Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT
Implement OpenCL kernels for batched Matrix Multiplication for the quantized data types QASYMM8 and QASYMM8_SIGNED.
Quantized MatMul is supported with the following MatMul attributes:
* adj_x = false, adj_y = false
* adj_x = true, adj_y = false
We consider native format kernels only. In other words, no reshaping of the operand matrices is done.
Resolves: COMPMID-5921, COMPMID-5922
Change-Id: I99e0f68054a2bd635c60ec2641acc2e7ff398473
Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com>
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9435
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/gpu/cl/kernels/ClMatMulLowpNativeKernel.h b/src/gpu/cl/kernels/ClMatMulLowpNativeKernel.h
new file mode 100644
index 0000000..13a33fb
--- /dev/null
+++ b/src/gpu/cl/kernels/ClMatMulLowpNativeKernel.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (c) 2023 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ACL_SRC_GPU_CL_KERNELS_CLMATMULLOWPNATIVEKERNEL
+#define ACL_SRC_GPU_CL_KERNELS_CLMATMULLOWPNATIVEKERNEL
+
+#include "src/core/common/Macros.h"
+#include "src/gpu/cl/ClCompileContext.h"
+#include "src/gpu/cl/IClKernel.h"
+
+namespace arm_compute
+{
+// Forward declerations
+struct MatMulKernelInfo;
+namespace opencl
+{
+namespace kernels
+{
+class ClMatMulLowpNativeKernel : public IClKernel
+{
+public:
+ ClMatMulLowpNativeKernel();
+ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClMatMulLowpNativeKernel);
+ /** Initialise the kernel's input and output.
+ *
+ * @param[in] compile_context The compile context to be used.
+ * @param[in] lhs Input tensor for the LHS matrix. Data type supported: QASYMM8_SIGNED/QASYMM8.
+ * Dimensions above 2 are collapsed onto dimension 2 and represent the batch.
+ * @param[in] rhs Input tensor for the RHS matrix. Data type supported: same as @p lhs.
+ * Dimensions above 2 are collapsed onto dimension 2 and represent the batch.
+ * @param[out] output Output tensor info. Data type supported: same as @p lhs
+ * @param[in] matmul_info Attributes for Batch MatMul Kernel
+ */
+ void configure(const ClCompileContext &compile_context, ITensorInfo *lhs, ITensorInfo *rhs, ITensorInfo *output, const MatMulKernelInfo &matmul_info);
+ /** Static function to check if given info will lead to a valid configuration
+ *
+ * Similar to @ref ClMatMulLowpNativeKernel::configure()
+ *
+ * @return a status
+ */
+ static Status validate(const ITensorInfo *lhs, const ITensorInfo *rhs, const ITensorInfo *output, const MatMulKernelInfo &matmul_info);
+
+ // Inherited methods overridden:
+ void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
+};
+} // namespace kernels
+} // namespace opencl
+} // namespace arm_compute
+#endif /* ACL_SRC_GPU_CL_KERNELS_CLMATMULLOWPNATIVEKERNEL */