Skip to content

Unify pragmas mm kernel #2457

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.

Sign up for GitHub

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
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Unify pragmas mm kernel #2457

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
76c190e
Unify pragmas for aie2p/mm.cc
L-roro Jul 30, 2025
e30496f
Remove accidental line indent
L-roro Jul 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions aie_kernels/aie2p/mm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
#define REL_WRITE 0
#define REL_READ 1

#include "../aie_kernel_utils.h"
#include <aie_api/aie.hpp>

#include "zero.cc"
Expand Down Expand Up @@ -74,14 +75,15 @@ static inline void matmul_vectorized_2x2_mmul(const T_in *__restrict pA,

event0();

for (unsigned z = 0; z < rowA; z += 2)
chess_prepare_for_pipelining chess_loop_range(4, ) {
AIE_PREPARE_FOR_PIPELINING
AIE_LOOP_MIN_ITERATION_COUNT(4)
for (unsigned z = 0; z < rowA; z += 2) {
T_out *__restrict pC1 = pC + (z * colB) * MMUL::size_C;
T_out *__restrict pC2 = pC + ((z + 1) * colB) * MMUL::size_C;

for (unsigned j = 0; j < colB; j += 2)
#ifdef OPT_PERF_ENABLED
chess_flatten_loop
AIE_LOOP_FLATTEN
#endif
{
const T_in *__restrict pA1 = pA + (z * colA) * MMUL::size_A;
Expand Down Expand Up @@ -119,7 +121,7 @@ static inline void matmul_vectorized_2x2_mmul(const T_in *__restrict pA,

for (unsigned i = 0; i < colA; ++i)
#ifdef OPT_PERF_ENABLED
chess_flatten_loop
AIE_LOOP_FLATTEN
#endif
{
A0 = aie::load_v<MMUL::size_A>(pA1);
Expand Down Expand Up @@ -437,4 +439,4 @@ extern "C" {
combos(matmul_vectorized_c_func) combos(matmul_scalar_c_func)
combos(zero_vectorized_c_func) combos(zero_scalar_c_func)

} // extern "C"
} // extern "C"
Loading