aboutsummaryrefslogtreecommitdiff
path: root/src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp
diff options
context:
space:
mode:
authorMichael Tyler <michael.tyler@arm.com>2023-04-12 17:43:17 +0100
committermichael.tyler <michael.tyler@arm.com>2023-06-05 15:57:58 +0000
commit74921eee924625426429044decefe3673561b174 (patch)
tree654da1a95e3d42d6af8ad1ff27bb40d77b1fd8c5 /src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp
parentdf5d9878008be9b60586df97ebfff197abb5195e (diff)
downloadComputeLibrary-74921eee924625426429044decefe3673561b174.tar.gz
Update CPU kernel implementations and guard directives
Resolves COMPMID-6023 Change-Id: I868975d14c4f98af6716726feda22405a6a4c891 Signed-off-by: Michael Tyler <michael.tyler@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9686 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp')
-rw-r--r--src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp4
1 files changed, 2 insertions, 2 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp b/src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp
index 4c7bb71fb2..15545c24db 100644
--- a/src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp
+++ b/src/core/NEON/kernels/arm_gemm/indirect-interleaves/a64_interleave4_block16_u8_u8_summing.hpp
@@ -210,8 +210,8 @@ void interleave_block<4, 16, VLType::None, true>(
"uadalp v22.4s, v26.8h\n"
"uadalp v21.4s, v25.8h\n"
"addp v24.4s, v24.4s, v23.4s\n"
- "addp v23.4s, v22.4s, v21.4s\n"
- "addp v24.4s, v24.4s, v23.4s\n"
+ "addp v16.4s, v22.4s, v21.4s\n"
+ "addp v24.4s, v24.4s, v16.4s\n"
"add v24.4s, v24.4s, v20.4s\n"
"str q24, [%x[out_ptr], #0x0]\n"
"add %x[out_ptr], %x[out_ptr], #0x10\n"