e3cf80c5c1
BlockFrequencyInfo calculates block frequencies as Scaled64 numbers but as a last step converts them to unsigned 64bit integers (`BlockFrequency`). This improves the factors picked for this conversion so that: * Avoid big numbers close to UINT64_MAX to avoid users overflowing/saturating when adding multiply frequencies together or when multiplying with integers. This leaves the topmost 10 bits unused to allow for some room. * Spread the difference between hottest/coldest block as much as possible to increase precision. * If the hot/cold spread cannot be represented loose precision at the lower end, but keep the frequencies at the upper end for hot blocks differentiable.
35 lines
996 B
LLVM
35 lines
996 B
LLVM
; RUN: opt < %s -passes=partial-inliner -max-num-inline-blocks=2 -skip-partial-inlining-cost-analysis -S | FileCheck %s
|
|
|
|
; This test checks to make sure that CodeExtractor updates
|
|
; the exit branch probabilities for multiple exit blocks.
|
|
|
|
define i32 @inlinedFunc(i1 %cond) !prof !1 {
|
|
entry:
|
|
br i1 %cond, label %if.then, label %return, !prof !2
|
|
if.then:
|
|
br i1 %cond, label %return, label %return.2, !prof !3
|
|
return.2:
|
|
ret i32 10
|
|
return: ; preds = %entry
|
|
ret i32 0
|
|
}
|
|
|
|
|
|
define internal i32 @dummyCaller(i1 %cond) !prof !1 {
|
|
entry:
|
|
%val = call i32 @inlinedFunc(i1 %cond)
|
|
ret i32 %val
|
|
|
|
; CHECK-LABEL: @dummyCaller
|
|
; CHECK: call
|
|
; CHECK-NEXT: br i1 {{.*}}return.i{{.*}}return.2{{.*}}!prof [[COUNT1:![0-9]+]]
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 1, !"MaxFunctionCount", i32 10000}
|
|
!1 = !{!"function_entry_count", i64 10000}
|
|
!2 = !{!"branch_weights", i32 5, i32 5}
|
|
!3 = !{!"branch_weights", i32 4, i32 1}
|
|
|
|
; CHECK: [[COUNT1]] = !{!"branch_weights", i32 858993459, i32 214748365}
|