maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

amdgpu/math: Don't use llvm instrinsic for native_log 

AMDGPU targets don't have insturction for it,
so it'll be expanded to C * log2 anyway.

v2: use native_log2 instead of the more precise sw implementation
v3: move to amdgpu
v4: drop old AMD copyright

Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 316587
This commit is contained in:
Jan Vesely 2017-10-25 16:49:17 +00:00
parent 538612c885
commit 9fedbb9d8e
3 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libclc/amdgpu/lib/SOURCES
View File

@ -1,2 +1,3 @@
math/native_log.cl
math/nextafter.cl math/nextafter.cl
math/sqrt.cl math/sqrt.cl

5
libclc/amdgpu/lib/math/native_log.cl Normal file
View File

@ -0,0 +1,5 @@
#include <clc/clc.h>
#define __CLC_BODY <native_log.inc>
#define __FLOAT_ONLY
#include <clc/math/gentype.inc>

3
libclc/amdgpu/lib/math/native_log.inc Normal file
View File

@ -0,0 +1,3 @@
_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE native_log(__CLC_GENTYPE val) {
return native_log2(val) * (1.0f / M_LOG2E_F);
}