From 2b6ebfe4270b06b09e45f306e8384950aeca7e4e Mon Sep 17 00:00:00 2001
From: Ramy Elgammal <ramy.elgammal@arm.com>
Date: Thu, 9 Mar 2023 21:15:37 +0000
Subject: Implement OpenCL MatMul for Lhs NT Rhs T/NT FP32/16

 - Implement ClNativeMatMulKernel class
 - Implement opencl kernel for LHS non-transposed and RHS non-transposed
 - Implement opencl kernel for LHS non-transposed and RHS transposed
 - Add test fixture and dataset for matmul
 - Implement transpose_tensor() for reference implementation to transpose high dimensional tensors

Resolves: COMPMID-5944, COMPMID-5951

Co-authored-by: Gunes Bayir <gunes.bayir@arm.com>
Co-authored-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: I1d5b8978f41be27baddb3153ade880472141573f
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9333
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
---
 filelist.json | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'filelist.json')

diff --git a/filelist.json b/filelist.json
index 1b0d07bc42..f858c6a29f 100644
--- a/filelist.json
+++ b/filelist.json
@@ -509,6 +509,13 @@
         ]
       }
     },
+    "MatMul": {
+      "files": {
+        "common": [
+          "src/gpu/cl/kernels/ClNativeMatMulKernel.cpp"
+        ]
+      }
+    },
     "GenerateProposals": {
       "deps": [ "BoundingBoxTransform", "Dequantize", "Pad", "Permute", "Quantize", "Reshape" ],
       "files": {
-- 
cgit v1.2.1