diff options
| author | Kevin Qin <Kevin.Qin@arm.com> | 2015-03-09 06:14:28 +0000 |
|---|---|---|
| committer | Kevin Qin <Kevin.Qin@arm.com> | 2015-03-09 06:14:28 +0000 |
| commit | aef68418de5da1b2271057001d57b4078d140192 (patch) | |
| tree | 10609ce41b8ed25851fc97bf64458b21e494fca0 /llvm/test/Transforms/LoopUnroll/AArch64/partial.ll | |
| parent | 715b01e979aad41b1138fb21ed08601cc328159e (diff) | |
| download | bcm5719-llvm-aef68418de5da1b2271057001d57b4078d140192.tar.gz bcm5719-llvm-aef68418de5da1b2271057001d57b4078d140192.zip | |
[AArch64] Enable partial & runtime unrolling on cortex-a57
For inner one of nested loops, it is more likely to be a hot loop,
and the runtime check can be promoted out from patch 0001, so the
overhead is less, we can try a doubled threshold to unroll more loops.
llvm-svn: 231632
Diffstat (limited to 'llvm/test/Transforms/LoopUnroll/AArch64/partial.ll')
| -rw-r--r-- | llvm/test/Transforms/LoopUnroll/AArch64/partial.ll | 76 |
1 files changed, 76 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopUnroll/AArch64/partial.ll b/llvm/test/Transforms/LoopUnroll/AArch64/partial.ll new file mode 100644 index 00000000000..8a1ea80c9d5 --- /dev/null +++ b/llvm/test/Transforms/LoopUnroll/AArch64/partial.ll @@ -0,0 +1,76 @@ +; RUN: opt < %s -S -loop-unroll -mtriple aarch64 -mcpu=cortex-a57 | FileCheck %s + +; Partial unroll 8 times for this loop. +define void @unroll1() nounwind { +entry: + br label %loop + +loop: + %iv = phi i32 [ 0, %entry ], [ %inc, %loop ] + %inc = add i32 %iv, 1 + %exitcnd = icmp uge i32 %inc, 1024 + br i1 %exitcnd, label %exit, label %loop + +exit: + ret void +} + +; CHECK: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: icmp + +; Partial unroll 16 times for this loop. +define void @unroll2() nounwind { +entry: + br label %loop1 + +loop1: + %iv1 = phi i32 [ 0, %entry ], [ %inc1, %loop1.latch ] + br label %loop2.header + +loop2.header: + br label %loop2 + +loop2: + %iv2 = phi i32 [ 0, %loop2.header ], [ %inc2, %loop2 ] + %inc2 = add i32 %iv2, 1 + %exitcnd2 = icmp uge i32 %inc2, 1024 + br i1 %exitcnd2, label %exit2, label %loop2 + +exit2: + br label %loop1.latch + +loop1.latch: + %inc1 = add i32 %iv1, 1 + %exitcnd1 = icmp uge i32 %inc1, 1024 + br i1 %exitcnd2, label %exit, label %loop1 + +exit: + ret void +} + + + +; CHECK: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: add +; CHECK-NEXT: icmp |
