-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge remote-tracking branch 'origin/main' into egor/gemm_trans
- Loading branch information
Showing
23 changed files
with
569 additions
and
209 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
104 changes: 88 additions & 16 deletions
104
test/Conversion/amd/decompose-unsupported-conversions.mlir
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,33 +1,105 @@ | ||
| // RUN: triton-opt %s --split-input-file --decompose-unsupported-amd-conversions=arch=gfx1130 | FileCheck %s | ||
| // RUN: triton-opt %s --split-input-file --decompose-unsupported-amd-conversions | FileCheck %s | ||
|
|
||
| // CHECK: #[[BLOCKED:.+]] = #triton_gpu.blocked<{{.*}}> | ||
| // CHECK: #[[WMMA:.+]] = #triton_gpu.amd_wmma<{{.*}}> | ||
| // CHECK: #[[SHARED:.+]] = #triton_gpu.shared<{{.*}}> | ||
| // CHECK: wmma_to_wmma_dot_op | ||
| // CHECK: #[[$BLOCKED:.+]] = #triton_gpu.blocked<{{.*}}> | ||
| // CHECK: #[[$WMMA:.+]] = #triton_gpu.amd_wmma<{{.*}}> | ||
| // CHECK: #[[$SHARED:.+]] = #triton_gpu.shared<{{.*}}> | ||
| // CHECK-LABEL: wmma_to_wmma_dot_op | ||
| #mma = #triton_gpu.amd_wmma<{version = 1, warpsPerCTA = [2, 2]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 32 : i32} { | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx1130", "triton_gpu.threads-per-warp" = 32 : i32} { | ||
| tt.func @wmma_to_wmma_dot_op(%arg0: tensor<16x16xf16, #mma>) { | ||
| // CHECK: %[[SRC_BLOCKED:.+]] = triton_gpu.convert_layout %{{.*}} : tensor<16x16xf16, #[[WMMA]]> -> tensor<16x16xf16, #[[BLOCKED]]> | ||
| // CHECK-NEXT: %[[INT_SHARED:.+]] = triton_gpu.local_alloc %[[SRC_BLOCKED]] : {{.*}} -> !tt.memdesc<16x16xf16, #[[SHARED]], #triton_gpu.shared_memory> | ||
| // CHECK-NEXT: %[[DST_DOT_OP:.+]] = triton_gpu.local_load %[[INT_SHARED]] : {{.*}} -> tensor<16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #[[WMMA]], kWidth = 16}>> | ||
| // CHECK: %[[SRC_BLOCKED:.+]] = triton_gpu.convert_layout %{{.*}} : tensor<16x16xf16, #[[$WMMA]]> -> tensor<16x16xf16, #[[$BLOCKED]]> | ||
| // CHECK-NEXT: %[[INT_SHARED:.+]] = triton_gpu.local_alloc %[[SRC_BLOCKED]] : {{.*}} -> !tt.memdesc<16x16xf16, #[[$SHARED]], #triton_gpu.shared_memory> | ||
| // CHECK-NEXT: %[[DST_DOT_OP:.+]] = triton_gpu.local_load %[[INT_SHARED]] : {{.*}} -> tensor<16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #[[$WMMA]], kWidth = 16}>> | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<16x16xf16, #mma> -> tensor<16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #mma, kWidth = 16}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK: #[[BLOCKED:.+]] = #triton_gpu.blocked<{{.*}}> | ||
| // CHECK: #[[WMMA:.+]] = #triton_gpu.amd_wmma<{{.*}}> | ||
| // CHECK: #[[SHARED:.+]] = #triton_gpu.shared<{{.*}}> | ||
| // CHECK: wmma_to_wmma_dot3d_op | ||
| // CHECK: #[[$BLOCKED:.+]] = #triton_gpu.blocked<{{.*}}> | ||
| // CHECK: #[[$WMMA:.+]] = #triton_gpu.amd_wmma<{{.*}}> | ||
| // CHECK: #[[$SHARED:.+]] = #triton_gpu.shared<{{.*}}> | ||
| // CHECK-LABEL: wmma_to_wmma_dot3d_op | ||
| #mma = #triton_gpu.amd_wmma<{version = 1, warpsPerCTA = [2, 2, 2]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 32 : i32} { | ||
| tt.func @wmma_to_wmma_dot3d_op(%arg0: tensor<2x16x16xf16, #mma>) { | ||
| // CHECK: %[[SRC_BLOCKED:.+]] = triton_gpu.convert_layout %{{.*}} : tensor<2x16x16xf16, #[[WMMA]]> -> tensor<2x16x16xf16, #[[BLOCKED]]> | ||
| // CHECK-NEXT: %[[INT_SHARED:.+]] = triton_gpu.local_alloc %[[SRC_BLOCKED]] : {{.*}} -> !tt.memdesc<2x16x16xf16, #[[SHARED]], #triton_gpu.shared_memory> | ||
| // CHECK-NEXT: %[[DST_DOT_OP:.+]] = triton_gpu.local_load %[[INT_SHARED]] : {{.*}} -> tensor<2x16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #[[WMMA]], kWidth = 16}>> | ||
| // CHECK: %[[SRC_BLOCKED:.+]] = triton_gpu.convert_layout %{{.*}} : tensor<2x16x16xf16, #[[$WMMA]]> -> tensor<2x16x16xf16, #[[$BLOCKED]]> | ||
| // CHECK-NEXT: %[[INT_SHARED:.+]] = triton_gpu.local_alloc %[[SRC_BLOCKED]] : {{.*}} -> !tt.memdesc<2x16x16xf16, #[[$SHARED]], #triton_gpu.shared_memory> | ||
