diff options
| author | Qiu Chaofan <qiucofan@cn.ibm.com> | 2019-09-12 07:51:24 +0000 |
|---|---|---|
| committer | Qiu Chaofan <qiucofan@cn.ibm.com> | 2019-09-12 07:51:24 +0000 |
| commit | b7fb5d0f6f2abf07f0ce6edc3397b4c291c1d25e (patch) | |
| tree | b5fb0cbe9b96f54540d31e4c268e1cf633b249d2 /llvm/test/CodeGen/AMDGPU/rsq.ll | |
| parent | 75f65fe8d316407c5dd7cd9bfdfc760203947aa1 (diff) | |
| download | bcm5719-llvm-b7fb5d0f6f2abf07f0ce6edc3397b4c291c1d25e.tar.gz bcm5719-llvm-b7fb5d0f6f2abf07f0ce6edc3397b4c291c1d25e.zip | |
[DAGCombiner] Improve division estimation of floating points.
Current implementation of estimating divisions loses precision since it
estimates reciprocal first and does multiplication. This patch is to re-order
arithmetic operations in the last iteration in DAGCombiner to improve the
accuracy.
Reviewed By: Sanjay Patel, Jinsong Ji
Differential Revision: https://reviews.llvm.org/D66050
llvm-svn: 371713
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/rsq.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/rsq.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/rsq.ll b/llvm/test/CodeGen/AMDGPU/rsq.ll index 204eeb99838..40c3c94246e 100644 --- a/llvm/test/CodeGen/AMDGPU/rsq.ll +++ b/llvm/test/CodeGen/AMDGPU/rsq.ll @@ -48,7 +48,7 @@ define amdgpu_kernel void @rsq_f32_sgpr(float addrspace(1)* noalias %out, float ; SI-UNSAFE-DAG: v_rsq_f32_e32 [[RSQA:v[0-9]+]], [[A]] ; SI-UNSAFE-DAG: v_rcp_f32_e32 [[RCPB:v[0-9]+]], [[B]] -; SI-UNSAFE-DAG: v_mul_f32_e32 [[TMP:v[0-9]+]], [[RSQA]], [[RCPB]] +; SI-UNSAFE-DAG: v_mul_f32_e32 [[TMP:v[0-9]+]], [[RCPB]], [[RSQA]] ; SI-UNSAFE: v_mul_f32_e32 [[RESULT:v[0-9]+]], [[C]], [[TMP]] ; SI-UNSAFE: buffer_store_dword [[RESULT]] |
