diff options
| author | dfukalov <daniil.fukalov@amd.com> | 2019-11-18 16:42:34 +0300 |
|---|---|---|
| committer | dfukalov <daniil.fukalov@amd.com> | 2019-11-19 16:33:16 +0300 |
| commit | 6fd11b14f604914df4f777f4c7ff20dbbc50877b (patch) | |
| tree | 5b344c97e9218d537f332da25bbc56944a63c484 /llvm/test | |
| parent | 6de85095ed7d8f161a7f39422d42b5bc2d2dcb98 (diff) | |
| download | bcm5719-llvm-6fd11b14f604914df4f777f4c7ff20dbbc50877b.tar.gz bcm5719-llvm-6fd11b14f604914df4f777f4c7ff20dbbc50877b.zip | |
[AMDGPU] Tune inlining parameters for AMDGPU target (part 2)
Summary:
Most of IR instructions got better code size estimations after commit 47a5c36b.
So default parameters values should be updated to improve inlining and
unrolling for the target.
Reviewers: rampitec, arsenm
Reviewed By: rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, zzheng, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70391
Diffstat (limited to 'llvm/test')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll | 7 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll | 2 |
2 files changed, 8 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll index c2f1836f44a..243522e28dd 100644 --- a/llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll +++ b/llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll @@ -28,8 +28,15 @@ if.end: ; preds = %if.then, %entry define coldcc void @foo_private_ptr2(float addrspace(5)* nocapture %p1, float addrspace(5)* nocapture %p2) { entry: %tmp1 = load float, float addrspace(5)* %p1, align 4 + %cmp = fcmp ogt float %tmp1, 1.000000e+00 + br i1 %cmp, label %if.then, label %if.end + +if.then: %div = fdiv float 2.000000e+00, %tmp1 store float %div, float addrspace(5)* %p2, align 4 + br label %if.end + +if.end: ret void } diff --git a/llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll b/llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll index 74e124cf6af..d1fbc87602b 100644 --- a/llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll +++ b/llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll @@ -1,4 +1,4 @@ -; RUN: opt -data-layout=A5 -mtriple=amdgcn-unknown-amdhsa -loop-unroll -S -amdgpu-unroll-threshold-private=12000 %s | FileCheck %s +; RUN: opt -data-layout=A5 -mtriple=amdgcn-unknown-amdhsa -loop-unroll -S %s | FileCheck %s ; Check that we full unroll loop to be able to eliminate alloca ; CHECK-LABEL: @non_invariant_ind |
