-
Notifications
You must be signed in to change notification settings - Fork 38
[codex] add test6 validshape tpush/tpop sample #476
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Draft
zhangstevenunity
wants to merge
1
commit into
main
Choose a base branch
from
codex/add-test6-validshape-pop
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+87
−0
Draft
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| // RUN: ptoas --pto-arch a5 %s | ||
| module { | ||
| func.func @matmul_tpush_tpop_loop4_print( | ||
| %gm_a: !pto.ptr<f32>, | ||
| %gm_b_all: !pto.ptr<f32>) | ||
| attributes {pto.entry} { | ||
| func.call @matmul_tpush_tpop_loop4_print_cube(%gm_a, %gm_b_all) | ||
| : (!pto.ptr<f32>, !pto.ptr<f32>) -> () | ||
| func.call @matmul_tpush_tpop_loop4_print_vector() : () -> () | ||
| return | ||
| } | ||
|
|
||
| func.func private @matmul_tpush_tpop_loop4_print_cube( | ||
| %gm_a: !pto.ptr<f32>, | ||
| %gm_b_all: !pto.ptr<f32>) | ||
| attributes {pto.kernel_kind = #pto.kernel_kind<cube>} { | ||
| %c0_i32 = arith.constant 0 : i32 | ||
| %c0 = arith.constant 0 : index | ||
| %c1 = arith.constant 1 : index | ||
| %c4 = arith.constant 4 : index | ||
| %c16 = arith.constant 16 : index | ||
| %c64 = arith.constant 64 : index | ||
|
|
||
| %c2v_import = pto.import_reserved_buffer { | ||
| name = "c2v_fifo", | ||
| peer_func = @matmul_tpush_tpop_loop4_print_vector | ||
| } -> i32 | ||
| pto.aic_initialize_pipe {dir_mask = 1, slot_size = 1024} | ||
| (c2v_consumer_buf = %c2v_import : i32, | ||
| v2c_consumer_buf = %c0_i32 : i32) | ||
|
|
||
| %mat_a_tile = pto.alloc_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0> | ||
| %mat_b_tile = pto.alloc_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0> | ||
| %left_tile = pto.alloc_tile : !pto.tile_buf<loc=left, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0> | ||
| %right_tile = pto.alloc_tile : !pto.tile_buf<loc=right, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=row_major, slayout=col_major, fractal=512, pad=0> | ||
| %c8 = arith.constant 8 : index | ||
| %acc_tile = pto.alloc_tile valid_row = %c16 valid_col = %c16 | ||
| : !pto.tile_buf<loc=acc, dtype=f32, rows=16, cols=16, v_row=?, v_col=?, blayout=col_major, slayout=row_major, fractal=1024, pad=0> | ||
|
|
||
| %gm_a_view = pto.make_tensor_view %gm_a, shape = [%c16, %c16], strides = [%c16, %c1] : !pto.tensor_view<?x?xf32> | ||
| %gm_b_all_view = pto.make_tensor_view %gm_b_all, shape = [%c64, %c16], strides = [%c16, %c1] : !pto.tensor_view<?x?xf32> | ||
| %gm_a_tile_view = pto.partition_view %gm_a_view, offsets = [%c0, %c0], sizes = [%c16, %c16] : !pto.tensor_view<?x?xf32> -> !pto.partition_tensor_view<16x16xf32> | ||
|
|
||
| pto.tload ins(%gm_a_tile_view : !pto.partition_tensor_view<16x16xf32>) outs(%mat_a_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>) | ||
| pto.tmov ins(%mat_a_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>) outs(%left_tile : !pto.tile_buf<loc=left, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>) | ||
|
|
||
| scf.for %i = %c0 to %c4 step %c1 { | ||
| %row_offset = arith.muli %i, %c16 : index | ||
| %gm_b_iter = pto.partition_view %gm_b_all_view, offsets = [%row_offset, %c0], sizes = [%c16, %c16] : !pto.tensor_view<?x?xf32> -> !pto.partition_tensor_view<16x16xf32> | ||
|
|
||
| pto.tload ins(%gm_b_iter : !pto.partition_tensor_view<16x16xf32>) outs(%mat_b_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>) | ||
