berkus
/
ANE
mirror of https://github.com/maderix/ANE.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
6 Commits 3 Branches 0 Tags 1.1 MiB
Commit Graph

6 Commits

Author SHA1 Message Date
manni07 ad119aed46 fix: address CRIT security findings (CRIT-01 to CRIT-04) 
- CRIT-01: dlopen() return check + NSClassFromString validation in ane_init()
           (ane_runtime.h + stories_config.h); g_ane_ok / g_ane_ok_large flag
           only set when all private classes load successfully; stories_config.h
           gets re-entry guard (g_ane_init_done) that was previously missing
- CRIT-02: g_ane_ok guard in ane_compile() and compile_kern_mil_w(); NULL check
           for inMemoryModel after inMemoryModelWithDescriptor: — prevents crash
           when API call returns nil (ane_runtime.h, stories_io.h)
- CRIT-03: Validate fread() return for critical config/header reads to prevent
           garbage malloc() sizes; fopen() NULL check in save_checkpoint();
           design decision documented (model.h, train_large.m)
- CRIT-04: int -> size_t in build_blob*/build_blob_t/build_blob_fp16; calloc()
           NULL checks added; (size_t) cast in malloc() size calculations to
           prevent signed integer overflow UB (stories_io.h, model.h)

Simulation: 3 iterations, overall score 96.15% (all criteria >= 95%)
ref: docs/reports/security-audit-2026-03-02.md
 2026-03-02 22:14:51 +01:00
Manjeet Singh 893f58e725
Merge pull request #2 from m0at/m5-maximized 
ANE probe tests + training telemetry for M5 optimization
 2026-03-02 14:57:12 +05:30
m0at 184b182bfc Add M5 probe results: weight reload fails, all QoS work, chaining API found 
Key findings from running all 4 probes on Apple M5:

- Weight reload (unload+load after file overwrite) does NOT work — weights
  are baked at compile time, output is identical regardless of file changes
- weightsBuffer IOSurface parameter also does not override compiled weights
- All QoS values 0-63 work, no measurable latency difference (~0.07ms/eval)
- _ANEPerformanceStats has hwExecutionTime (ns) + perfCounterData
- _ANEChainingRequest supports loopback execution (output→input chaining)
- _ANEClient has real-time eval path and chaining preparation methods
- procedureIndex 0-15 all succeed on single-procedure models

Fixed probe tests to use fp32 I/O with cast (matching inmem_peak pattern)
and 64+ channel kernels (ANE minimum size requirement).

Full analysis in training/m5result.md.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 23:16:38 -08:00
m0at 40d3f45631 Add ANE probe tests and training telemetry for M5 optimization 
Four standalone probe tests to characterize the M5 ANE:
- test_weight_reload: Can weights be hot-swapped via unload+load without recompilation?
- test_perf_stats: Enumerate _ANEPerformanceStats methods/properties and hardware counters
- test_qos_sweep: Measure compile/load/eval latency across QoS 0-63
- test_ane_advanced: Probe SharedEvents, weightsBuffer IOSurface, procedureIndex, VirtualClient

Training telemetry (train_large.m):
- JSON lines to stderr with per-step timing breakdown and per-batch TFLOPS metrics
- Enables external monitoring tools to visualize ANE utilization in real-time

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 22:54:58 -08:00
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
maderix f213c8db68 Initial release 2026-02-28 00:22:06 -08:00