:blobcatverified2: on Nostr: Using DirectML to benchmark ML Productivity is a fail... Why does DirectML has ...
Using DirectML to benchmark ML Productivity is a fail...
Why does DirectML has performance issues on AMD Cards and why ROCm can match CUDA?
So why not ROCm vs CUDA Benchmarks in the first place?
Published at
2025-03-05 15:55:30Event JSON
{
"id": "37cffa59dff0a917847916b604daf521bd60d1a7773655fc2e345dad009f08ab",
"pubkey": "304bca196ea40de81c5e94e588eeb5568ec36f4aa54cd073bde05f8939db0645",
"created_at": 1741190130,
"kind": 1,
"tags": [
[
"proxy",
"https://blob.cat/objects/9c37b4ab-5959-4231-b14f-4c2cc06945ed",
"activitypub"
]
],
"content": "Using DirectML to benchmark ML Productivity is a fail...\nWhy does DirectML has performance issues on AMD Cards and why ROCm can match CUDA?\nSo why not ROCm vs CUDA Benchmarks in the first place?",
"sig": "e433f389249db60bcb9357bdd985558d20344af848be8c0ee7f97cf0bd68f6c0a0382af10eda0d02625194239e6e61fbcef8421e568c5fe2dfe1c50a53b7cd30"
}
