* Select Apple Metal 4.0.1 kernel; keep 4.0.0 u64 elsewhere
NVIDIA was ~37% slower on the 4.0.1 Metal-tuned kernel. Split
Poseidon2 kernels and pick by backend:
- Metal + SHADER_INT64: v4.0.1 u64
- other SHADER_INT64: v4.0.0 u64
- no SHADER_INT64: 32-bit fallback (same as 4.0.0)
CI uploads the Linux release binary as an artifact so we can
bench NVIDIA without building on the GPU box.
* Drop version numbers from GPU kernel labels
Log native-u64 vs native-u64 Apple Metal without tying
the strings to release tags.
Investigating reported seal submission failures. Root cause analysis:
the miner's job-id staleness chain (worker check, quic-loop filter,
node-side job_id compare) cannot mislabel a candidate — internal and
node job ids are updated atomically together. The remaining benign race
is node-side: a block-template rebuild (new pre_hash, same parent) does
not bump the node's job counter, so an in-flight seal mined on the old
template passes the job-id check and fails seal verification, logging
"Failed to submit seal". Fixing that belongs in the chain repo (bump the
job counter on template rebuild).
Miner-side hardening in this commit:
- gpu_cpu_parity is now a two-phase fuzzer. Phase 1 dumps FULL 512-bit
hashes for randomized (header, nonce) pairs via the real
midstate-resume datapath and verifies each against the canonical CPU
implementation, multi-threaded (defaults to 1M hashes, ~5s; 10M runs
in ~15s). Phase 2 fuzzes whole mining jobs with five profiles: random,
carry-edge starts (saturated low limbs), 2^256-boundary crossings,
impossible difficulty with exact hash-count assertion, and CPU-known
solutions to catch false negatives. Seeded and reproducible; also
asserts the submitted work bytes match the nonce.
Verified clean: 10M bulk hashes + ~1,500 seals across 6 seeds.
- miner-service re-verifies every candidate on the CPU (one hash) before
sending JobResult; an engine-produced invalid seal is never submitted
and is logged loudly instead.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Exploring a fully native Metal port of the mining kernel showed it runs
~16% faster than the wgpu path at equal batch size. Decomposing that gap:
~9% is naga's injected runtime bounds checks and forced loop bounding,
~1.5% is mulhi()-based multiplication (inexpressible in WGSL), <1% is
the constant address space; the rest is binding/codegen residue.
The dominant term is recoverable inside wgpu on every backend:
the engine now builds its pipelines with create_shader_module_trusted +
ShaderRuntimeChecks::unchecked(). This is sound for our shaders: sources
are compiled into the binary, every buffer access is a constant-bounded
loop index into fixed-size bindings the engine allocates itself, all
loops have static bounds, and both variants remain covered by the
dual-shader component suite and the CPU parity example.
Apple M4: 11.39 -> 12.34 MH/s at the default 1M batch (+8.3%), 11.74 ->
12.73 MH/s at 8M (+8.4%). Cumulative vs main: 4.4x.
New examples/trusted_hashrate.rs measures checked vs trusted on the same
shader and CPU-verifies results.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Three stacked optimizations, each verified bit-exact against the CPU
reference (qp-poseidon-core) by the dual-shader component suite and a
new GPU/CPU parity example:
- mining_u64.wgsl: native 64-bit Goldilocks arithmetic with plonky2-style
lazy reduction, used automatically when the adapter supports
SHADER_INT64 (all Apple Silicon, NVIDIA, modern AMD). mining.wgsl
remains the 32-bit fallback. (+50%)
- Midstate precompute: the first two of five sponge permutations absorb
the header and high nonce half, both constant per batch; they are now
computed once on the CPU (pow_core::mining_midstate) and resumed on
the GPU. Batches are clamped so nonces never carry past 2^256. (+77%)
- Lazy second squeeze: the first squeeze yields the most significant 256
bits of the hash, which decide hash-vs-target unless exactly equal to
the target's high half, so the common reject path skips the final
permutation. (+56%)
Apple M4 throughput: 2.81 -> 11.4 MH/s at the default 1M batch
(criterion large_range_1m/gpu: 355.8ms -> 86.3ms, -75.7%).
Also:
- Fix criterion GPU bench crash: thread-local worker resources are now
tagged with an engine id so multiple GpuEngines per process never mix
devices.
- Fix stale end-to-end test harness (6-binding layout) and run the full
component suite against both shader variants.
- New examples: hashrate, gpu_cpu_parity (25 jobs incl. 2^256-boundary
crossing), gpu_features.
- Add Apple M5 family GPU tiers.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* handle lost device correctly
* Update lib.rs
* allow-integrated flag otherwise exclude
* DeviceLost is a status
* Integrated GPU skipped when discrete init fails
* nits
* improve logging
* don't let the queue spill, just drain it
* move cancellation out of the shader, since it doesn't work
* simplify batch size mechanism, improve logs
* fmt
* address review items
* implement quic
* simpler names
* simplify worker logic
* simplify gpu configuration logic
* miner initiates and picks random start nonce
* remove mining service
* clean up logs and remove unused engines
* clean up metrics
* metrics fix
* shared worker pool, cpu driven cancellation
just 10x the gpu thru-put, no more batch-size on gpu
* fmt
* non-local git
* taplo derp
* fix the benches
* handle stale results correctly in gpu
* more accurate gpu hashrate
* fmt
* remove unused
* handle duplicate solutions, cli controls gpu cancel frequency
* put plonky2 back
* demote noisy log
* ok wgpu runs hello world
* toy hasher
* separate wgsl file
* kinda poseidon2
* test vectors
* closer
* a bit of debug
* closer
* sort of almost
* fixed gf_mul
* merge gf_mul back into mining, clean up tests
* fix bytes_to_field_elements
* linear layer fixed
* maybe better?
* mds tests
* cleanup debug output
* found gf_mul bug
* fixed gf_mul bug
* efficient sbox again
* mds matches
* cleanup
* test internal layer
* cleaner
* external linear passes
* external layer tests
* fixed the constants
* moar tests
* more cleaning
* actually test just internal
* fairly clean tests now
* removed another pointless test
* more cleanup
* gf_from_const tests
* testing
* fixed permutations
* double hash tests, but they fail
* moar tests!
* hash-twice works, thanks Gemini 3 Pro!
* gpu runs but doesn't mine
* better logging
* lock workers to gpu
* send target to gpu not difficulty
* fix verify_nonce
* double hash failures
* double hash matches
* tests pass and it mines now
* fix benches
* a bit faster now
* improved logging
* fix benches
* simplified gpu code
* further simplification
* a bit simpler
* slight simplification
* a bit faster
* dynamic thread allocation and work coarsening
* more benching
* faster
* faster
* faster
* clean up documentation
* a bit faster
* simplify
* simplify
* optimized mds
* almost par with cpu now
* fmt
* clippy
* support multiple gpus
* clippy
* unused
* fixed some logs
---------
Co-authored-by: Nikolaus Heger <nheger@gmail.com>
