aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/dynamic_fusion
diff options
context:
space:
mode:
authorRamy Elgammal <ramy.elgammal@arm.com>2022-11-30 16:23:10 +0000
committerRamy Elgammal <ramy.elgammal@arm.com>2022-12-09 13:57:49 +0000
commitdf6a3b05842a98702437347ca269138ccd55f852 (patch)
treed38b3cc83acfa0aa492b953b6a3c06104e0d76fc /arm_compute/dynamic_fusion
parent86689cdd95f634fb374f3875f62a4cb3408e1699 (diff)
downloadComputeLibrary-df6a3b05842a98702437347ca269138ccd55f852.tar.gz
Use heuristics for setting dynamic fusion direct conv2d tile sizes
Resolves: COMPMID-5735 Change-Id: I9958413b69c5052cfa205dd0e9457cc4953aaf35 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/474818 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8724 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/dynamic_fusion')
-rw-r--r--arm_compute/dynamic_fusion/sketch/gpu/operators/GpuAdd.h6
1 files changed, 1 insertions, 5 deletions
diff --git a/arm_compute/dynamic_fusion/sketch/gpu/operators/GpuAdd.h b/arm_compute/dynamic_fusion/sketch/gpu/operators/GpuAdd.h
index df3177867f..833f341b2f 100644
--- a/arm_compute/dynamic_fusion/sketch/gpu/operators/GpuAdd.h
+++ b/arm_compute/dynamic_fusion/sketch/gpu/operators/GpuAdd.h
@@ -68,11 +68,7 @@ public:
ITensorInfo *rhs,
ITensorInfo *dst);
/** Check if the operator configuration is supported, irrespective of fusion
- *
- * @param[in] context Workload context within which the operator is running
- * @param[in] lhs Left hand side tensor info. Data types supported: U8/S16/S32/F16/F32.
- * @param[in] rhs Right hand side tensor info. Data types supported: U8/S16/S32/F16/F32.
- * @param[out] dst Destination tensor info. Data types supported: U8/S16/S32/F16/F32. If an uninitialized ITensorInfo is passed in, it will be auto-initialized
+ * Similar to @ref GpuAdd::create_op()
*/
static Status is_supported_op(const GpuWorkloadContext &context,
const ITensorInfo *lhs,