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

amdgcn: Fix return type of get_num_groups 

llvm-svn: 279723
This commit is contained in:
Matt Arsenault 2016-08-25 07:31:40 +00:00
parent 83fd5d6aca
commit 958fce3192
5 changed files with 24 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libclc/amdgcn/lib/SOURCES
View File

@ -5,4 +5,5 @@ workitem/get_group_id.cl
workitem/get_global_size.ll
workitem/get_local_id.cl
workitem/get_local_size.ll
workitem/get_num_groups.ll
workitem/get_work_dim.cl

21
libclc/amdgcn/lib/workitem/get_num_groups.ll Normal file
View File

@ -0,0 +1,21 @@
declare i32 @llvm.r600.read.ngroups.x() nounwind readnone
declare i32 @llvm.r600.read.ngroups.y() nounwind readnone
declare i32 @llvm.r600.read.ngroups.z() nounwind readnone
define i64 @get_num_groups(i32 %dim) nounwind readnone alwaysinline {
switch i32 %dim, label %default [i32 0, label %x_dim i32 1, label %y_dim i32 2, label %z_dim]
x_dim:
%x = call i32 @llvm.r600.read.ngroups.x()
%x.ext = zext i32 %x to i64
ret i64 %x.ext
y_dim:
%y = call i32 @llvm.r600.read.ngroups.y()
%y.ext = zext i32 %y to i64
ret i64 %y.ext
z_dim:
%z = call i32 @llvm.r600.read.ngroups.z()
%z.ext = zext i32 %z to i64
ret i64 %z.ext
default:
ret i64 1
}

1
libclc/amdgpu/lib/SOURCES
View File

@ -16,4 +16,3 @@ image/write_imagef.cl
image/write_imagei.cl
image/write_imageui.cl
image/write_image_impl.ll
workitem/get_num_groups.ll

1
libclc/r600/lib/SOURCES
View File

@ -4,4 +4,5 @@ workitem/get_group_id.cl
workitem/get_global_size.ll
workitem/get_local_id.cl
workitem/get_local_size.ll
workitem/get_num_groups.ll
workitem/get_work_dim.cl

2
libclc/amdgpu/lib/workitem/get_num_groups.ll → libclc/r600/lib/workitem/get_num_groups.ll
View File

@ -14,5 +14,5 @@ z_dim:
%z = call i32 @llvm.r600.read.ngroups.z() nounwind readnone
ret i32 %z
default:
ret i32 0
ret i32 1
}