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

amdgcn: Convert get_global_size to clc 

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-By: Aaron Watry <awatry@gmail.com>
llvm-svn: 346080
This commit is contained in:
Jan Vesely 2018-11-04 00:39:20 +00:00
parent ea2f32b75d
commit 97283de27d
13 changed files with 16 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libclc/amdgcn/lib/OVERRIDES_3.9
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.ll
workitem/get_global_size.ll
workitem/get_num_groups.ll

1
libclc/amdgcn/lib/OVERRIDES_4.0
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.ll
workitem/get_global_size.ll
workitem/get_num_groups.ll

1
libclc/amdgcn/lib/OVERRIDES_5.0
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.ll
workitem/get_global_size.ll
workitem/get_num_groups.ll

1
libclc/amdgcn/lib/OVERRIDES_6.0
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.ll
workitem/get_global_size.ll
workitem/get_num_groups.ll

2
libclc/amdgcn/lib/SOURCES
View File

@ -7,7 +7,7 @@ mem_fence/fence.cl
synchronization/barrier.cl
workitem/get_global_offset.cl
workitem/get_group_id.cl
workitem/get_global_size.ll
workitem/get_global_size.cl
workitem/get_local_id.cl
workitem/get_local_size.cl
workitem/get_num_groups.ll

1
libclc/amdgcn/lib/SOURCES_3.9
View File

@ -1,4 +1,3 @@
cl_khr_int64_extended_atomics/minmax_helpers.39.ll
mem_fence/waitcnt.ll
workitem/get_global_size.39.ll
workitem/get_num_groups.39.ll

1
libclc/amdgcn/lib/SOURCES_4.0
View File

@ -1,4 +1,3 @@
cl_khr_int64_extended_atomics/minmax_helpers.39.ll
mem_fence/waitcnt.ll
workitem/get_global_size.40.ll
workitem/get_num_groups.40.ll

1
libclc/amdgcn/lib/SOURCES_5.0
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.39.ll
workitem/get_global_size.40.ll
workitem/get_num_groups.40.ll

1
libclc/amdgcn/lib/SOURCES_6.0
View File

@ -1,3 +1,2 @@
cl_khr_int64_extended_atomics/minmax_helpers.39.ll
workitem/get_global_size.40.ll
workitem/get_num_groups.40.ll

20
libclc/amdgcn/lib/workitem/get_global_size.39.ll
View File

@ -1,20 +0,0 @@
declare i32 @llvm.r600.read.global.size.x() nounwind readnone
declare i32 @llvm.r600.read.global.size.y() nounwind readnone
declare i32 @llvm.r600.read.global.size.z() nounwind readnone
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
define i32 @get_global_size(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.global.size.x()
ret i32 %x
y_dim:
%y = call i32 @llvm.r600.read.global.size.y()
ret i32 %y
z_dim:
%z = call i32 @llvm.r600.read.global.size.z()
ret i32 %z
default:
ret i32 1
}

23
libclc/amdgcn/lib/workitem/get_global_size.40.ll
View File

@ -1,23 +0,0 @@
declare i32 @llvm.r600.read.global.size.x() nounwind readnone
declare i32 @llvm.r600.read.global.size.y() nounwind readnone
declare i32 @llvm.r600.read.global.size.z() nounwind readnone
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
define i64 @get_global_size(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.global.size.x()
%x.ext = zext i32 %x to i64
ret i64 %x.ext
y_dim:
%y = call i32 @llvm.r600.read.global.size.y()
%y.ext = zext i32 %y to i64
ret i64 %y.ext
z_dim:
%z = call i32 @llvm.r600.read.global.size.z()
%z.ext = zext i32 %z to i64
ret i64 %z.ext
default:
ret i64 1
}

15
libclc/amdgcn/lib/workitem/get_global_size.cl Normal file
View File

@ -0,0 +1,15 @@
#include <clc/clc.h>
uint __clc_amdgcn_get_global_size_x(void) __asm("llvm.r600.read.global.size.x");
uint __clc_amdgcn_get_global_size_y(void) __asm("llvm.r600.read.global.size.y");
uint __clc_amdgcn_get_global_size_z(void) __asm("llvm.r600.read.global.size.z");
_CLC_DEF size_t get_global_size(uint dim)
{
switch (dim) {
case 0: return __clc_amdgcn_get_global_size_x();
case 1: return __clc_amdgcn_get_global_size_y();
case 2: return __clc_amdgcn_get_global_size_z();
default: return 1;
}
}

23
libclc/amdgcn/lib/workitem/get_global_size.ll
View File

@ -1,23 +0,0 @@
declare i32 @llvm.r600.read.global.size.x() nounwind readnone
declare i32 @llvm.r600.read.global.size.y() nounwind readnone
declare i32 @llvm.r600.read.global.size.z() nounwind readnone
target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
define i64 @get_global_size(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.global.size.x()
%x.ext = zext i32 %x to i64
ret i64 %x.ext
y_dim:
%y = call i32 @llvm.r600.read.global.size.y()
%y.ext = zext i32 %y to i64
ret i64 %y.ext
z_dim:
%z = call i32 @llvm.r600.read.global.size.z()
%z.ext = zext i32 %z to i64
ret i64 %z.ext
default:
ret i64 1
}