maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/PGOProfile/loop2.ll

73 lines
2.7 KiB
LLVM
Raw Normal View History

[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
[PGO] Use %t as the temporary profdata filename in the test cases. Using %t rather %T/<specific_name> as the temporary profdata filename. llvm-svn: 255271
2015-12-11 02:24:44 +08:00
; RUN: llvm-profdata merge %S/Inputs/loop2.proftext -o %t.profdata
; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
[PGO] Differentiate Clang instrumentation and IR level instrumentation profiles This patch uses one bit in profile version to differentiate Clang instrumentation and IR level instrumentation profiles. PGOInstrumenation generates a COMDAT variable __llvm_profile_raw_version so that the compiler runtime can set the right profile kind. For Maco-O platform, we generate the variable as linkonce_odr linkage as COMDAT is not supported. PGOInstrumenation now checks this bit to make sure it's an IR level instrumentation profile. The patch was submitted as r260164 but reverted due to a Darwin test breakage. Original Differential Revision: http://reviews.llvm.org/D15540 Differential Revision: http://reviews.llvm.org/D17020 llvm-svn: 260385
2016-02-11 01:18:30 +08:00
; GEN: $__llvm_profile_raw_version = comdat any
; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
[PGO] make profile prefix even shorter and more readable llvm-svn: 255586
2015-12-15 08:32:56 +08:00
; GEN: @__profn_test_nested_for = private constant [15 x i8] c"test_nested_for"
[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
define i32 @test_nested_for(i32 %r, i32 %s) {
entry:
; GEN: entry:
; GEN-NOT: call void @llvm.instrprof.increment
br label %for.cond.outer
for.cond.outer:
; GEN: for.cond.outer:
; GEN-NOT: call void @llvm.instrprof.increment
%i.0 = phi i32 [ 0, %entry ], [ %inc.2, %for.inc.outer ]
%sum.0 = phi i32 [ 1, %entry ], [ %sum.1, %for.inc.outer ]
%cmp = icmp slt i32 %i.0, %r
br i1 %cmp, label %for.body.outer, label %for.end.outer
; USE: br i1 %cmp, label %for.body.outer, label %for.end.outer
; USE-SAME: !prof ![[BW_FOR_COND_OUTER:[0-9]+]]
for.body.outer:
; GEN: for.body.outer:
; GEN-NOT: call void @llvm.instrprof.increment
br label %for.cond.inner
for.cond.inner:
; GEN: for.cond.inner:
; GEN-NOT: call void @llvm.instrprof.increment
%j.0 = phi i32 [ 0, %for.body.outer ], [ %inc.1, %for.inc.inner ]
%sum.1 = phi i32 [ %sum.0, %for.body.outer ], [ %inc, %for.inc.inner ]
%cmp2 = icmp slt i32 %j.0, %s
br i1 %cmp2, label %for.body.inner, label %for.end.inner
; USE: br i1 %cmp2, label %for.body.inner, label %for.end.inner
; USE-SAME: !prof ![[BW_FOR_COND_INNER:[0-9]+]]
for.body.inner:
; GEN: for.body.inner:
; GEN-NOT: call void @llvm.instrprof.increment
%inc = add nsw i32 %sum.1, 1
br label %for.inc.inner
for.inc.inner:
; GEN: for.inc.inner:
[PGO] make profile prefix even shorter and more readable llvm-svn: 255586
2015-12-15 08:32:56 +08:00
; GEN: call void @llvm.instrprof.increment(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @__profn_test_nested_for, i32 0, i32 0), i64 53929068288, i32 3, i32 0)
[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
%inc.1 = add nsw i32 %j.0, 1
br label %for.cond.inner
for.end.inner:
; GEN: for.end.inner:
br label %for.inc.outer
for.inc.outer:
; GEN: for.inc.outer:
[PGO] make profile prefix even shorter and more readable llvm-svn: 255586
2015-12-15 08:32:56 +08:00
; GEN: call void @llvm.instrprof.increment(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @__profn_test_nested_for, i32 0, i32 0), i64 53929068288, i32 3, i32 1)
[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
%inc.2 = add nsw i32 %i.0, 1
br label %for.cond.outer
for.end.outer:
; GEN: for.end.outer:
[PGO] make profile prefix even shorter and more readable llvm-svn: 255586
2015-12-15 08:32:56 +08:00
; GEN: call void @llvm.instrprof.increment(i8* getelementptr inbounds ([15 x i8], [15 x i8]* @__profn_test_nested_for, i32 0, i32 0), i64 53929068288, i32 3, i32 2)
[PGO] Resubmit "MST based PGO instrumentation infrastructure" (r254021) This new patch fixes a few bugs that exposed in last submit. It also improves the test cases. --Original Commit Message-- This patch implements a minimum spanning tree (MST) based instrumentation for PGO. The use of MST guarantees minimum number of CFG edges getting instrumented. An addition optimization is to instrument the less executed edges to further reduce the instrumentation overhead. The patch contains both the instrumentation and the use of the profile to set the branch weights. Differential Revision: http://reviews.llvm.org/D12781 llvm-svn: 255132
2015-12-10 02:08:16 +08:00
ret i32 %sum.0
}
; USE-DAG: ![[BW_FOR_COND_OUTER]] = !{!"branch_weights", i32 10, i32 6}
; USE-DAG: ![[BW_FOR_COND_INNER]] = !{!"branch_weights", i32 33, i32 10}