transforms/CodeGenPrepare/X86/sink-addrmode.ll
View File

@ -194,7 +194,6 @@ rare.2:
br label %fallthrough
}
declare void @slowpath(i32, i32*)
; Make sure we don't end up in an infinite loop after we fail to sink.
@ -218,3 +217,37 @@ load.i145:
pl_loop.i.i122:
br label %pl_loop.i.i122
}
; Make sure we can sink address computation even
; if there is a cycle in phi nodes.
define void @test9(i1 %cond, i64* %base) {
; CHECK-LABEL: @test9
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br label %header
header:
%iv = phi i32 [0, %entry], [%iv.inc, %backedge]
%casted.loop = phi i32* [%casted, %entry], [%casted.merged, %backedge]
br i1 %cond, label %if.then, label %backedge
if.then:
call void @foo(i32 %iv)
%addr.1 = getelementptr inbounds i64, i64* %base, i64 5
%casted.1 = bitcast i64* %addr.1 to i32*
br label %backedge
backedge:
; CHECK-LABEL: backedge:
; CHECK: getelementptr i8, {{.+}} 40
%casted.merged = phi i32* [%casted.loop, %header], [%casted.1, %if.then]
%v = load i32, i32* %casted.merged, align 4
call void @foo(i32 %v)
%iv.inc = add i32 %iv, 1
%cmp = icmp slt i32 %iv.inc, 1000
br i1 %cmp, label %header, label %exit
exit:
ret void
}