So a typical RX 550 has a 2GB memory buffer that can shift data at a peak rate of 112GB/s. Shifting data in and out of system memory is significantly slower than VRAM.
Regardless of capacity though, it uses memory clocked at 1.75GHz and with a 128-bit wide bus can be fed data at 112GB/s. In fact, the RX 550 could only take advantage of half that capacity and in today's games the card works as well with a 2GB buffer. Because the compute performance for this card is around nine times lower, it doesn't require such a massive bandwidth or an 8GB memory buffer either. HBM2 provides a 2048-bit wide bus that with the memory clocked at 1.25GHz allows for a bandwidth of 483GB/s.įurther down the food chain, like at the bottom, you'll find graphics cards such as the RX 550. Because this is a high-end graphics card, not only it has a large 8GB buffer but the bus it uses to access this memory is also quite fast. For example, a Vega 64 has 8GB of dedicated memory where it can store data and then access it quickly when it needs to. Unlike a typical discrete graphics card, most integrated solutions don't have their own dedicated memory. However, since posting the review, a few questions have popped up and the one that I've probably seen the most revolves around the Vega GPU's memory allocation. Although both chips were impressive on that initial run, there's still loads of information that we'd like to cover, including deeper overclocking tests.
We recently took our first look at AMD's Raven Ridge desktop APUs after a grueling four day grind of benchmarking the Ryzen 5 2400G and Ryzen 3 2200G.
0 kommentar(er)
