Add scalar reduction codegen schedule #1284
Open
Conversation
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
Pokemons386
force-pushed
the
scalar_reduction
branch
from
5009a3f to
6fc8883
Compare
Yancey1989
force-pushed
the
scalar_reduction
branch
from
aee2026 to
81aa949
Compare
Yancey1989
changed the title
eedalong
approved these changes
Mar 22, 2024
yunzhongOvO
reviewed
Mar 22, 2024
| * shm[tid] += inputs[j] + inputs[j + block_size]; | ||
| * } | ||
| * __syncthreads(); | ||
| * for (int stride = block_size / 2; stride > 0; stride /= 2) { |
There was a problem hiding this comment.
here missing the logic of warpReduce.
| } | ||
| { | ||
| SmallVector<Value, 4> init_values = {}; | ||
| for (int stride = 128; stride > 16; stride /= 2) { |
There was a problem hiding this comment.
warp_size=32, it is better to set the stop condition to stride > 32
| b.create<memref::LoadOp>(loc, shared_mem_map[root_op], strid_tid); | ||
| Value sum = accum_factory[idx](shm_val_1, shm_val_2); | ||
| b.create<memref::StoreOp>(loc, sum, shared_mem_map[root_op], tid); | ||
| b.create<gpu::BarrierOp>(loc); |
There was a problem hiding this comment.
BarrierOp is not necessary, threads in a warp are synchronized all the time.
There was a problem hiding this comment.
I rewrite the wrap reduction section with shuffle inst, and will update this PR later.
| /*hasElseRegion*/ false); | ||
| b.setInsertionPointToStart(&if_tid_valid_op.getThenRegion().front()); | ||
| SmallVector<Value, 4> yield_values; | ||
| for (int stride = 16; stride > 0; stride /= 2) { |
There was a problem hiding this comment.
Start with stride = 32.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
add scalar-reduction codegen template , the algorithm comes from https://developer.download.nvidia.com/assets/cuda/files/reduction.pdf