From 7fad9b1d00f3ee1488ba4038d1371f6ea219f8b7 Mon Sep 17 00:00:00 2001 From: Pablo Tello Date: Wed, 14 Mar 2018 17:55:27 +0000 Subject: 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 Reviewed-by: Anthony Barbier --- src/runtime/NEON/functions/NEGEMM.cpp | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'src/runtime/NEON/functions/NEGEMM.cpp') 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 -- cgit v1.2.1