diff options
Diffstat (limited to 'src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp')
| -rw-r--r-- | src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp b/src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp index 91b91d6668..a3080e7f29 100644 --- a/src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp +++ b/src/runtime/NEON/functions/NEGEMMAssemblyDispatch.cpp @@ -505,17 +505,17 @@ NEGEMMAssemblyDispatch::NEGEMMAssemblyDispatch(std::shared_ptr<IMemoryManager> m Status NEGEMMAssemblyDispatch::validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *d, const GEMMInfo &gemm_info) { - ARM_COMPUTE_UNUSED(gemm_info); - ARM_COMPUTE_UNUSED(c); + ARM_COMPUTE_UNUSED(gemm_info, c); ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(a, b, d); ARM_COMPUTE_RETURN_ERROR_ON_CPU_F16_UNSUPPORTED(a); + ARM_COMPUTE_RETURN_ERROR_ON_CPU_BF16_UNSUPPORTED(a); #ifndef __aarch64__ ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->element_size() == 1, "8bit integer types only supported for aarch64"); #endif /* __aarch64__ */ ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(a, 1, DataType::U8, DataType::QASYMM8, DataType::QASYMM8_SIGNED, DataType::S8, - DataType::F16, DataType::F32); + DataType::BFLOAT16, DataType::F16, DataType::F32); ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(b, 1, DataType::U8, DataType::QASYMM8, DataType::QASYMM8_SIGNED, DataType::QSYMM8_PER_CHANNEL, DataType::S8, - DataType::F16, DataType::F32); + DataType::BFLOAT16, DataType::F16, DataType::F32); if(is_data_type_quantized_per_channel(b->data_type())) { ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(a, 1, DataType::QASYMM8_SIGNED, DataType::S8); @@ -526,6 +526,7 @@ Status NEGEMMAssemblyDispatch::validate(const ITensorInfo *a, const ITensorInfo } ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::F32 && d->data_type() != DataType::F32, "Only F32 output supported for F32 input"); ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::F16 && d->data_type() != DataType::F16, "Only F16 output supported for F16 input"); + ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::BFLOAT16 && d->data_type() != DataType::F32, "Only F32 output supported for BFLOAT16 input"); ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::U8 && d->data_type() != DataType::U32, "Only U32 output supported for U8 input"); ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::S8 && d->data_type() != DataType::S32, "Only S32 output supported for S8 input"); ARM_COMPUTE_RETURN_ERROR_ON_MSG(a->data_type() == DataType::QASYMM8 && d->data_type() != DataType::QASYMM8, "Only QASYMM8 output supported for QASYMM8 input"); @@ -578,6 +579,11 @@ void NEGEMMAssemblyDispatch::configure(const ITensor *a, const ITensor *b, const } break; #endif /* __aarch64__ */ +#if defined(__ARM_FEATURE_BF16_VECTOR_ARITHMETIC) || defined(ARM_COMPUTE_FORCE_BF16) + case DataType::BFLOAT16: + create_arm_gemm<bfloat16, float>(_arm_gemm, _memory_group, a, b, c, d, act, gemm_info, _weights_manager); + break; +#endif /* defined(__ARM_FEATURE_BF16_VECTOR_ARITHMETIC) || defined(ARM_COMPUTE_FORCE_BF16) */ #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC case DataType::F16: create_arm_gemm<float16_t, float16_t>(_arm_gemm, _memory_group, a, b, c, d, act, gemm_info, _weights_manager); |