aboutsummaryrefslogtreecommitdiff
path: root/examples/gemm_tuner/cl_gemmlowp_reshaped.cpp
diff options
context:
space:
mode:
authorGeorgios Pinitas <georgios.pinitas@arm.com>2021-04-22 21:13:21 +0100
committerGeorgios Pinitas <georgios.pinitas@arm.com>2021-05-18 14:48:39 +0000
commit856f66e6c61b77d03f754cd0fa8439891f0e4aca (patch)
treef9379cd0853ac407109e54c3d53b385ceee066c2 /examples/gemm_tuner/cl_gemmlowp_reshaped.cpp
parent37f4b2ef1ea225a90ccb563fcb2c08f8fb0fb5d5 (diff)
downloadComputeLibrary-856f66e6c61b77d03f754cd0fa8439891f0e4aca.tar.gz
Port CLGEMM to memory injecting interface
Moves the following kernels: - CLGEMMMatrixMultiplyKernel - CLGEMMMatrixMultiplyNativeKernel - CLGEMMMatrixMultipluReshapedKernel - CLGEMMMatrixMultiplyReshapedOnlyRHSKernel Moves the following functions - CLGEMM Introduces facilities to easy handling of auxiliary temporary buffers under then new run interface. Such are: - CLAuxTensorHandler: That allows wrapping of workspace buffers memory to CLBuffer objects - Ability to inject TensorInfo to allocator without transferring ownership. This reduce the copy overhead if needed. Resolves: COMPMID-4188 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I7055435d831b05b749b26302082e4ac45f26dfb0 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5498 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'examples/gemm_tuner/cl_gemmlowp_reshaped.cpp')
-rw-r--r--examples/gemm_tuner/cl_gemmlowp_reshaped.cpp11
1 files changed, 7 insertions, 4 deletions
diff --git a/examples/gemm_tuner/cl_gemmlowp_reshaped.cpp b/examples/gemm_tuner/cl_gemmlowp_reshaped.cpp
index 5b81963752..3d3f7fef1e 100644
--- a/examples/gemm_tuner/cl_gemmlowp_reshaped.cpp
+++ b/examples/gemm_tuner/cl_gemmlowp_reshaped.cpp
@@ -34,7 +34,7 @@
#include "examples/gemm_tuner/CommonGemmExampleOptions.h"
#include "examples/gemm_tuner/GemmTunerHelpers.h"
#include "src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h"
-#include "src/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.h"
+#include "src/core/gpu/cl/kernels/ClGemmReshapeLhsMatrixKernel.h"
#include "tests/CL/Helper.h"
#include "utils/Utils.h"
#include "utils/command_line/CommandLineOptions.h"
@@ -43,6 +43,7 @@
#include <cstdlib>
using namespace arm_compute;
+using namespace arm_compute::opencl::kernels;
using namespace utils;
using namespace arm_compute::misc::shape_calculator;
using namespace gemm_tuner;
@@ -167,7 +168,7 @@ GemmConfigs consume_gemm_configs(const GemmConfigOptions &options)
} // namespace
-using CLGEMMReshapeLHSMatrix = test::CLSynthetizeFunction<CLGEMMReshapeLHSMatrixKernel>;
+using CLGEMMReshapeLHSMatrix = test::CLSynthetizeOperator<ClGemmReshapeLhsMatrixKernel>;
using CLGEMMLowpMatrixMultiplyReshaped = test::CLSynthetizeFunction<CLGEMMLowpMatrixMultiplyReshapedKernel>;
class CLGEMMLowpMatrixMultiplyReshapedExample : public Example
@@ -279,7 +280,7 @@ public:
}
// Configure functions
- reshape_lhs.configure(&lhs, &lhs_reshaped, lhs_info);
+ reshape_lhs.configure(lhs.info(), lhs_reshaped.info(), lhs_info);
gemm.configure(&lhs_reshaped, &rhs_reshaped, &dst, lhs_info, rhs_info, gemm_info);
@@ -294,7 +295,9 @@ public:
}
void do_run() override
{
- reshape_lhs.run();
+ ITensorPack reshape_lsh_pack({ { ACL_SRC, &lhs }, { ACL_DST, &lhs_reshaped } });
+ reshape_lhs.run(reshape_lsh_pack);
+
gemm.run();
// Make sure all the OpenCL jobs are done executing: