95. NVIDIA CUDA: results and suite pointers

Part: XIII · NVIDIA acceleration (welvet.cuda)
Package: w2a / cuda_smoke
Status: ok: host-only; no GPU required

When

Find where live CUDA timing/parity matrices live after the small usage chapters.

Where

go run .
../run_nvidia.sh

Why

Separate labelled pointers from live GPU measurement (same idea as Apple chapter 88).

What

Prints Go v1.4.0 / welvet.cuda 0.79 pins and commands for w2a go_v_cuda and welvet.cuda/examples/cuda_smoke. Does not execute CUDA.

Captured sample

NVIDIA CUDA results pointers (not a live benchmark)

Engine pin: welvet.cuda 0.79 · model ABI 1 · Go binding: nativecuda (Welvet v1.4.0)
…

main.go

Download source ↓

// Pointers to CUDA validation matrices; no GPU run is implied.
package main

import "fmt"

func main() {
	fmt.Println("NVIDIA CUDA results pointers (not a live benchmark)")
	fmt.Println()
	fmt.Println("Engine pin: welvet.cuda 0.79 · model ABI 1 · Go binding: nativecuda (Welvet v1.4.0)")
	fmt.Println("Usage tour: 89 mount · 90 Mamba dtypes · 91 train modes · 92 SyncToGo/ENTITY · 93 JSON · 94 mixed")
	fmt.Println()
	fmt.Println("Live matrices (sibling checkouts):")
	fmt.Println("  cd ../../w2a && go test ./tests/go_v_cuda -count=1 -timeout 180m")
	fmt.Println("  cd ../../welvet.cuda/examples/cuda_smoke && go run .")
	fmt.Println()
	fmt.Println("Install shared library into Go:")
	fmt.Println("  cd ../../welvet.cuda && ./scripts/linux_install_go.sh")
	fmt.Println()
	fmt.Println("Small usage tour without the large matrix:")
	fmt.Println("  ../run_nvidia.sh")
}