[PATCH] D21405: [PGO] IRPGO pre-cleanup pass changes
Rong Xu via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 15 13:31:50 PDT 2016
xur created this revision.
xur added reviewers: silvas, vsk, davidxl, mehdi_amini, tejohnson.
xur added a subscriber: llvm-commits.
Herald added a subscriber: mehdi_amini.
This patch adds a selected set of cleanup passes including a pre-inline pass before LLVM IR PGO instrumentation. The inline is only intended to apply those obvious/trivial ones before instrumentation so that much less instrumentation is needed to get better profiling information. This will drastically improve the instrumented code performance for large C++ applications. Another benefit was the context sensitive counts that can potentially improve the PGO optimization.
This is previously discussed here:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089425.html
Here I recollected some the data to show the impact using the followings:
(1) spec2006 C and C++ programs
(2) some Google internal benchmarks (which are of different size of C++ applications).
(3) instrumented LLVM compiler
The metrics collected are:
(1) instrumented code runtime performance.
https://docs.google.com/document/d/1DCP7KPjtitHMotX2KgTO8PADd9zjLzPJgSXZ8egd6Mk/edit?usp=sharing
(2) program text size (i.e. sum of sections (having address and name) sizes minus
writable section sizes.)
https://docs.google.com/document/d/1ItOetOEc1vTpU54EBjQK4O0LfulFIv3gs9XXnmzwqdo/edit?usp=sharing
(3) program binary size
https://docs.google.com/document/d/1nmiR6He0cxMFqMzWE-X7FdhL5jSzdS9h7WLxDrfmSxQ/edit?usp=sharing
http://reviews.llvm.org/D21405
Files:
lib/Transforms/IPO/PassManagerBuilder.cpp
test/Transforms/PGOProfile/preinline.ll
Index: test/Transforms/PGOProfile/preinline.ll
===================================================================
--- /dev/null
+++ test/Transforms/PGOProfile/preinline.ll
@@ -0,0 +1,20 @@
+; RUN: opt < %s -O2 -profile-generate=default.profraw -S | FileCheck %s --check-prefix=GEN
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @foo(i32 %i) {
+entry:
+; GEN: %pgocount = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_foo
+; GEN-NOT: %pgocount.i = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc__stdin__bar
+ %call = call i32 @bar()
+ %add = add nsw i32 %i, %call
+ ret i32 %add
+}
+
+define internal i32 @bar() {
+entry:
+ %call = call i32 (...) @bar1()
+ ret i32 %call
+}
+
+declare i32 @bar1(...)
Index: lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- lib/Transforms/IPO/PassManagerBuilder.cpp
+++ lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -118,6 +118,14 @@
"enable-loop-versioning-licm", cl::init(false), cl::Hidden,
cl::desc("Enable the experimental Loop Versioning LICM pass"));
+static cl::opt<bool>
+ RunPreInliner("preinline", cl::init(true), cl::Hidden, cl::ZeroOrMore,
+ cl::desc("Enable pre-instrumentation inliner"));
+
+static cl::opt<bool>
+ DisablePreInliner("disable-preinline", cl::init(false), cl::Hidden,
+ cl::desc("Disable pre-instrumentation inliner"));
+
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
SizeLevel = 0;
@@ -209,8 +217,32 @@
FPM.add(createLowerExpectIntrinsicPass());
}
+// Get the inline threshold for pre-instrumentation inline.
+static int computePreInlineThresholdFromOptLevels(unsigned OptLevel,
+ unsigned SizeOptLevel) {
+ if (SizeOptLevel == 1) // -Os
+ return 75;
+ if (SizeOptLevel == 2) // -Oz
+ return 25;
+ return 75;
+}
+
// Do PGO instrumentation generation or use pass as the option specified.
void PassManagerBuilder::addPGOInstrPasses(legacy::PassManagerBase &MPM) {
+ if (PGOInstrGen.empty() && PGOInstrUse.empty())
+ return;
+ if (OptLevel > 0 && RunPreInliner && !DisablePreInliner) {
+ // Create preinline pass.
+ MPM.add(createFunctionInliningPass(
+ computePreInlineThresholdFromOptLevels(OptLevel, SizeLevel)));
+ MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
+ MPM.add(createJumpThreadingPass()); // Thread jumps.
+ MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
+ MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
+ MPM.add(createInstructionCombiningPass()); // Combine silly seq's
+ MPM.add(createGVNPass(DisableGVNLoadPRE)); // Remove redundancies
+ addExtensionsToPM(EP_Peephole, MPM);
+ }
if (!PGOInstrGen.empty()) {
MPM.add(createPGOInstrumentationGenLegacyPass());
// Add the profile lowering pass.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D21405.60891.patch
Type: text/x-patch
Size: 3039 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160615/838e8e8c/attachment.bin>
More information about the llvm-commits
mailing list