mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-13 23:18:51 +00:00
c4f6d8cd25
LoopUnroll is a loop pass, so the analysis of OptimizationRemarkEmitter
is added to the common function analysis passes that loop passes
depend on.
The BFI and indirectly BPI used in this pass is computed lazily so no
overhead should be observed unless -pass-remarks-with-hotness is used.
This is how the patch affects the O3 pipeline:
Dominator Tree Construction
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Rotate Loops
Loop Invariant Code Motion
Unswitch loops
Simplify the CFG
Dominator Tree Construction
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Combine redundant instructions
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Induction Variable Simplification
Recognize loop idioms
Delete dead loops
Unroll loops
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@277203 91177308-0d34-0410-b5e6-96231b3b80d8
29 lines
1.1 KiB
LLVM
29 lines
1.1 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -pass-remarks=loop-unroll -pass-remarks-with-hotness -unroll-count=16 2>&1 | FileCheck -check-prefix=COMPLETE-UNROLL %s
|
|
; RUN: opt < %s -S -loop-unroll -pass-remarks=loop-unroll -pass-remarks-with-hotness -unroll-count=4 2>&1 | FileCheck -check-prefix=PARTIAL-UNROLL %s
|
|
|
|
; COMPLETE-UNROLL: remark: {{.*}}: completely unrolled loop with 16 iterations (hotness: 300)
|
|
; PARTIAL-UNROLL: remark: {{.*}}: unrolled loop by a factor of 4 {{.*}} (hotness: 300)
|
|
|
|
define i32 @sum() !prof !0 {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%s.06 = phi i32 [ 0, %entry ], [ %add1, %for.body ]
|
|
%i.05 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
|
%add = add nsw i32 %i.05, 4
|
|
%call = tail call i32 @baz(i32 %add) #2
|
|
%add1 = add nsw i32 %call, %s.06
|
|
%inc = add nsw i32 %i.05, 1
|
|
%exitcond = icmp eq i32 %inc, 16
|
|
br i1 %exitcond, label %for.end, label %for.body, !prof !1
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 %add1
|
|
}
|
|
|
|
declare i32 @baz(i32)
|
|
|
|
!0 = !{!"function_entry_count", i64 3}
|
|
!1 = !{!"branch_weights", i32 1, i32 99}
|