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

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

15 lines
341 B
Plaintext
Raw Normal View History

Implement cl_khr_int64_extended_atomics builtins Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 313811
2017-09-21 04:42:19 +08:00
cl_khr_int64_extended_atomics/minmax_helpers.ll
amdgcn,popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICs This is only really needed for VI+ ASICs. However, llvm would cast the value to i32 for older asics anyway. The proper fix is in LLVM-7 (r326535). Fixes CTS popcount on carrizo. Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327044
2018-03-09 02:58:07 +08:00
integer/popcount.cl
amdgcn/fmax: fcanonicalize operands v_max instruction needs canonicalized operands. Passes CTS on carrizo Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327076
2018-03-09 07:01:01 +08:00
math/fmax.cl
amdgcn/fmin: fcanonicalize operands v_min instruction needs canonicalized operands. Passes CTS on carrizo Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327075
2018-03-09 07:00:58 +08:00
math/fmin.cl
Replace llvm.AMDGPU.ldexp with llvm.amdgcn.ldexp It didn't really work on r600 to begin with, which should get its own intrinsic. llvm-svn: 275813
2016-07-19 00:42:50 +08:00
math/ldexp.cl
amdgcn: Implement {read_,write_,}mem_fence builtin v2: add more detailed comment about waitcnt instruction Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 311021
2017-08-17 01:08:56 +08:00
mem_fence/fence.cl
amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier Specs require using fences when barrier() is invoked: "The barrier function will either flush any variables stored in local memory or queue a memory fence to ensure correct ordering of memory operations to local memory." and "The barrier function will queue a memory fence to ensure correct ordering of memory operations to global memory." Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 311022
2017-08-17 01:09:00 +08:00
synchronization/barrier.cl
AMDGPU: Implement get_global_offset builtin Also fix get_global_id to consider offset No idea how to add this for ptx, so they are stuck with the old get_global_id implementation. v2: split to a separate patch v3: Switch R600 to use implictarg.ptr Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 276443
2016-07-23 01:24:24 +08:00
workitem/get_global_offset.cl
AMDGPU: Use clang intrinsics for workitem builtins v2: split into 2 patches use clang builtins for other intrinsics as well v3: Fix warnings Switch r600 to use implictarg.ptr Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 276442
2016-07-23 01:24:20 +08:00
workitem/get_group_id.cl
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
2018-11-04 08:39:20 +08:00
workitem/get_global_size.cl
AMDGPU: Use clang intrinsics for workitem builtins v2: split into 2 patches use clang builtins for other intrinsics as well v3: Fix warnings Switch r600 to use implictarg.ptr Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 276442
2016-07-23 01:24:20 +08:00
workitem/get_local_id.cl
amdgcn: Convert get_local_size to clc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-By: Aaron Watry <awatry@gmail.com> llvm-svn: 346079
2018-11-04 08:39:16 +08:00
workitem/get_local_size.cl
amdgcn: Convert get_num_groups to clc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> Reviewed-By: Aaron Watry <awatry@gmail.com> llvm-svn: 346081
2018-11-04 08:39:25 +08:00
workitem/get_num_groups.cl
AMDGPU: Use clang intrinsics for workitem builtins v2: split into 2 patches use clang builtins for other intrinsics as well v3: Fix warnings Switch r600 to use implictarg.ptr Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 276442
2016-07-23 01:24:20 +08:00
workitem/get_work_dim.cl