diff options
| author | Dan Gohman <gohman@apple.com> | 2009-01-06 01:19:04 +0000 |
|---|---|---|
| committer | Dan Gohman <gohman@apple.com> | 2009-01-06 01:19:04 +0000 |
| commit | 79c35169123c4bafaaf8e6d379d23131c361d08a (patch) | |
| tree | fc391a80840761d69aa58dc47180d468da48fcb2 | |
| parent | 04a207972683416dc4328851b7ce2d20b530cf1c (diff) | |
| download | bcm5719-llvm-79c35169123c4bafaaf8e6d379d23131c361d08a.tar.gz bcm5719-llvm-79c35169123c4bafaaf8e6d379d23131c361d08a.zip | |
Use a latency value of 0 for the artificial edges inserted by
AddPseudoTwoAddrDeps. This lets the scheduling infrastructure
avoid recalculating node heights. In very large testcases this
was a major bottleneck. Thanks to Roman Levenstein for finding
this!
As a side effect, fold-pcmpeqd-0.ll is now scheduled better
and it no longer requires spilling on x86-32.
llvm-svn: 61778
| -rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp | 2 | ||||
| -rw-r--r-- | llvm/test/CodeGen/X86/fold-pcmpeqd-0.ll | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp b/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp index 436056c6445..676a69bd633 100644 --- a/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/ScheduleDAGRRList.cpp @@ -1252,7 +1252,7 @@ void RegReductionPriorityQueue<SF>::AddPseudoTwoAddrDeps() { !scheduleDAG->IsReachable(SuccSU, SU)) { DOUT << "Adding a pseudo-two-addr edge from SU # " << SU->NodeNum << " to SU #" << SuccSU->NodeNum << "\n"; - scheduleDAG->AddPred(SU, SDep(SuccSU, SDep::Order, /*Latency=*/1, + scheduleDAG->AddPred(SU, SDep(SuccSU, SDep::Order, /*Latency=*/0, /*Reg=*/0, /*isMustAlias=*/false, /*isArtificial=*/true)); } diff --git a/llvm/test/CodeGen/X86/fold-pcmpeqd-0.ll b/llvm/test/CodeGen/X86/fold-pcmpeqd-0.ll index a529f91598f..152c12215dc 100644 --- a/llvm/test/CodeGen/X86/fold-pcmpeqd-0.ll +++ b/llvm/test/CodeGen/X86/fold-pcmpeqd-0.ll @@ -1,4 +1,4 @@ -; RUN: llvm-as < %s | llc -mtriple=i386-apple-darwin | not grep pcmpeqd +; RUN: llvm-as < %s | llc -mtriple=i386-apple-darwin | grep pcmpeqd | count 1 ; RUN: llvm-as < %s | llc -mtriple=x86_64-apple-darwin | grep pcmpeqd | count 1 ; This testcase shouldn't need to spill the -1 value, |
