mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
c5ec2f707a
## Summary
- Add `generate_identity_sequences<N>()` helper that returns
`Tuple<Sequence<0>, Sequence<1>, ..., Sequence<N-1>>`
- Replace lambdas with named functors in `transform_tensor_descriptor`
- Add `unpack_and_merge_sequences` helper functor
- Reduces `transform_tensor_descriptor` instantiations from 388 to 32
(92% reduction)
## Motivation
Multiple call sites use `generate_tuple([](auto i) { return
Sequence<i>{}; }, Number<N>{})` pattern. A named helper reduces lambda
instantiations.
Additionally, each lambda in `transform_tensor_descriptor` creates a
unique closure type, causing the function to be instantiated separately
for every call site. Named functors share a single type, so the compiler
reuses the same instantiation.
## Changes
### Part 1: generate_identity_sequences helper
- Replaces common lambda pattern for generating identity sequences
- Each lambda expression creates a unique closure type, causing separate
template instantiations at every call site
- Named helper shares a single type across all uses
### Part 2: Named functors in transform_tensor_descriptor
- Add `unpack_and_merge_sequences` helper to replace lambda in
`GetNumOfHiddenDimension`
- Use `generate_identity_sequences` in `matrix_padder.hpp`
## Test Plan
- [x] Added 7 unit tests:
- 4 tests for `generate_identity_sequences`
- 3 tests for `unpack_and_merge_sequences`
- [ ] Waiting for full CI
## Related PRs
This PR merges the functionality from:
- ROCm/composable_kernel#3588 (generate_identity_sequences helper)
- ROCm/composable_kernel#3589 (Named functors in
transform_tensor_descriptor)
Part of PR stack for issue #4229 (Reduce CK/CKTile Build Times)
**Note:** This PR supersedes #4283, ROCm/composable_kernel#3588 and
ROCm/composable_kernel#3589, which can be closed once this is merged.
---
🔁 Imported from
[ROCm/composable_kernel#3628](https://github.com/ROCm/composable_kernel/pull/3628)
🧑💻 Originally authored by @tenpercent
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
66 lines
2.3 KiB
C++
66 lines
2.3 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#include <gtest/gtest.h>
|
|
#include "ck/utility/sequence_helper.hpp"
|
|
#include "ck/utility/tuple_helper.hpp"
|
|
|
|
using namespace ck;
|
|
|
|
// Tests for generate_identity_sequences (PR #3588)
|
|
TEST(GenerateIdentitySequences, Size5)
|
|
{
|
|
auto result = generate_identity_sequences(Number<5>{});
|
|
auto expected =
|
|
make_tuple(Sequence<0>{}, Sequence<1>{}, Sequence<2>{}, Sequence<3>{}, Sequence<4>{});
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|
|
|
|
TEST(GenerateIdentitySequences, Size1)
|
|
{
|
|
auto result = generate_identity_sequences(Number<1>{});
|
|
auto expected = make_tuple(Sequence<0>{});
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|
|
|
|
TEST(GenerateIdentitySequences, Size0)
|
|
{
|
|
auto result = generate_identity_sequences(Number<0>{});
|
|
auto expected = make_tuple();
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|
|
|
|
TEST(GenerateIdentitySequences, WithNumber)
|
|
{
|
|
constexpr auto result = generate_identity_sequences(Number<3>{});
|
|
EXPECT_EQ(result.Size(), 3);
|
|
EXPECT_TRUE((is_same<decltype(result.At(Number<0>{})), const Sequence<0>&>::value));
|
|
EXPECT_TRUE((is_same<decltype(result.At(Number<1>{})), const Sequence<1>&>::value));
|
|
EXPECT_TRUE((is_same<decltype(result.At(Number<2>{})), const Sequence<2>&>::value));
|
|
}
|
|
|
|
// Tests for unpack_and_merge_sequences (PR #3589)
|
|
TEST(UnpackAndMergeSequences, MergeMultipleSequences)
|
|
{
|
|
auto input = make_tuple(Sequence<1, 2>{}, Sequence<3, 4>{}, Sequence<5, 6>{});
|
|
auto result = unpack_and_merge_sequences(input);
|
|
auto expected = Sequence<1, 2, 3, 4, 5, 6>{};
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|
|
|
|
TEST(UnpackAndMergeSequences, SingleSequence)
|
|
{
|
|
auto input = make_tuple(Sequence<10, 20, 30>{});
|
|
auto result = unpack_and_merge_sequences(input);
|
|
auto expected = Sequence<10, 20, 30>{};
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|
|
|
|
TEST(UnpackAndMergeSequences, TwoSequences)
|
|
{
|
|
auto input = make_tuple(Sequence<100>{}, Sequence<200, 300>{});
|
|
auto result = unpack_and_merge_sequences(input);
|
|
auto expected = Sequence<100, 200, 300>{};
|
|
EXPECT_TRUE((is_same<decltype(result), decltype(expected)>::value));
|
|
}
|