1 Reply Latest reply on Aug 28, 2018 3:17 AM by dipak

    Is there any way to split a compute device (emulate two, or more, GPUs on the a single device)?


      For example I have a RX Vega 64 with 64 CUs and 8 GB VRAM, would it be somehow possible to make it appear like two GPU compute devices with 32 CUs and 4 GB VRAM each? Maybe some undocumented environment variable for debugging purposes?