diff options
| author | Zvi Rackover <zvi.rackover@intel.com> | 2017-09-04 08:35:13 +0000 |
|---|---|---|
| committer | Zvi Rackover <zvi.rackover@intel.com> | 2017-09-04 08:35:13 +0000 |
| commit | 9a087a357a4be44bb40f69f3e23a3e295f70f13e (patch) | |
| tree | 6912a8eea740e79d05328ea5af7a45470027ded6 /llvm/test/Transforms/LoopVectorize | |
| parent | 7cd826a321d96af6581e0b1a5d6ec9ad26dcc6c1 (diff) | |
| download | bcm5719-llvm-9a087a357a4be44bb40f69f3e23a3e295f70f13e.tar.gz bcm5719-llvm-9a087a357a4be44bb40f69f3e23a3e295f70f13e.zip | |
LoopVectorize: MaxVF should not be larger than the loop trip count
Summary:
Improve how MaxVF is computed while taking into account that MaxVF should not be larger than the loop's trip count.
Other than saving on compile-time by pruning the possible MaxVF candidates, this patch fixes pr34438 which exposed the following flow:
1. Short trip count identified -> Don't bail out, set OptForSize:=True to avoid tail-loop and runtime checks.
2. Compute MaxVF returned 16 on a target supporting AVX512.
3. OptForSize -> choose VF:=MaxVF.
4. Bail out because TripCount = 8, VF = 16, TripCount % VF !=0 means we need a tail loop.
With this patch step 2. will choose MaxVF=8 based on TripCount.
Reviewers: Ayal, dorit, mkuper, hfinkel
Reviewed By: hfinkel
Subscribers: hfinkel, llvm-commits
Differential Revision: https://reviews.llvm.org/D37425
llvm-svn: 312472
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/X86/pr34438.ll | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr34438.ll b/llvm/test/Transforms/LoopVectorize/X86/pr34438.ll new file mode 100644 index 00000000000..6699985c0a0 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/X86/pr34438.ll @@ -0,0 +1,35 @@ +; PR34438 +; Loop has a short trip count of 8 iterations. It should be vectorized because no runtime checks or tail loop are necessary. +; Two cases tested AVX (MaxVF=8 = TripCount) and AVX512 (MaxVF=16 > TripCount) + +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s +; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=skylake-avx512 -S | FileCheck %s + +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx10.8.0" + +define void @small_tc(float* noalias nocapture %A, float* noalias nocapture readonly %B) { +; CHECK-LABEL: @small_tc +; CHECK: load <8 x float>, <8 x float>* +; CHECK: fadd fast <8 x float> +entry: + br label %for.body + +for.body: + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv + %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3 + %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv + %1 = load float, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3 + %add = fadd fast float %0, %1 + store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 8 + br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4 + +for.end: + ret void +} + +!3 = !{!3} +!4 = !{!4} |
