imaginary_num6er@alien.topB to Hardware@hardware.watchEnglish · 1 year agoDell reportedly restricts exports of AMD's fastest gaming GPUs to China — Radeon RX 7900 XTX, RX 7900, Pro W7900 purportedly listed as sanctioned techwww.tomshardware.comexternal-linkmessage-square50fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDell reportedly restricts exports of AMD's fastest gaming GPUs to China — Radeon RX 7900 XTX, RX 7900, Pro W7900 purportedly listed as sanctioned techwww.tomshardware.comimaginary_num6er@alien.topB to Hardware@hardware.watchEnglish · 1 year agomessage-square50fedilink
minus-squareTwanToni@alien.topBlinkfedilinkEnglisharrow-up1·1 year agodoesn’t RDNA3 have WAVA MMA or Wave Matrix Multiply Accumulate which is their AI cores?
minus-squareFrom-UoM@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoIt has the instruction sets in the compute units They are called AI accelerators for that reason. Not Ai cores. The actual Matrix “Cores” , i.e. dedicated silicon, are on the instinct series
minus-squaredotjzzz@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoNo. Tensor cores have seperate specialised matrix ALUs, AMD’s WMMA are instructions on existing shader ALUs. Tensor cores can process AI tasks in parallel to CUDA cores, RDNA3 can’t do both on the same CU.
doesn’t RDNA3 have WAVA MMA or Wave Matrix Multiply Accumulate which is their AI cores?
It has the instruction sets in the compute units
They are called AI accelerators for that reason.
Not Ai cores.
The actual Matrix “Cores” , i.e. dedicated silicon, are on the instinct series
No. Tensor cores have seperate specialised matrix ALUs, AMD’s WMMA are instructions on existing shader ALUs.
Tensor cores can process AI tasks in parallel to CUDA cores, RDNA3 can’t do both on the same CU.