Skip to content
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

Jump to bottom

Cascade matrix multiplication test with Peano #1856

Merged
merged 10 commits into from
Oct 19, 2024
Merged

Cascade matrix multiplication test with Peano #1856

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
a233273
[aievec] Resolve call ambiguity when using peano
jsetoain Oct 18, 2024
0d0cc30
Remaining to peano
jgmelber Oct 18, 2024
6bc3fb8
Apply suggestions from code review
jgmelber Oct 18, 2024
1af4e34
Merge branch 'main' into peano-ambiguous
jgmelber Oct 18, 2024
9e5980c
Constants to unsigned
jgmelber Oct 18, 2024
0335524
Constants to unsigned
jgmelber Oct 18, 2024
99990e8
Constants to unsigned
jgmelber Oct 18, 2024
18f8043
Merge branch 'main' into peano-ambiguous
jgmelber Oct 18, 2024
e845f53
Cascade MM test with peano
jgmelber Oct 19, 2024
d483386
Merge branch 'main' into cascade-peano
jgmelber Oct 19, 2024
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
8 changes: 4 additions & 4 deletions aie_kernels/aie2/cascade_mm.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ void matmul_scalar_cascade_put_only(T_in *a, T_in *b, T_out *c) {
running_sum += a[row * colA + i] * b[i * colB + col];
}
v16int32 v16 = undef_v16int32();
v16 = upd_elem(v16, 0, running_sum);
v16 = upd_elem(v16, 0, (int)running_sum);
put_mcd(v16);
}
}
Expand All @@ -51,7 +51,7 @@ void matmul_scalar_cascade_get_only(T_in *a, T_in *b, T_out *c) {
running_sum += a[row * colA + i] * b[i * colB + col];
}
v16int32 v16 = get_scd_v16int32();
running_sum += ext_elem(v16, 0);
running_sum += ext_elem(v16, 0U);
c[row * colB + col] += running_sum;
}
}
Expand All @@ -68,8 +68,8 @@ void matmul_scalar_cascade_put_get(T_in *a, T_in *b, T_out *c) {
running_sum += a[row * colA + i] * b[i * colB + col];
}
v16int32 v16 = get_scd_v16int32();
running_sum += ext_elem(v16, 0);
v16 = upd_elem(v16, 0, running_sum);
running_sum += ext_elem(v16, 0U);
v16 = upd_elem(v16, 0, (int)running_sum);
put_mcd(v16);
}
}
Expand Down
4 changes: 1 addition & 3 deletions programming_examples/basic/matrix_multiplication/cascade/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,8 +25,6 @@ target_suffix=${M}x${K}x${N}_${m}x${k}x${n}_${n_aie_cols}c

include ${srcdir}/../makefile-common

CHESS=true

build/mm_${m}x${k}x${n}.o: ${kernels_dir}/cascade_mm.cc
mkdir -p ${@D}
cd ${@D} && xchesscc_wrapper ${CHESSCCWRAP2_FLAGS} -DBIT_WIDTH=8 -DDIM_M=${m} -DDIM_K=${k} -DDIM_N=${n} -c $< -o ${@F}
cd ${@D} && ${PEANO_INSTALL_DIR}/bin/clang++ ${PEANOWRAP2_FLAGS} -fno-unroll-loops -DBIT_WIDTH=8 -DDIM_M=${m} -DDIM_K=${k} -DDIM_N=${n} -c $< -o ${@F}
2 changes: 1 addition & 1 deletion programming_examples/basic/matrix_multiplication/cascade/run_makefile.lit
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// (c) Copyright 2024 Advanced Micro Devices, Inc.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
// REQUIRES: ryzen_ai, chess
// REQUIRES: ryzen_ai, peano
//
// RUN: make -f %S/Makefile clean
// RUN: make -f %S/Makefile
Expand Down
Loading