From 8bf75ed41c95e50b62a4f8b03552d51ad6e86c7a Mon Sep 17 00:00:00 2001 From: Hal Finkel Date: Sat, 9 Jun 2012 03:14:50 +0000 Subject: [PATCH] Enable tail merging on PPC. Tail merging had been disabled on PPC because it would disturb bundling decisions made during pre-RA scheduling on the 970 cores. Now, however, all bundling decisions are made during post-RA scheduling, and tail merging is generally beneficial (the average test-suite speedup is insignificantly positive). Largest test-suite speedups: MultiSource/Benchmarks/mediabench/gsm/toast/toast - 30% MultiSource/Benchmarks/BitBench/uuencode/uuencode - 23% SingleSource/Benchmarks/Shootout-C++/ary - 21% SingleSource/Benchmarks/Stanford/Queens - 17% Largest slowdowns: MultiSource/Benchmarks/MiBench/security-sha/security-sha - 24% MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 22% MultiSource/Applications/JM/ldecod/ldecod - 14% MultiSource/Benchmarks/mediabench/g721/g721encode/encode - 9% This is improved by using full (instead of just critical) anti-dependency breaking, but doing so still causes miscompiles and so cannot yet be enabled by default. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158259 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/Target/PowerPC/PPCTargetMachine.cpp | 8 +------- test/CodeGen/PowerPC/2007-05-22-tailmerge-3.ll | 10 +++++----- 2 files changed, 6 insertions(+), 12 deletions(-) diff --git a/lib/Target/PowerPC/PPCTargetMachine.cpp b/lib/Target/PowerPC/PPCTargetMachine.cpp index b9c703e708d..d7a808855bb 100644 --- a/lib/Target/PowerPC/PPCTargetMachine.cpp +++ b/lib/Target/PowerPC/PPCTargetMachine.cpp @@ -93,13 +93,7 @@ public: } // namespace TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) { - TargetPassConfig *PassConfig = new PPCPassConfig(this, PM); - - // Override this for PowerPC. Tail merging happily breaks up instruction issue - // groups, which typically degrades performance. - PassConfig->setEnableTailMerge(false); - - return PassConfig; + return new PPCPassConfig(this, PM); } bool PPCPassConfig::addPreRegAlloc() { diff --git a/test/CodeGen/PowerPC/2007-05-22-tailmerge-3.ll b/test/CodeGen/PowerPC/2007-05-22-tailmerge-3.ll index c1415510d05..382ba1f6a82 100644 --- a/test/CodeGen/PowerPC/2007-05-22-tailmerge-3.ll +++ b/test/CodeGen/PowerPC/2007-05-22-tailmerge-3.ll @@ -1,8 +1,8 @@ -; RUN: llc < %s -march=ppc32 | grep bl.*baz | count 2 -; RUN: llc < %s -march=ppc32 | grep bl.*quux | count 2 -; RUN: llc < %s -march=ppc32 -enable-tail-merge | grep bl.*baz | count 1 -; RUN: llc < %s -march=ppc32 -enable-tail-merge=1 | grep bl.*quux | count 1 -; Check that tail merging is not the default on ppc, and that -enable-tail-merge works. +; RUN: llc < %s -march=ppc32 -enable-tail-merge=0 | grep bl.*baz | count 2 +; RUN: llc < %s -march=ppc32 -enable-tail-merge=0 | grep bl.*quux | count 2 +; RUN: llc < %s -march=ppc32 | grep bl.*baz | count 1 +; RUN: llc < %s -march=ppc32 | grep bl.*quux | count 1 +; Check that tail merging is the default on ppc, and that -enable-tail-merge works. ; ModuleID = 'tail.c' target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64"