Measured on this machine's actual CPU at the real 760-wide geometry, through a
real DLL boundary (an earlier harness #included the .cpp and the fast-math
build hoisted the timing loop, reporting a flat ~4us for shapes 8x apart).
Every hot kernel is a floating-point reduction. Under the default /fp:precise
MSVC may not reassociate one, so it cannot vectorize one - the dot product was
scalar mulsd/addsd through a single accumulator. Forward pass measured
1.1-1.9 GFLOP/s precise vs 1.7-2.8 GFLOP/s fast, and the same three
neurons*inputs loops (forward, hidden gradient, weight-gradient accumulate)
dominate an era.
batch_accum_check passes on both builds with identical output to every digit
it prints, including the 5-decade optimizer scale-invariance sweep. The
deploy-time CPU-vs-MQL5 self-check tolerance is 1.0e-3, ~11 orders looser than
fast-math drift.
/arch:AVX2 is now explicitly forbidden in the script with the reason. This CPU
is an Ivy Bridge-EP Xeon: AVX yes, AVX2/FMA no. An AVX2 build faults on every
kernel, SehCallFn swallows it per dispatch, buffers are never written, and
every shape takes a flat ~5us - which benchmarks as a 250x speedup until you
check that the outputs are all zero. /arch:AVX alone was measured and bought
nothing; these loops are memory-bound and Ivy Bridge splits 256-bit loads
into 2x128 anyway.
Requires rebuilding WarriorCPU.dll (build_cpu.bat) - the .ex5 is unchanged.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Add type checks to correctly cast `CNeuronBaseOCL` objects in gradient clipping,
softmax evaluation, and `backProp`/`backPropDfa` loops. Previously, all neurons
were assumed to be `CNeuronBase`, causing invalid pointer casts and incorrect
gradient/output access for OpenCL layers. This ensures proper support for both
CPU and OCL neuron implementations.
- Define MAX_WEIGHT constant (1.0e6) for weight limits in clusters
- Remove redundant barrier from FeedForward kernel (prevents sync issues)
- Port FeedForwardProof and CalcInputGradientProof kernels for max-pooling (no weights, sliding max)
- Port FeedForwardConv kernel for convolution layers (shared weights, multiple output channels)
- Remove unused code and refactor signal condition logic (CSignalPAI)
