diff options
| author | Tom Stellard <thomas.stellard@amd.com> | 2016-09-16 22:43:29 +0000 |
|---|---|---|
| committer | Tom Stellard <thomas.stellard@amd.com> | 2016-09-16 22:43:29 +0000 |
| commit | e7ad23bad32014b579fbc07ef9bf0a52bd070ec0 (patch) | |
| tree | b0a64b858f302eeb06e60037c0363237f98506a8 /libclc | |
| parent | 0a3ede0a14226b4b74335b81be466e045697ff80 (diff) | |
| download | llvm-e7ad23bad32014b579fbc07ef9bf0a52bd070ec0.zip llvm-e7ad23bad32014b579fbc07ef9bf0a52bd070ec0.tar.gz llvm-e7ad23bad32014b579fbc07ef9bf0a52bd070ec0.tar.bz2 | |
amdgcn-amdhsa: Add get_global_size() implementation
llvm-svn: 281791
Diffstat (limited to 'libclc')
| -rw-r--r-- | libclc/amdgcn-amdhsa/lib/SOURCES | 1 | ||||
| -rw-r--r-- | libclc/amdgcn-amdhsa/lib/workitem/get_global_size.ll | 39 |
2 files changed, 40 insertions, 0 deletions
diff --git a/libclc/amdgcn-amdhsa/lib/SOURCES b/libclc/amdgcn-amdhsa/lib/SOURCES index b33368d..257942c0 100644 --- a/libclc/amdgcn-amdhsa/lib/SOURCES +++ b/libclc/amdgcn-amdhsa/lib/SOURCES @@ -1 +1,2 @@ +workitem/get_global_size.ll workitem/get_local_size.ll diff --git a/libclc/amdgcn-amdhsa/lib/workitem/get_global_size.ll b/libclc/amdgcn-amdhsa/lib/workitem/get_global_size.ll new file mode 100644 index 0000000..af0f2ea --- /dev/null +++ b/libclc/amdgcn-amdhsa/lib/workitem/get_global_size.ll @@ -0,0 +1,39 @@ +declare i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr() #0 + +define i64 @get_global_size(i32 %dim) #1 { + %dispatch_ptr = call noalias nonnull dereferenceable(64) i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr() + switch i32 %dim, label %default [ + i32 0, label %x + i32 1, label %y + i32 2, label %z + ] + +x: + %ptr_x = getelementptr inbounds i8, i8 addrspace(2)* %dispatch_ptr, i64 12 + %ptr_x32 = bitcast i8 addrspace(2)* %ptr_x to i32 addrspace(2)* + %x32 = load i32, i32 addrspace(2)* %ptr_x32, align 4, !invariant.load !0 + %size_x = zext i32 %x32 to i64 + ret i64 %size_x + +y: + %ptr_y = getelementptr inbounds i8, i8 addrspace(2)* %dispatch_ptr, i64 16 + %ptr_y32 = bitcast i8 addrspace(2)* %ptr_y to i32 addrspace(2)* + %y32 = load i32, i32 addrspace(2)* %ptr_y32, align 4, !invariant.load !0 + %size_y = zext i32 %y32 to i64 + ret i64 %size_y + +z: + %ptr_z = getelementptr inbounds i8, i8 addrspace(2)* %dispatch_ptr, i64 20 + %ptr_z32 = bitcast i8 addrspace(2)* %ptr_z to i32 addrspace(2)* + %z32 = load i32, i32 addrspace(2)* %ptr_z32, align 4, !invariant.load !0 + %size_z = zext i32 %z32 to i64 + ret i64 %size_z + +default: + ret i64 1 +} + +attributes #0 = { nounwind readnone } +attributes #1 = { alwaysinline norecurse nounwind readonly } + +!0 = !{} |