diff --git a/bolt/README.md b/bolt/README.md --- a/bolt/README.md +++ b/bolt/README.md @@ -180,7 +180,7 @@ BOLT. Assuming your environment is setup to include the right path, execute `llvm-bolt`: ``` -$ llvm-bolt -o .bolt -data=perf.fdata -reorder-blocks=cache+ -reorder-functions=hfsort -split-functions=2 -split-all-cold -split-eh -dyno-stats +$ llvm-bolt -o .bolt -data=perf.fdata -reorder-blocks=ext-tsp -reorder-functions=hfsort -split-functions=2 -split-all-cold -split-eh -dyno-stats ``` If you do need an updated debug info, then add `-update-debug-sections` option diff --git a/bolt/docs/OptimizingClang.md b/bolt/docs/OptimizingClang.md --- a/bolt/docs/OptimizingClang.md +++ b/bolt/docs/OptimizingClang.md @@ -64,7 +64,7 @@ the generated profile: ```bash $ llvm-bolt $CPATH/clang-7 -o $CPATH/clang-7.bolt -b clang-7.yaml \ - -reorder-blocks=cache+ -reorder-functions=hfsort+ -split-functions=3 \ + -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions=3 \ -split-all-cold -dyno-stats -icf=1 -use-gnu-stack ``` The output will look similar to the one below: diff --git a/bolt/test/X86/bug-reorder-bb-jrcxz.s b/bolt/test/X86/bug-reorder-bb-jrcxz.s --- a/bolt/test/X86/bug-reorder-bb-jrcxz.s +++ b/bolt/test/X86/bug-reorder-bb-jrcxz.s @@ -15,7 +15,7 @@ # RUN: %clang %cflags %t.o -falign-labels -march=native -o %t.exe -Wl,-q # RUN: llvm-bolt %t.exe -o %t.bolted -data %t.fdata \ -# RUN: -reorder-blocks=cache+ -reorder-functions=hfsort \ +# RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort \ # RUN: -split-functions=2 -split-all-cold -split-eh -dyno-stats \ # RUN: -print-finalized 2>&1 | FileCheck %s diff --git a/bolt/test/X86/loop-inversion-pass.s b/bolt/test/X86/loop-inversion-pass.s --- a/bolt/test/X86/loop-inversion-pass.s +++ b/bolt/test/X86/loop-inversion-pass.s @@ -6,9 +6,9 @@ # RUN: link_fdata %s %t.o %t.fdata2 "FDATA2" # RUN: link_fdata %s %t.o %t.fdata3 "FDATA3" # RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=cache+ -print-finalized \ +# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=ext-tsp -print-finalized \ # RUN: -loop-inversion-opt -o %t.out | FileCheck %s -# RUN: llvm-bolt %t.exe -data %t.fdata2 -reorder-blocks=cache+ -print-finalized \ +# RUN: llvm-bolt %t.exe -data %t.fdata2 -reorder-blocks=ext-tsp -print-finalized \ # RUN: -loop-inversion-opt -o %t.out2 | FileCheck --check-prefix="CHECK2" %s # RUN: llvm-bolt %t.exe -data %t.fdata3 -reorder-blocks=none -print-finalized \ # RUN: -loop-inversion-opt -o %t.out3 | FileCheck --check-prefix="CHECK3" %s diff --git a/bolt/test/X86/tail-duplication-pass.s b/bolt/test/X86/tail-duplication-pass.s --- a/bolt/test/X86/tail-duplication-pass.s +++ b/bolt/test/X86/tail-duplication-pass.s @@ -4,7 +4,7 @@ # RUN: %s -o %t.o # RUN: link_fdata %s %t.o %t.fdata # RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=cache+ -print-finalized \ +# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=ext-tsp -print-finalized \ # RUN: -tail-duplication -tail-duplication-minimum-offset 1 -o %t.out | FileCheck %s # FDATA: 1 main 2 1 main #.BB2# 0 10 diff --git a/bolt/test/runtime/X86/exceptions-instrumentation.test b/bolt/test/runtime/X86/exceptions-instrumentation.test --- a/bolt/test/runtime/X86/exceptions-instrumentation.test +++ b/bolt/test/runtime/X86/exceptions-instrumentation.test @@ -8,7 +8,7 @@ RUN: %t.exc arg1 arg2 arg3 RUN: llvm-bolt %t_exc_split -o %t.exc.bolted -data %t.fdata \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ -split-functions=3 \ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions=3 \ RUN: -split-eh=1 | FileCheck --check-prefix=EXCEPTIONS %s EXCEPTIONS-NOT: invalid (possibly stale) profile diff --git a/bolt/test/runtime/X86/fix-branches-jrcxz.s b/bolt/test/runtime/X86/fix-branches-jrcxz.s --- a/bolt/test/runtime/X86/fix-branches-jrcxz.s +++ b/bolt/test/runtime/X86/fix-branches-jrcxz.s @@ -7,7 +7,7 @@ # RUN: link_fdata %s %t.o %t.fdata # RUN: llvm-strip --strip-unneeded %t.o # RUN: %clang %cflags -no-pie %t.o -o %t.exe -Wl,-q -# RUN: llvm-bolt %t.exe -relocs=1 -reorder-blocks=cache+ -print-finalized \ +# RUN: llvm-bolt %t.exe -relocs=1 -reorder-blocks=ext-tsp -print-finalized \ # RUN: -o %t.out -data %t.fdata | FileCheck %s # RUN: %t.out 1 2 3 diff --git a/bolt/test/runtime/X86/instrumentation-dup-jts.s b/bolt/test/runtime/X86/instrumentation-dup-jts.s --- a/bolt/test/runtime/X86/instrumentation-dup-jts.s +++ b/bolt/test/runtime/X86/instrumentation-dup-jts.s @@ -56,7 +56,7 @@ # Test that the instrumented data makes sense # RUN: llvm-bolt %t.exe -o %t.bolted -data %t.fdata \ -# RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ \ +# RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ \ # RUN: -print-only=interp -print-finalized | FileCheck %s # RUN: %t.bolted 120 diff --git a/bolt/test/runtime/X86/instrumentation-ind-calls.s b/bolt/test/runtime/X86/instrumentation-ind-calls.s --- a/bolt/test/runtime/X86/instrumentation-ind-calls.s +++ b/bolt/test/runtime/X86/instrumentation-ind-calls.s @@ -20,7 +20,7 @@ # Test that the instrumented data makes sense # RUN: llvm-bolt %t.exe -o %t.bolted -data %t.fdata \ -# RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ \ +# RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ \ # RUN: -print-only=main -print-finalized | FileCheck %s # RUN: %t.bolted arg1 arg2 diff --git a/bolt/test/runtime/X86/instrumentation-indirect.c b/bolt/test/runtime/X86/instrumentation-indirect.c --- a/bolt/test/runtime/X86/instrumentation-indirect.c +++ b/bolt/test/runtime/X86/instrumentation-indirect.c @@ -56,7 +56,7 @@ # Test that the instrumented data makes sense RUN: llvm-bolt %t.exe -o %t.bolted -data %t.fdata \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ \ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ \ RUN: -print-only=interp -print-finalized RUN: %t.bolted | FileCheck %s -check-prefix=CHECK-OUTPUT diff --git a/bolt/test/runtime/X86/instrumentation-pie.c b/bolt/test/runtime/X86/instrumentation-pie.c --- a/bolt/test/runtime/X86/instrumentation-pie.c +++ b/bolt/test/runtime/X86/instrumentation-pie.c @@ -31,7 +31,7 @@ # Test that the instrumented data makes sense RUN: llvm-bolt %t.exe -o %t.bolted -data %t.fdata \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ RUN: %t.bolted 1 2 3 | FileCheck %s -check-prefix=CHECK-OUTPUT diff --git a/bolt/test/runtime/X86/instrumentation-shlib.c b/bolt/test/runtime/X86/instrumentation-shlib.c --- a/bolt/test/runtime/X86/instrumentation-shlib.c +++ b/bolt/test/runtime/X86/instrumentation-shlib.c @@ -61,7 +61,7 @@ # Test that the instrumented data makes sense RUN: llvm-bolt %t.so -o %t.so.bolted -data %t.so.fdata \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ RUN: %t.exe %t.so.bolted 1 2 | FileCheck %s -check-prefix=CHECK-OUTPUT diff --git a/bolt/test/runtime/X86/tail-duplication-constant-prop.s b/bolt/test/runtime/X86/tail-duplication-constant-prop.s --- a/bolt/test/runtime/X86/tail-duplication-constant-prop.s +++ b/bolt/test/runtime/X86/tail-duplication-constant-prop.s @@ -4,7 +4,7 @@ # RUN: %s -o %t.o # RUN: link_fdata %s %t.o %t.fdata # RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=cache+ -print-finalized \ +# RUN: llvm-bolt %t.exe -data %t.fdata -reorder-blocks=ext-tsp -print-finalized \ # RUN: -tail-duplication -tail-duplication-minimum-offset 1 -o %t.out | FileCheck %s # RUN: %t.exe; echo $? # RUN: %t.out; echo $? diff --git a/bolt/test/runtime/meta-merge-fdata.test b/bolt/test/runtime/meta-merge-fdata.test --- a/bolt/test/runtime/meta-merge-fdata.test +++ b/bolt/test/runtime/meta-merge-fdata.test @@ -20,7 +20,7 @@ # Check that BOLT works with this profile RUN: llvm-bolt merge-fdata -o %t.bolt -data %t.fdata1 \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ -split-functions=3 | \ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions=3 | \ RUN: FileCheck %s --check-prefix=CHECK-BOLT1 CHECK-BOLT1-NOT: invalid (possibly stale) profile @@ -41,7 +41,7 @@ # Optimize using merged fdata RUN: llvm-bolt merge-fdata -o %t.opt -data %t.fdata.base \ -RUN: -reorder-blocks=cache+ -reorder-functions=hfsort+ -split-functions=3 | \ +RUN: -reorder-blocks=ext-tsp -reorder-functions=hfsort+ -split-functions=3 | \ RUN: FileCheck %s --check-prefix=CHECK-BOLT2 CHECK-BOLT2-NOT: invalid (possibly stale) profile