berkus/ANE - ANE

Commit Graph

Author	SHA1	Message	Date
Alvaro GPT	7ea45c2fab	perf: vectorize CPU bottlenecks with vDSP and cblas - Vectorize adam_update with vDSP batch ops (stories_cpu_ops.h) Replaces scalar per-element loop with vDSP_vsmul/vsma/vsq/vdiv Expected ~3-4x faster for 2.4M parameter updates - Vectorize model_adam_step ADAM_UPDATE macro with vDSP (backward.h) Same batch ops pattern for the train.m model pipeline - Replace cpu_accum_dW with cblas_sgemm (backward.h) dW += dy^T @ x is a standard BLAS GEMM operation Expected 5-10x faster for weight gradient accumulation - Replace cpu_matmul_backward_dx with cblas_sgemm (backward.h) dx = dy @ W^T is also a standard BLAS GEMM - Add -framework Accelerate to train target (Makefile)	2026-03-03 20:47:03 +01:00
maderix	4d67db1bdb	stories110M: 12-layer ANE training with dashboard, 107ms/step - Scale to full stories110M (109M params, 12 layers) with real TinyStories data - vDSP-vectorized cross-entropy (110ms→14ms), NEON fp16 IO, async dW - TUI dashboard: loss curve, ANE/CPU power, CPU/memory graphs, text generation - Split into modular headers: config, io, mil, cpu_ops	2026-03-01 03:14:39 -08:00

Author

SHA1

Message

Date

Alvaro GPT

7ea45c2fab

perf: vectorize CPU bottlenecks with vDSP and cblas

- Vectorize adam_update with vDSP batch ops (stories_cpu_ops.h)
  Replaces scalar per-element loop with vDSP_vsmul/vsma/vsq/vdiv
  Expected ~3-4x faster for 2.4M parameter updates

- Vectorize model_adam_step ADAM_UPDATE macro with vDSP (backward.h)
  Same batch ops pattern for the train.m model pipeline

- Replace cpu_accum_dW with cblas_sgemm (backward.h)
  dW += dy^T @ x is a standard BLAS GEMM operation
  Expected 5-10x faster for weight gradient accumulation

- Replace cpu_matmul_backward_dx with cblas_sgemm (backward.h)
  dx = dy @ W^T is also a standard BLAS GEMM

- Add -framework Accelerate to train target (Makefile)

2026-03-03 20:47:03 +01:00

maderix

4d67db1bdb

stories110M: 12-layer ANE training with dashboard, 107ms/step

- Scale to full stories110M (109M params, 12 layers) with real TinyStories data
- vDSP-vectorized cross-entropy (110ms→14ms), NEON fp16 IO, async dW
- TUI dashboard: loss curve, ANE/CPU power, CPU/memory graphs, text generation
- Split into modular headers: config, io, mil, cpu_ops

2026-03-01 03:14:39 -08:00

2 Commits