Add TGATHER indices part #988
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 |
|---|---|---|
| @@ -0,0 +1,88 @@ | ||
| # Copyright (c) 2026 Huawei Technologies Co., Ltd. | ||
| # This program is free software, you can redistribute it and/or modify it under the terms and conditions of | ||
| # CANN Open Software License Agreement Version 2.0 (the "License"). | ||
| # Please refer to the License for details. You may not use this file except in compliance with the License. | ||
| # THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, | ||
| # INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. | ||
| # See LICENSE in the root of the software repository for the full text of the License. | ||
|
|
||
| """PTODSL TileLib templates for pto.tgather.""" | ||
|
|
||
| from ptodsl import pto | ||
| import ptodsl.tilelib as tilelib | ||
| from ._common import NUMERIC_DTYPES | ||
| from ._common import element_store_dist | ||
|
|
||
|
|
||
| def gather_dtype_signatures(dtypes=NUMERIC_DTYPES): | ||
| res = [] | ||
| for dtype in dtypes: | ||
| for dtype_indices in ('i16', 'ui16', "i32", "ui32"): | ||
| res.append((dtype, dtype, dtype_indices)) | ||
| return res | ||
|
|
||
|
|
||
| @tilelib.tile_template( | ||
| op="pto.tgather", | ||
| target="a5", | ||
| name="template_tgather", | ||
| dtypes=gather_dtype_signatures(), | ||
| iteration_axis="none", | ||
| op_engine="vector", | ||
| op_class="other", | ||
| layouts=("row_major",), | ||
| loop_depth=2, | ||
| is_post_update=False | ||
| ) | ||
| def template_tgather( | ||
| src: pto.Tile, | ||
| dst: pto.Tile, | ||
| indices: pto.Tile): | ||
| dtype = dst.element_type | ||
| dtype_indices = indices.element_type | ||
| elem_bytes = pto.bytewidth(dtype) | ||
| elem_bytes_s1 = pto.bytewidth(dtype_indices) | ||
| valid_rows, valid_cols = indices.valid_shape | ||
| src_ptr = src.as_ptr() | ||
| if pto.const_expr(elem_bytes == 2 and elem_bytes_s1 == 4): | ||
| indices_type = pto.ui32 | ||
| lanes = pto.elements_per_vreg(indices_type) | ||
| for row in range(0, valid_rows, 1): | ||
| remained = valid_cols | ||
| for col in range(0, valid_cols, lanes): | ||
| indices_reg = pto.vlds(indices[row, col:]) | ||
| mask, remained = pto.make_mask(indices_type, remained) | ||
| dst_reg = pto.vgather2_bc(src_ptr, pto.vbitcast(indices_reg, indices_type), mask) | ||
| pto.vsts(dst_reg, dst[row, col:], mask) | ||
| elif pto.const_expr(elem_bytes == 1): | ||
| packed_lanes = pto.elements_per_vreg(dtype) >> 1 | ||
| result_elem = pto.ui16 if pto.const_expr(dtype == pto.ui8) else pto.i16 | ||
| result_ty = pto.vreg_type(packed_lanes, result_elem) | ||
| for row in range(0, valid_rows, 1): | ||
| remained = valid_cols | ||
| for col in range(0, valid_cols, packed_lanes): | ||
| indices_reg = pto.vlds(indices[row, col:]) | ||
| mask, remained = pto.make_mask(result_elem, remained) | ||
| dst_reg = pto.vgather2(src_ptr, pto.vbitcast(indices_reg, pto.ui16), mask, result_vreg_type=result_ty) | ||
| pto.vsts(dst_reg, dst[row, col:], mask, dist=pto.VStoreDist.PK_B16) | ||
|
Comment on lines
+47
to
+67
Collaborator
There was a problem hiding this comment. 这里4个分支大部分逻辑是相同的，能否合并，降低维护难度 |
||
| elif pto.const_expr(elem_bytes == 4): | ||
| indices_type = pto.ui32 | ||
| lanes = pto.elements_per_vreg(indices_type) | ||
| for row in range(0, valid_rows, 1): | ||
| remained = valid_cols | ||
| for col in range(0, valid_cols, lanes): | ||
| indices_reg = pto.vlds(indices[row, col:]) | ||
| mask, remained = pto.make_mask(indices_type, remained) | ||
| dst_reg = pto.vgather2(src_ptr, pto.vbitcast(indices_reg, indices_type), mask) | ||
| pto.vsts(dst_reg, dst[row, col:], mask) | ||
| else: | ||
| indices_type = pto.ui16 | ||
| lanes = pto.elements_per_vreg(indices_type) | ||
