[Triton-MLIR][Backend] Fix many problems to get the pipeline working (#809)
1. Rewrite code generation of insert_slice_async. 2. Correct the wrong index passed to extract_slice in pipeline. 3. Add a prologue in pipeline to wait for dangling cp.asyncs. 4. Move scf to cf conversion inside TritonGPUToLLVM because we need to perform membar before scf to cf. It shouldn't be a technical limitation and could be improved by a more general membar analysis. 5. Use an attribute to memoize the shared memory size and support dynamic shared memory. 6. Prevent the combine pass to reorder insert_slice and extract_slice across async_wait Co-authored-by: Superjomn <yanchunwei@outlook.com>
This commit is contained in:
@@ -22,7 +22,7 @@
|
||||
// CHECK: triton_gpu.async_wait {num = 2 : i32}
|
||||
// CHECK: %[[A0:.*]] = triton_gpu.extract_slice %[[A1BUFFER]], %[[CONSTANT_0]]
|
||||
// CHECK: %[[B0:.*]] = triton_gpu.extract_slice %[[B1BUFFER]], %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}, %[[arg_a0:.*]] = %[[A0]], %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}, %[[arg_a0:.*]] = %[[A0]], %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_1]]
|
||||
// CHECK: tt.dot %[[arg_a0]], %[[arg_b0]], {{.*}}
|
||||
// CHECK-DAG: %[[INSERT_IDX:.*]] = arith.remsi %[[PIPELINE_IDX]], %[[CONSTANT_3]]
|
||||
// CHECK-DAG: %[[EXTRACT_IDX:.*]] = arith.remsi %[[LOOP_IDX]], %[[CONSTANT_3]]
|
||||
@@ -78,7 +78,7 @@ func @matmul_loop(%lb : index, %ub : index, %step : index, %A : !tt.ptr<f16>, %B
|
||||
// CHECK: triton_gpu.async_wait {num = 2 : i32}
|
||||
// CHECK: %[[A0:.*]] = triton_gpu.extract_slice %[[A1BUFFER]], %[[CONSTANT_0]]
|
||||
// CHECK: %[[B0:.*]] = triton_gpu.extract_slice %[[B1BUFFER]], %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}, %[[arg_a0:.*]] = %[[A0]], %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}, %[[arg_a0:.*]] = %[[A0]], %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_1]]
|
||||
// CHECK: tt.dot %[[arg_a0]], %[[arg_b0]], {{.*}}
|
||||
// CHECK-DAG: %[[INSERT_IDX:.*]] = arith.remsi %[[PIPELINE_IDX]], %[[CONSTANT_3]]
|
||||
// CHECK-DAG: %[[EXTRACT_IDX:.*]] = arith.remsi %[[LOOP_IDX]], %[[CONSTANT_3]]
|
||||
@@ -131,7 +131,7 @@ func @matmul_loop_nested(%lb : index, %ub : index, %step : index, %A : !tt.ptr<f
|
||||
// CHECK: %[[B1BUFFER:.*]] = triton_gpu.insert_slice_async {{.*}}, {{.*}}, %[[CONSTANT_1]]
|
||||
// CHECK: triton_gpu.async_wait {num = 1 : i32}
|
||||
// CHECK: %[[B0:.*]] = triton_gpu.extract_slice %[[B1BUFFER]], %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_0]]
|
||||
// CHECK: scf.for {{.*}} iter_args({{.*}}, {{.*}}, {{.*}}, %[[arg_b0:.*]] = %[[B0]], {{.*}}, {{.*}}, %[[PIPELINE_IDX:.*]] = %[[CONSTANT_2]], %[[LOOP_IDX:.*]] = %[[CONSTANT_1]]
|
||||
// CHECK: tt.dot {{.*}}, %[[arg_b0]], {{.*}}
|
||||
// CHECK-DAG: %[[INSERT_IDX:.*]] = arith.remsi %[[PIPELINE_IDX]], %[[CONSTANT_3]]
|
||||
// CHECK-DAG: %[[EXTRACT_IDX:.*]] = arith.remsi %[[LOOP_IDX]], %[[CONSTANT_3]]
|
||||
|
Reference in New Issue
Block a user