aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/CodeGen/CommandFlags.cpp
diff options
context:
space:
mode:
authorSnehasish Kumar <snehasishk@google.com>2020-08-05 15:34:31 -0700
committerSnehasish Kumar <snehasishk@google.com>2020-08-28 11:10:14 -0700
commit94faadaca4e1704f674d2e9d4a1d25643b9ca52c (patch)
tree2838a645b079079538e845291ea8185cb6266bbc /llvm/lib/CodeGen/CommandFlags.cpp
parent064981f0cee47b140e94ca7df6c24102514af6f0 (diff)
downloadllvm-94faadaca4e1704f674d2e9d4a1d25643b9ca52c.zip
llvm-94faadaca4e1704f674d2e9d4a1d25643b9ca52c.tar.gz
llvm-94faadaca4e1704f674d2e9d4a1d25643b9ca52c.tar.bz2
[llvm][CodeGen] Machine Function Splitter
We introduce a codegen optimization pass which splits functions into hot and cold parts. This pass leverages the basic block sections feature recently introduced in LLVM from the Propeller project. The pass targets functions with profile coverage, identifies cold blocks and moves them to a separate section. The linker groups all cold blocks across functions together, decreasing fragmentation and improving icache and itlb utilization. We evaluated the Machine Function Splitter pass on clang bootstrap and SPECInt 2017. For clang bootstrap we observe a mean 2.33% runtime improvement with a ~32% reduction in itlb and stlb misses. Additionally, L1 icache misses reduced by 9.5% while L2 instruction misses reduced by 20%. For SPECInt we report the change in IntRate the C/C++ benchmarks. All benchmarks apart from mcf and x264 improve, on average by 0.6% with the max for deepsjeng at 1.6%. Benchmark % Change 500.perlbench_r 0.78 502.gcc_r 0.82 505.mcf_r -0.30 520.omnetpp_r 0.18 523.xalancbmk_r 0.37 525.x264_r -0.46 531.deepsjeng_r 1.61 541.leela_r 0.83 557.xz_r 0.15 Differential Revision: https://reviews.llvm.org/D85368
Diffstat (limited to 'llvm/lib/CodeGen/CommandFlags.cpp')
-rw-r--r--llvm/lib/CodeGen/CommandFlags.cpp9
1 files changed, 9 insertions, 0 deletions
diff --git a/llvm/lib/CodeGen/CommandFlags.cpp b/llvm/lib/CodeGen/CommandFlags.cpp
index a47608c..0a7c7a9 100644
--- a/llvm/lib/CodeGen/CommandFlags.cpp
+++ b/llvm/lib/CodeGen/CommandFlags.cpp
@@ -84,6 +84,7 @@ CGOPT(DebuggerKind, DebuggerTuningOpt)
CGOPT(bool, EnableStackSizeSection)
CGOPT(bool, EnableAddrsig)
CGOPT(bool, EmitCallSiteInfo)
+CGOPT(bool, EnableMachineFunctionSplitter)
CGOPT(bool, EnableDebugEntryValues)
CGOPT(bool, ValueTrackingVariableLocations)
CGOPT(bool, ForceDwarfFrameSection)
@@ -407,6 +408,13 @@ codegen::RegisterCodeGenFlags::RegisterCodeGenFlags() {
cl::init(false));
CGBINDOPT(ValueTrackingVariableLocations);
+ static cl::opt<bool> EnableMachineFunctionSplitter(
+ "split-machine-functions",
+ cl::desc("Split out cold basic blocks from machine functions based on "
+ "profile information"),
+ cl::init(false));
+ CGBINDOPT(EnableMachineFunctionSplitter);
+
static cl::opt<bool> ForceDwarfFrameSection(
"force-dwarf-frame-section",
cl::desc("Always emit a debug frame section."), cl::init(false));
@@ -479,6 +487,7 @@ TargetOptions codegen::InitTargetOptionsFromCodeGenFlags() {
Options.ExplicitEmulatedTLS = EmulatedTLSView->getNumOccurrences() > 0;
Options.ExceptionModel = getExceptionModel();
Options.EmitStackSizeSection = getEnableStackSizeSection();
+ Options.EnableMachineFunctionSplitter = getEnableMachineFunctionSplitter();
Options.EmitAddrsig = getEnableAddrsig();
Options.EmitCallSiteInfo = getEmitCallSiteInfo();
Options.EnableDebugEntryValues = getEnableDebugEntryValues();