| for row in range(0, valid_rows, 1): | ||
| remained = valid_cols | ||
| for col in range(0, valid_cols, lanes): | ||
| indices_reg = pto.vlds(indices[row, col:]) | ||
| mask, remained = pto.make_mask(indices_type, remained) | ||
| dst_reg = pto.vgather2(src_ptr, pto.vbitcast(indices_reg, indices_type), mask) | ||
| pto.vsts(dst_reg, dst[row, col:], mask) | ||
|
|
||
This file contains hidden or 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 |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| // RUN: ptoas --pto-arch=a3 %s 2>&1 | FileCheck %s | ||
|
|
||
| module { | ||
| func.func @tgather_a2a3_index_with_tmp() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %tmp = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices, %tmp : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
| } | ||
|
|
||
| // CHECK: TGATHER({{[_A-Za-z][_A-Za-z0-9]*}}, {{[_A-Za-z][_A-Za-z0-9]*}}, {{[_A-Za-z][_A-Za-z0-9]*}}, {{[_A-Za-z][_A-Za-z0-9]*}}); |
This file contains hidden or 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 |
|---|---|---|
| @@ -0,0 +1,45 @@ | ||
| // RUN: not ptoas --pto-arch=a3 %s 2>&1 | FileCheck %s | ||
|
|
||
| module { | ||
| func.func @tgather_a2a3_index_missing_tmp() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
|
|
||
| func.func @tgather_a2a3_index_missing_indices() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
|
|
||
| func.func @tgather_a2a3_index_invalid_src_dtype() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i8, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %tmp = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i8, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices, %tmp : !pto.tile_buf<loc=vec, dtype=i8, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=i8, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
|
|
||
| func.func @tgather_a2a3_index_invalid_indices_dtype() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %tmp = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices, %tmp : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f16, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
| } | ||
|
|
||
| // CHECK: error: 'pto.tgather' op index-form tgather expects both indices and tmp | ||
| // CHECK: error: 'pto.tgather' op index-form tgather expects both indices and tmp | ||
| // CHECK: error: 'pto.tgather' op expects gather src/dst element type to be i16/i32/f16/f32 | ||
| // CHECK: error: 'pto.tgather' op expects indices element type to be i32 |
This file contains hidden or 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 |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| // RUN: ptoas --pto-arch=a5 %s 2>&1 | FileCheck %s | ||
|
|
||
| module { | ||
|
Collaborator
There was a problem hiding this comment. 本PR的主要变更是把tmp变为可选参数，这里要有相应的正负例测试 |
||
| func.func @tgather_a5_index_no_tmp() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
|
|
||
| func.func @tgather_a5_index_with_tmp() { | ||
| %src = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %indices = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %tmp = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| %dst = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tgather ins(%src, %indices, %tmp : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>, !pto.tile_buf<loc=vec, dtype=i32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| outs(%dst : !pto.tile_buf<loc=vec, dtype=f32, rows=1, cols=32, v_row=1, v_col=32, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| return | ||
| } | ||
| } | ||
|
|
||
| // CHECK: TGATHER | ||
|
Collaborator
There was a problem hiding this comment. lit只check TGATHER op name，没有check tmp参数等是否符合预期 |
||
| // CHECK: TGATHER | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A2A3和A5的行为都需要lit用例看护