[BACKEND] two minor bugfix on StoreOpLowering and kernel launch & support optional other in LoadOpLowering (#69)
* [BACKEND] two minor bugfix on StoreOpLowering and kernel launch & support optional other in LoadOpLowering * Clean code Co-authored-by: goostavz <gzhu@nvidia.com> Co-authored-by: Yan Chunwei <yanchunwei@outlook.com>
This commit is contained in:
@@ -183,9 +183,9 @@ module attributes {"triton_gpu.num-warps" = 4 : i32} {
|
||||
// CHECK-LABEL: basic_store
|
||||
func @basic_store(%ptrs: tensor<256x!tt.ptr<f32>, #blocked0>, %vals: tensor<256xf32, #blocked0>, %mask: tensor<256xi1, #blocked0>) {
|
||||
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att
|
||||
// CHECK-SAME: st.global.v32.b1 [ ${{.*}} + 0 ], { ${{.*}} };", "b,l,r" %{{.*}}, %{{.*}}, %{{.*}} : (i1, !llvm.ptr<f32, 1>, i32) -> !llvm.struct<()>
|
||||
// CHECK-SAME: st.global.b32 [ ${{.*}} + 0 ], { ${{.*}} };", "b,l,r" %{{.*}}, %{{.*}}, %{{.*}} : (i1, !llvm.ptr<f32, 1>, i32) -> !llvm.struct<()>
|
||||
// CHECK: llvm.inline_asm has_side_effects asm_dialect = att
|
||||
// CHECK-SAME: st.global.v32.b1 [ ${{.*}} + 0 ], { ${{.*}} };", "b,l,r" %{{.*}}, %{{.*}}, %{{.*}} : (i1, !llvm.ptr<f32, 1>, i32) -> !llvm.struct<()>
|
||||
// CHECK-SAME: st.global.b32 [ ${{.*}} + 0 ], { ${{.*}} };", "b,l,r" %{{.*}}, %{{.*}}, %{{.*}} : (i1, !llvm.ptr<f32, 1>, i32) -> !llvm.struct<()>
|
||||
tt.store %ptrs, %vals, %mask, {} : tensor<256xf32, #blocked0>
|
||||
return
|
||||
}
|
||||
|
Reference in New Issue
Block a user