aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/cl_kernels/gemm.cl
diff options
context:
space:
mode:
authorMoritz Pflanzer <moritz.pflanzer@arm.com>2017-07-21 15:55:28 +0100
committerAnthony Barbier <anthony.barbier@arm.com>2018-09-17 14:16:42 +0100
commite49e26613264842f91d29a32be3a226a0d6adb42 (patch)
tree78d88bded1f178d06b9dbfe3950ba716ef229599 /src/core/CL/cl_kernels/gemm.cl
parent27b386cb7596542a3296c32e41f7a5168b4d53be (diff)
downloadComputeLibrary-e49e26613264842f91d29a32be3a226a0d6adb42.tar.gz
COMPMID-415: Use half_float library for F16
3RDPARTY_UPDATE Change-Id: Iee572e18d5b1df71300d738cc8690f49d7203d5c Reviewed-on: http://mpd-gerrit.cambridge.arm.com/81353 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/gemm.cl')
-rw-r--r--src/core/CL/cl_kernels/gemm.cl2
1 files changed, 1 insertions, 1 deletions
diff --git a/src/core/CL/cl_kernels/gemm.cl b/src/core/CL/cl_kernels/gemm.cl
index db15720ad0..00c73e7be0 100644
--- a/src/core/CL/cl_kernels/gemm.cl
+++ b/src/core/CL/cl_kernels/gemm.cl
@@ -754,7 +754,7 @@ __kernel void gemm_mm_f16(IMAGE_DECLARATION(src0),
half8 c20 = 0.0f;
half8 c30 = 0.0f;
- for(; src_addr.s1 <= (end_row_mtx_b - 8); src_addr += (int2)(8, 16))
+ for(; src_addr.s1 <= (end_row_mtx_b - 16); src_addr += (int2)(8, 16))
{
/* Load values from matrix A (interleaved) and matrix B (transposed) */
half4 a0 = vload4(0, ((__global half *)src0_ptr) + src_addr.s0);