| pto.tmov ins(%mat_b_tile : !pto.tile_buf<loc=mat, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>) outs(%right_tile : !pto.tile_buf<loc=right, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=row_major, slayout=col_major, fractal=512, pad=0>) | ||
| pto.tmatmul ins(%left_tile, %right_tile : !pto.tile_buf<loc=left, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=col_major, slayout=row_major, fractal=512, pad=0>, !pto.tile_buf<loc=right, dtype=f32, rows=16, cols=16, v_row=16, v_col=16, blayout=row_major, slayout=col_major, fractal=512, pad=0>) outs(%acc_tile : !pto.tile_buf<loc=acc, dtype=f32, rows=16, cols=16, v_row=?, v_col=?, blayout=col_major, slayout=row_major, fractal=1024, pad=0>) | ||
| pto.set_validshape %acc_tile, %c8, %c16 | ||
| : !pto.tile_buf<loc=acc, dtype=f32, rows=16, cols=16, v_row=?, v_col=?, blayout=col_major, slayout=row_major, fractal=1024, pad=0> | ||
| pto.tpush_to_aiv(%acc_tile : !pto.tile_buf<loc=acc, dtype=f32, rows=16, cols=16, v_row=?, v_col=?, blayout=col_major, slayout=row_major, fractal=1024, pad=0>) {split = 1} | ||
| } | ||
| return | ||
| } | ||
|
|
||
| func.func private @matmul_tpush_tpop_loop4_print_vector() | ||
| attributes {pto.kernel_kind = #pto.kernel_kind<vector>} { | ||
| %c0_i32 = arith.constant 0 : i32 | ||
| %c0 = arith.constant 0 : index | ||
| %c1 = arith.constant 1 : index | ||
| %c4 = arith.constant 4 : index | ||
| %c2v_local = pto.reserve_buffer { | ||
| name = "c2v_fifo", | ||
| size = 8192, | ||
| location = #pto.address_space<vec>, | ||
| auto = true | ||
| } -> i32 | ||
| pto.aiv_initialize_pipe {dir_mask = 1, slot_size = 1024} | ||
| (c2v_consumer_buf = %c2v_local : i32, | ||
| v2c_consumer_buf = %c0_i32 : i32) | ||
|
|
||
| %vec_print = pto.alloc_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=4, cols=16, v_row=4, v_col=16, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| scf.for %i = %c0 to %c4 step %c1 { | ||
| %fifo_tile = pto.tpop_from_aic {split = 1} | ||
| -> !pto.tile_buf<loc=vec, dtype=f32, rows=4, cols=16, v_row=4, v_col=16, blayout=row_major, slayout=none_box, fractal=512, pad=0> | ||
| pto.tmov ins(%fifo_tile : !pto.tile_buf<loc=vec, dtype=f32, rows=4, cols=16, v_row=4, v_col=16, blayout=row_major, slayout=none_box, fractal=512, pad=0>) outs(%vec_print : !pto.tile_buf<loc=vec, dtype=f32, rows=4, cols=16, v_row=4, v_col=16, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| pto.tprint ins(%vec_print : !pto.tile_buf<loc=vec, dtype=f32, rows=4, cols=16, v_row=4, v_col=16, blayout=row_major, slayout=none_box, fractal=512, pad=0>) | ||
| pto.tfree_from_aic {split = 1} | ||
| } | ||
| return | ||
| } | ||
| } | ||
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.
The accumulator tile
%acc_tileis allocated outside the loop, but its valid shape is modified inside the loop usingpto.set_validshape(line 54). Sinceset_validshapeupdates the tile metadata in-place, subsequent iterations of the loop will start with the modified valid shape (8x16 instead of 16x16). This will likely cause thepto.tmatmulin iterations 2-4 to only compute a partial result (8x16) instead of the full 16x16 multiplication performed in the first iteration. To ensure each iteration computes a full 16x16 result before shrinking the valid shape for pushing, thealloc_tilefor%acc_tileshould be moved inside the loop, similar to the implementation intest/samples/TPushTPop/test4/kernel.pto.