diff options
author | Pablo Tello <pablo.tello@arm.com> | 2018-03-14 17:55:27 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:49:16 +0000 |
commit | 7fad9b1d00f3ee1488ba4038d1371f6ea219f8b7 (patch) | |
tree | ded71e1cfa8e0c085f8bce5dfc26a99786d60e52 /src/runtime/NEON/functions/NEGEMM.cpp | |
parent | 1562be3e8a449360a90af75f6f1481a30d41be75 (diff) | |
download | ComputeLibrary-7fad9b1d00f3ee1488ba4038d1371f6ea219f8b7.tar.gz |
COMPMID-1021: CPUInfo refactoring.
Removed CPUTarget in favor of the CPUModel type.
CPUInfo now holds a vector of N CPUs.
CPUInfo autoinitialise upon construction with 1 GENERIC CPU.
CPPScheduler fills CPUInfo's vector upon construction (runtime).
IScheduler has a single CPUInfo obj and ThreadInfo always gets a pointer to it (avoid copying the vector)
Change-Id: I30f293258c959c87f6bac5eac8b963beb6a4d365
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/124626
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/runtime/NEON/functions/NEGEMM.cpp')
-rw-r--r-- | src/runtime/NEON/functions/NEGEMM.cpp | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/src/runtime/NEON/functions/NEGEMM.cpp b/src/runtime/NEON/functions/NEGEMM.cpp index c8cba8a174..18e6e919c3 100644 --- a/src/runtime/NEON/functions/NEGEMM.cpp +++ b/src/runtime/NEON/functions/NEGEMM.cpp @@ -65,7 +65,8 @@ void NEGEMM::configure(const ITensor *a, const ITensor *b, const ITensor *c, ITe // Check if we need to reshape the matrix B only on the first run _reshape_b_only_on_first_run = gemm_info.reshape_b_only_on_first_run(); _run_vector_matrix_multiplication = a->info()->dimension(1) < 2; - const bool run_optimised = setup_assembly_kernel(a, b, c, d, alpha, beta, _workspace, _memory_group, _asm_glue); + + const bool run_optimised = a->info()->data_type() == DataType::F32 && (c == nullptr || beta == 0.f) && setup_assembly_kernel(a, b, d, alpha, beta, _workspace, _memory_group, _asm_glue); // Check if the first input tensor is a vector. // If so, all the kernels for reshaping the tensors can be skipped |