maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Analysis/BranchProbabilityInfo/pr22718.ll

86 lines
3.7 KiB
LLVM
Raw Normal View History

Fix information loss in branch probability computation. Summary: This addresses PR 22718. When branch weights are too large, they were being clamped to the range [1, MaxWeightForBB]. But this clamping is only applied to edges that go outside the range, so it distorts the relative branch probabilities. This patch changes the weight calculation to scale every branch so the relative probabilities are preserved. The scaling is done differently now. First, all the branch weights are added up, and if the sum exceeds 32 bits, it computes an integer scale to bring all the weights within the range. The patch fixes an existing test that had slightly wrong branch probabilities due to the previous clamping. It now gets branch weights scaled accordingly. Reviewers: dexonsmith Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9442 llvm-svn: 236750
2015-05-08 01:22:06 +08:00
; RUN: opt < %s -analyze -branch-prob | FileCheck %s
[PM] Port Branch Probability Analysis pass to the new pass manager. Differential Revision: http://reviews.llvm.org/D19839 llvm-svn: 268601
2016-05-05 10:59:57 +08:00
; RUN: opt < %s -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s
Fix information loss in branch probability computation. Summary: This addresses PR 22718. When branch weights are too large, they were being clamped to the range [1, MaxWeightForBB]. But this clamping is only applied to edges that go outside the range, so it distorts the relative branch probabilities. This patch changes the weight calculation to scale every branch so the relative probabilities are preserved. The scaling is done differently now. First, all the branch weights are added up, and if the sum exceeds 32 bits, it computes an integer scale to bring all the weights within the range. The patch fixes an existing test that had slightly wrong branch probabilities due to the previous clamping. It now gets branch weights scaled accordingly. Reviewers: dexonsmith Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9442 llvm-svn: 236750
2015-05-08 01:22:06 +08:00
; In this test, the else clause is taken about 90% of the time. This was not
; reflected in the probability computation because the weight is larger than
; the branch weight cap (about 2 billion).
;
Use fixed-point representation for BranchProbability. BranchProbability now is represented by its numerator and denominator in uint32_t type. This patch changes this representation into a fixed point that is represented by the numerator in uint32_t type and a constant denominator 1<<31. This is quite similar to the representation of BlockMass in BlockFrequencyInfoImpl.h. There are several pros and cons of this change: Pros: 1. It uses only a half space of the current one. 2. Some operations are much faster like plus, subtraction, comparison, and scaling by an integer. Cons: 1. Constructing a probability using arbitrary numerator and denominator needs additional calculations. 2. It is a little less precise than before as we use a fixed denominator. For example, 1 - 1/3 may not be exactly identical to 1 / 3 (this will lead to many BranchProbability unit test failures). This should not matter when we only use it for branch probability. If we use it like a rational value for some precise calculations we may need another construct like ValueRatio. One important reason for this change is that we propose to store branch probabilities instead of edge weights in MachineBasicBlock. We also want clients to use probability instead of weight when adding successors to a MBB. The current BranchProbability has more space which may be a concern. Differential revision: http://reviews.llvm.org/D12603 llvm-svn: 248633
2015-09-26 07:09:59 +08:00
; CHECK: edge for.body -> if.then probability is 0x0cccba45 / 0x80000000 = 10.00%
; CHECK: edge for.body -> if.else probability is 0x733345bb / 0x80000000 = 90.00% [HOT edge]
Fix information loss in branch probability computation. Summary: This addresses PR 22718. When branch weights are too large, they were being clamped to the range [1, MaxWeightForBB]. But this clamping is only applied to edges that go outside the range, so it distorts the relative branch probabilities. This patch changes the weight calculation to scale every branch so the relative probabilities are preserved. The scaling is done differently now. First, all the branch weights are added up, and if the sum exceeds 32 bits, it computes an integer scale to bring all the weights within the range. The patch fixes an existing test that had slightly wrong branch probabilities due to the previous clamping. It now gets branch weights scaled accordingly. Reviewers: dexonsmith Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D9442 llvm-svn: 236750
2015-05-08 01:22:06 +08:00
@y = common global i64 0, align 8
@x = common global i64 0, align 8
@.str = private unnamed_addr constant [17 x i8] c"x = %lu\0Ay = %lu\0A\00", align 1
; Function Attrs: inlinehint nounwind uwtable
define i32 @main() #0 {
entry:
%retval = alloca i32, align 4
%i = alloca i64, align 8
store i32 0, i32* %retval
store i64 0, i64* @y, align 8
store i64 0, i64* @x, align 8
call void @srand(i32 422304) #3
store i64 0, i64* %i, align 8
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i64, i64* %i, align 8
%cmp = icmp ult i64 %0, 13000000000
br i1 %cmp, label %for.body, label %for.end, !prof !1
for.body: ; preds = %for.cond
%call = call i32 @rand() #3
%conv = sitofp i32 %call to double
%mul = fmul double %conv, 1.000000e+02
%div = fdiv double %mul, 0x41E0000000000000
%cmp1 = fcmp ogt double %div, 9.000000e+01
br i1 %cmp1, label %if.then, label %if.else, !prof !2
if.then: ; preds = %for.body
%1 = load i64, i64* @x, align 8
%inc = add i64 %1, 1
store i64 %inc, i64* @x, align 8
br label %if.end
if.else: ; preds = %for.body
%2 = load i64, i64* @y, align 8
%inc3 = add i64 %2, 1
store i64 %inc3, i64* @y, align 8
br label %if.end
if.end: ; preds = %if.else, %if.then
br label %for.inc
for.inc: ; preds = %if.end
%3 = load i64, i64* %i, align 8
%inc4 = add i64 %3, 1
store i64 %inc4, i64* %i, align 8
br label %for.cond
for.end: ; preds = %for.cond
%4 = load i64, i64* @x, align 8
%5 = load i64, i64* @y, align 8
%call5 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([17 x i8], [17 x i8]* @.str, i32 0, i32 0), i64 %4, i64 %5)
ret i32 0
}
; Function Attrs: nounwind
declare void @srand(i32) #1
; Function Attrs: nounwind
declare i32 @rand() #1
declare i32 @printf(i8*, ...) #2
attributes #0 = { inlinehint nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #3 = { nounwind }
!llvm.ident = !{!0}
!0 = !{!"clang version 3.7.0 (trunk 236218) (llvm/trunk 236235)"}
!1 = !{!"branch_weights", i32 -1044967295, i32 1}
!2 = !{!"branch_weights", i32 433323762, i32 -394957723}