mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 11:02:59 +02:00
63de4725df
Summary: For flat loop, even if it is hot, it is not a good idea to unroll in runtime, thus we set a lower partial unroll threshold. For hot loop, we set a higher unroll threshold and allows expensive tripcount computation to allow more aggressive unrolling. Reviewers: davidxl, mzolotukhin Subscribers: sanjoy, mehdi_amini, llvm-commits Differential Revision: https://reviews.llvm.org/D26527 llvm-svn: 287186
60 lines
2.0 KiB
LLVM
60 lines
2.0 KiB
LLVM
; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-threshold=40 -unroll-dynamic-cost-savings-discount=0 | FileCheck %s
|
|
|
|
@known_constant = internal unnamed_addr constant [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
|
|
|
|
; CHECK-LABEL: @bar_prof
|
|
; CHECK: loop.prol:
|
|
; CHECK: loop:
|
|
; CHECK: %mul = mul
|
|
; CHECK: %mul.1 = mul
|
|
; CHECK: %mul.2 = mul
|
|
; CHECK: %mul.3 = mul
|
|
define i32 @bar_prof(i32* noalias nocapture readonly %src, i64 %c) !prof !1 {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
|
|
%r = phi i32 [ 0, %entry ], [ %add, %loop ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %src, i64 %iv
|
|
%src_element = load i32, i32* %arrayidx, align 4
|
|
%array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
|
|
%const_array_element = load i32, i32* %array_const_idx, align 4
|
|
%mul = mul nsw i32 %src_element, %const_array_element
|
|
%add = add nsw i32 %mul, %r
|
|
%inc = add nuw nsw i64 %iv, 1
|
|
%exitcond86.i = icmp eq i64 %inc, %c
|
|
br i1 %exitcond86.i, label %loop.end, label %loop, !prof !2
|
|
|
|
loop.end:
|
|
%r.lcssa = phi i32 [ %r, %loop ]
|
|
ret i32 %r.lcssa
|
|
}
|
|
|
|
; CHECK-LABEL: @bar_prof_flat
|
|
; CHECK-NOT: loop.prol
|
|
define i32 @bar_prof_flat(i32* noalias nocapture readonly %src, i64 %c) !prof !1 {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
|
|
%r = phi i32 [ 0, %entry ], [ %add, %loop ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %src, i64 %iv
|
|
%src_element = load i32, i32* %arrayidx, align 4
|
|
%array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
|
|
%const_array_element = load i32, i32* %array_const_idx, align 4
|
|
%mul = mul nsw i32 %src_element, %const_array_element
|
|
%add = add nsw i32 %mul, %r
|
|
%inc = add nuw nsw i64 %iv, 1
|
|
%exitcond86.i = icmp eq i64 %inc, %c
|
|
br i1 %exitcond86.i, label %loop, label %loop.end, !prof !2
|
|
|
|
loop.end:
|
|
%r.lcssa = phi i32 [ %r, %loop ]
|
|
ret i32 %r.lcssa
|
|
}
|
|
|
|
!1 = !{!"function_entry_count", i64 1}
|
|
!2 = !{!"branch_weights", i32 1, i32 1000}
|