quiz bu lëkkale ak tegtal · Diggante Niveau

Quiz tensor cores

Dafay muur jëfandikoo matrix Tensor Core, dajale ay presioŋ yu wuute, carreaux losisel, ak formaa nimero yuñ jagleel architecture.

Yooni njiit yu jëm ciTensor
Laaj 1 de 8

Ban core math lañu defar Tensor Cores ngir gaaw?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Ban core math lañu defar Tensor Cores ngir gaaw?
    • Matrix yokk-ak-dajale (D = A x B + C)
    • Tànn limu nimero yu bari
    • Defar nimero yu bari
    • Enkripte ak dekode ay done
  2. Ban arsitektir GPU NVIDIA moo njëkka dugal Tensor Cores?
    • Paskal
    • Volta
    • Turing
    • Maxwell
  3. Lan moo waral Tensor Cores di faral di jëfandikoo njubte gu néew lu melni FP16 wala FP8?
    • Yoon mingi sàkku ci IA mu gëna néew njub
    • GPU mënu am lu gëna dëggu
    • Dafay may ñu mëna liggéey ci nimero yu bari ci montor bu nekk, yokk produit bi boole ci tëye njubte gi
    • Dafay gëna ndaw chip bi
  4. Ngir baña gaawa jeex, ban njub la Tensor Cores yi di faral di jëfandikoo ngir am xaalis buy daw (accumulation)?
    • Benn njubte bu woyof ak dugal yi
    • Amul benn akumulaasioŋ buñ def
    • Integer kese te amul fraction
    • gëna jub lu melni FP32
  5. Ak naka la kaadar IA yu melni PyTorch di jëfandikoo Tensor Cores?
    • Biblioteek yu melni cuBLAS ak cuDNN dañuy jël matris yu mag yi def ko ay blok yu ndaw, core yi mën ko jëfandikoo
    • Developpeur yi dañu wara bind montage bi ak loxo ngir model bu nekk
    • Tensor Cores dafay dox ludul ak aparey buñ personaalise bu amul losisel bu mëna yegg
    • Mënu leen jëfandikoo ci kaadar yu kawe
  6. Ban formaa numérique bu bees la architecture Blackwell yokk ngir gëna yokk njariñu inférence bi?
    • FP64 (ñaari yoon)
    • FP4 (point flottant à 4 bits)
    • ASCII
    • FP128
  7. Why should a team validate model quality when changing Tensor Core input precision?
    • Reduced precision guarantees identical outputs
    • The model’s vocabulary changes automatically
    • Lower-precision arithmetic can change numerical results, so accuracy should be checked for the task
    • Tensor Cores remove all rounding effects
  8. Which computer-vision feature is a practical example of Tensor Core acceleration?
    • A database index with no matrix operations
    • A file compressor that never runs a neural network
    • A CPU-only spreadsheet calculation
    • Neural upscaling such as NVIDIA DLSS in games