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.
63 lines
1.2 KiB
Go
63 lines
1.2 KiB
Go
// Copyright (C) 2020-2026, Lux Industries Inc. All rights reserved.
|
|
// See the file LICENSE for licensing terms.
|
|
|
|
package sha256
|
|
|
|
import (
|
|
"github.com/luxfi/accel"
|
|
"github.com/luxfi/crypto/backend"
|
|
"github.com/luxfi/crypto/internal/gpuhost"
|
|
)
|
|
|
|
func batchGPU(inputs [][]byte, out [][Size]byte) (bool, error) {
|
|
if !backend.IsGPU() {
|
|
return false, nil
|
|
}
|
|
sess := gpuhost.Session()
|
|
if sess == nil {
|
|
return false, nil
|
|
}
|
|
|
|
width := 0
|
|
for _, in := range inputs {
|
|
if len(in) > width {
|
|
width = len(in)
|
|
}
|
|
}
|
|
if width == 0 {
|
|
empty := Sum256(nil)
|
|
for i := range out {
|
|
out[i] = empty
|
|
}
|
|
return true, nil
|
|
}
|
|
|
|
flat := make([]uint8, len(inputs)*width)
|
|
for i, in := range inputs {
|
|
copy(flat[i*width:(i+1)*width], in)
|
|
}
|
|
inT, err := accel.NewTensorWithData[uint8](sess, []int{len(inputs), width}, flat)
|
|
if err != nil {
|
|
return false, nil
|
|
}
|
|
defer inT.Close()
|
|
|
|
outT, err := accel.NewTensor[uint8](sess, []int{len(inputs), Size})
|
|
if err != nil {
|
|
return false, nil
|
|
}
|
|
defer outT.Close()
|
|
|
|
if err := sess.Crypto().SHA256(inT.Untyped(), outT.Untyped()); err != nil {
|
|
return false, nil
|
|
}
|
|
bytes, err := outT.ToSlice()
|
|
if err != nil {
|
|
return false, nil
|
|
}
|
|
for i := range out {
|
|
copy(out[i][:], bytes[i*Size:(i+1)*Size])
|
|
}
|
|
return true, nil
|
|
}
|