mirror of
https://github.com/luxfi/zap.git
synced 2026-10-30 15:04:16 +00:00
zeekay
d14b104790
Three orthogonal additions, one wire format. v2 package — generic ad-hoc schema dispatch (~/work/lux/zap/v2): - README + IMPOSSIBILITY + BENCH_RESULTS document the v1↔v2 split. - builder/field/iter/list/pool/registry/schema/view + codegen package emit v1-equivalent fast paths from declarative .zap sources. - _compile_fail_test/ + examples/ cover negative and positive cases. - v2_test.go exercises the generic dispatch path. - doc.go in v1 marks v1 deprecated for *new* schema authoring; existing v1 buffers stay parseable by both v1 and v2. bufpool — pooled read slabs (bufpool.go + bufpool_test.go): - Message gains optional *bufRef; Release() returns the slab to its pool when sourced from the pooled read path, GC-managed otherwise. - ParseHeader returns (data, rootOffset) without allocating *Message, used by zapv2 to avoid two allocations per parse. - bench_read_test.go + node_quic_stream_test.go cover both paths. Transport allocator + UMA/RDMA cgo (transport/*): - Transport.Caps()/Buffer interface: capability + slab-typed buffer contract. Bytes() vs DevicePtr() decoupled so UMA and GPUDirect can share the same call surface. - DPDK PMD + GPUDirect RDMA + CUDA UMA real cgo backends gated behind build tags; stub paths remain default on darwin / non-Linux. - transport_test.go covers Caps reporting + Buffer lifecycle on the default transport. LLM.md + go.mod follow the additions.
25 lines
832 B
Go
25 lines
832 B
Go
// Copyright (C) 2025-2026, Lux Industries Inc. All rights reserved.
|
|
// See the file LICENSE for licensing terms.
|
|
|
|
//go:build cgo && linux && !(gpudirect && cuda)
|
|
|
|
package transport
|
|
|
|
import "errors"
|
|
|
|
// newGPUDirect on linux without the gpudirect AND cuda build tags
|
|
// returns a clean not-available error so Pick() falls through. The
|
|
// real implementation requires:
|
|
//
|
|
// - `-tags gpudirect,cuda`
|
|
// - libibverbs userspace (Ubuntu: libibverbs-dev)
|
|
// - Mellanox ConnectX-6/7 HCA visible (/dev/infiniband/uverbsN)
|
|
// - nvidia-peermem kernel module loaded
|
|
// - libcudart at link/run time
|
|
//
|
|
// See gpudirect_linux_real.go (build tag cgo,linux,gpudirect,cuda) for
|
|
// the live implementation.
|
|
func newGPUDirect() (Transport, error) {
|
|
return nil, errors.New("zap/transport: gpudirect: built without -tags gpudirect,cuda")
|
|
}
|