| // CHECK-NEXT: %[[DST_DOT_OP:.+]] = triton_gpu.local_load %[[INT_SHARED]] : {{.*}} -> tensor<2x16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #[[$WMMA]], kWidth = 16}>> | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<2x16x16xf16, #mma> -> tensor<2x16x16xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #mma, kWidth = 16}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK-LABEL: blocked_to_dot_op_shortcut_gfx1130 | ||
| #blocked = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [32, 1], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx1130", "triton_gpu.threads-per-warp" = 32 : i32} { | ||
| tt.func @blocked_to_dot_op_shortcut_gfx1130(%arg0: tensor<32x32xf16, #blocked>) { | ||
| // CHECK-NOT: triton_gpu.local_alloc | ||
| // CHECK: triton_gpu.convert_layout | ||
| // CHECK-NOT: triton_gpu.local_alloc | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<32x32xf16, #blocked> -> tensor<32x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK-LABEL: blocked_to_dot_op_shortcut_gfx940 | ||
| #blocked = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [32, 2], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx940", "triton_gpu.threads-per-warp" = 64 : i32} { | ||
| tt.func @blocked_to_dot_op_shortcut_gfx940(%arg0: tensor<32x32xf16, #blocked>) { | ||
| // CHECK-NOT: triton_gpu.local_alloc | ||
| // CHECK: triton_gpu.convert_layout | ||
| // CHECK-NOT: triton_gpu.local_alloc | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<32x32xf16, #blocked> -> tensor<32x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK-LABEL: neg_blocked_to_dot_op_incompatible_elems_gfx940 | ||
| #blocked = #triton_gpu.blocked<{sizePerThread = [1, 16], threadsPerWarp = [32, 2], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx940", "triton_gpu.threads-per-warp" = 64 : i32} { | ||
| tt.func @neg_blocked_to_dot_op_incompatible_elems_gfx940(%arg0: tensor<32x32xf16, #blocked>) { | ||
| // CHECK-NOT: triton_gpu.convert_layout | ||
| // CHECK: triton_gpu.local_alloc | ||
| // CHECK: triton_gpu.local_load | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<32x32xf16, #blocked> -> tensor<32x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK-LABEL: neg_blocked_to_dot_op_incompatible_threads_gfx940 | ||
| #blocked = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [32, 2], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| #blocked1 = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [16, 4], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx940", "triton_gpu.threads-per-warp" = 64 : i32} { | ||
| tt.func @neg_blocked_to_dot_op_incompatible_threads_gfx940(%arg0: tensor<32x32xf16, #blocked>) { | ||
| // CHECK-NOT: triton_gpu.convert_layout | ||
| // CHECK: triton_gpu.local_alloc | ||
| // CHECK: triton_gpu.local_load | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<32x32xf16, #blocked> -> tensor<32x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked1}>> | ||
| tt.return | ||
| } | ||
| } | ||
|
|
||
| // ----- | ||
|
|
||
| // CHECK-LABEL: neg_blocked_to_dot_op_incompatible_warp_gfx940 | ||
| #blocked = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [32, 2], warpsPerCTA = [2, 2], order = [1, 0]}> | ||
| #blocked1 = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [32, 2], warpsPerCTA = [4, 1], order = [1, 0]}> | ||
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, triton_gpu.target = "hip:gfx940", "triton_gpu.threads-per-warp" = 64 : i32} { | ||
| tt.func @neg_blocked_to_dot_op_incompatible_warp_gfx940(%arg0: tensor<32x32xf16, #blocked>) { | ||
| // CHECK-NOT: triton_gpu.convert_layout | ||
| // CHECK: triton_gpu.local_alloc | ||
| // CHECK: triton_gpu.local_load | ||
| %0 = triton_gpu.convert_layout %arg0 : tensor<32x32xf16, #blocked> -> tensor<32x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked1}>> | ||
| tt.return | ||
| } | ||
| } |
Oops, something went wrong.