mirror of
https://github.com/luxfi/crypto.git
synced 2026-07-27 01:54:50 +00:00
Hanzo AI
ddff44bbee
Adds the canonical runtime substrate selector for luxfi/crypto and decomplects
all per-algorithm GPU dispatchers behind it.
New `backend` API:
- Default()/SetDefault/Resolved()/IsGPU/IsCGo/IsVanilla — runtime selection
- CGoAvailable()/GPUAvailable() — real probes (was stubbed)
- Probe() returning Snapshot{Default, Resolved, CGo, GPU, Disabled,
GPUBackend, GPUDeviceCount, AccelVersion, Fallbacks}
- GPUDisabled() reads LUX_GPU_DISABLE operator kill switch
- RecordFallback(reason, where) atomic counter + one-shot log per reason,
low-cardinality FallbackReason enum (disabled / unsupported / probe_failed
/ backend_unavailable / abi_mismatch)
Dispatcher cleanup (one-and-one-way):
- All Resolve(gpuhost.Available(), false) call sites replaced with IsGPU()
- hqc switched to IsVanilla() (its accel batch wins for any non-vanilla pick)
- gpu/gpu.go now delegates entirely to backend (no separate session)
- internal/gpuhost dropped Snapshot()/Provenance — backend.Probe() canonical
Build tag policy: CGo is the only gate. There is no `gpu` build tag.
LLM.md documents the canonical surface.
96 lines
3.1 KiB
Go
96 lines
3.1 KiB
Go
// Copyright (C) 2019-2026, Lux Industries Inc. All rights reserved.
|
|
// See the file LICENSE for licensing terms.
|
|
|
|
package backend
|
|
|
|
import (
|
|
"log"
|
|
"sync"
|
|
"sync/atomic"
|
|
)
|
|
|
|
// FallbackReason is the low-cardinality enum recorded by RecordFallback.
|
|
// Keeping the set small and closed is deliberate — these values land in
|
|
// counter labels and log lines, and dynamic strings there are an
|
|
// observability anti-pattern (label explosion in Prometheus, log noise).
|
|
type FallbackReason uint32
|
|
|
|
const (
|
|
// FallbackDisabled — LUX_GPU_DISABLE is set; dispatcher routed to CPU.
|
|
FallbackDisabled FallbackReason = iota
|
|
// FallbackUnsupported — host driver reported no usable device
|
|
// (cudaGetDeviceCount == 0, Metal device init failed, etc.).
|
|
FallbackUnsupported
|
|
// FallbackProbeFailed — first-use byte-equality probe rejected
|
|
// the GPU path (e.g. FHE NTT (N,Q) convention mismatch).
|
|
FallbackProbeFailed
|
|
// FallbackBackendUnavailable — accel session itself failed to load
|
|
// or the linked plugin returned LUX_NOT_SUPPORTED.
|
|
FallbackBackendUnavailable
|
|
// FallbackABIMismatch — a Go init() ABI-size/offset check would have
|
|
// panicked, but a dispatcher recovered and downgraded to CPU. Should
|
|
// never fire in a released build; included for completeness.
|
|
FallbackABIMismatch
|
|
|
|
numFallbackReasons
|
|
)
|
|
|
|
// String returns the canonical low-cardinality reason name. These are
|
|
// the strings that appear in metrics labels and log lines.
|
|
func (r FallbackReason) String() string {
|
|
switch r {
|
|
case FallbackDisabled:
|
|
return "disabled"
|
|
case FallbackUnsupported:
|
|
return "unsupported"
|
|
case FallbackProbeFailed:
|
|
return "probe_failed"
|
|
case FallbackBackendUnavailable:
|
|
return "backend_unavailable"
|
|
case FallbackABIMismatch:
|
|
return "abi_mismatch"
|
|
default:
|
|
return "unknown"
|
|
}
|
|
}
|
|
|
|
var (
|
|
fallbackCounters [numFallbackReasons]uint64
|
|
fallbackLogOnce [numFallbackReasons]sync.Once
|
|
)
|
|
|
|
// RecordFallback increments the per-reason counter and emits exactly one
|
|
// log line per distinct (reason) over the lifetime of the process. The
|
|
// `where` string identifies the dispatcher site ("amm", "clob",
|
|
// "fhe_ntt") so an operator skimming the log can locate the surface
|
|
// that fell back without per-call spam.
|
|
func RecordFallback(reason FallbackReason, where string) {
|
|
if reason >= numFallbackReasons {
|
|
return
|
|
}
|
|
atomic.AddUint64(&fallbackCounters[reason], 1)
|
|
fallbackLogOnce[reason].Do(func() {
|
|
log.Printf("[crypto/backend] GPU fallback: reason=%s where=%s", reason, where)
|
|
})
|
|
}
|
|
|
|
// FallbackCounters returns a snapshot of the per-reason counters keyed
|
|
// by the canonical reason name. Suitable for Prometheus / Grafana with
|
|
// `reason` as a label.
|
|
func FallbackCounters() map[string]uint64 {
|
|
out := make(map[string]uint64, int(numFallbackReasons))
|
|
for i := FallbackReason(0); i < numFallbackReasons; i++ {
|
|
out[i.String()] = atomic.LoadUint64(&fallbackCounters[i])
|
|
}
|
|
return out
|
|
}
|
|
|
|
// resetFallbackForTest zeros every counter and reinitialises the
|
|
// once-per-reason log gate. Test-only; package-private.
|
|
func resetFallbackForTest() {
|
|
for i := range fallbackCounters {
|
|
atomic.StoreUint64(&fallbackCounters[i], 0)
|
|
fallbackLogOnce[i] = sync.Once{}
|
|
}
|
|
}
|