VR World

Might AMD Hold The Solution For Connecting CPUs and GPUs?

AMD Restructuring AMD Restructuring

One of the most important advances in computing over the last decade has been the ability for programmers to properly harness the GPU for computing in their code. With this, and the massive increases in floating point power thanks to multi-core CPUs like the Intel Xeon E5v3, the amount of computer power available to users and institutions has spiked.

But there’s a problem. The link that binds the CPU and GPU, which in the vast majority of cases is PCI Express, is a bandwidth bottleneck. The full potential of the CPUs and GPUs cannot be realized since PCI Express has a maximum of 20GB/s achievable net bandwidth and up to 1 microsecond roundtrip latency.

But might AMD (NYSE: AMD) have a solution for this?

To read the full story, head to VR World, Bright Side of News* Asia-Pacific sister site.

  • foobario2

    Uh.. considering that discrete GPU performance barely rises at all when multiplying the bandwidth by a factor of 8x from PCIe 1.0 x8 to PCIE 3.0 x16, the answer is clearly no.

    • evolucion8

      Cause the videocards likes to keep most of their data on VRAM. Rarely the data spills from the VRAM into the System RAM through the PCI-E as it is costly from a performance perspective. PCI-E is a serious bottleneck and has serious latency issues.