static constexpr int FC_1_OUTPUTS = 32;
Layers::AffineTransform<TransformedFeatureDimensions, FC_0_OUTPUTS + 1> fc_0;
- Layers::ClippedReLU<FC_0_OUTPUTS> ac_0;
+ Layers::ClippedReLU<FC_0_OUTPUTS + 1> ac_0;
Layers::AffineTransform<FC_0_OUTPUTS, FC_1_OUTPUTS> fc_1;
Layers::ClippedReLU<FC_1_OUTPUTS> ac_1;
Layers::AffineTransform<FC_1_OUTPUTS, 1> fc_2;
alignas(CacheLineSize) decltype(fc_1)::OutputBuffer fc_1_out;
alignas(CacheLineSize) decltype(ac_1)::OutputBuffer ac_1_out;
alignas(CacheLineSize) decltype(fc_2)::OutputBuffer fc_2_out;
+
+ Buffer()
+ {
+ std::memset(this, 0, sizeof(*this));
+ }
};
#if defined(ALIGNAS_ON_STACK_VARIABLES_BROKEN)
- char bufferRaw[sizeof(Buffer) + alignment];
- char* bufferRawAligned = align_ptr_up<alignment>(&bufferRaw[0]);
- Buffer& buffer = *(new (bufferRawAligned) Buffer);
+ static thread_local char bufferRaw[sizeof(Buffer) + alignment];
+ static thread_local char* bufferRawAligned = align_ptr_up<alignment>(&bufferRaw[0]);
+ static thread_local Buffer& buffer = *(new (bufferRawAligned) Buffer);
#else
- alignas(alignment) Buffer buffer;
+ alignas(alignment) static thread_local Buffer buffer;
#endif
fc_0.propagate(transformedFeatures, buffer.fc_0_out);
std::int32_t fwdOut = int(buffer.fc_0_out[FC_0_OUTPUTS]) * (600*OutputScale) / (127*(1<<WeightScaleBits));
std::int32_t outputValue = buffer.fc_2_out[0] + fwdOut;
-#if defined(ALIGNAS_ON_STACK_VARIABLES_BROKEN)
- buffer.~Buffer();
-#endif
-
return outputValue;
}
};