DirectStorage Performance Compared: AMD vs Intel vs Nvidia
Microsoft’s DirectStorage 1.1 application programming interface is available for Windows-based computers, the latest graphics cards, and advanced NVMe solid-state drives. Now it’s time to find the hardware that best handles one of DirectStorage 1.1’s most exciting features: GPU decompression. good luck, Compusumble I have developed a suitable benchmark, PC gaming hardware Using it, I made some interesting discoveries.
Microsoft’s DirectStorage 1.1 has some important features that improve performance, but the main purpose of this API is to reduce the CPU load when handling NVMe requests. It also saves valuable CPU cycles for other workloads and handles game asset decompression via a highly parallel GPU with little OS intervention and low CPU utilization. Additionally, DirectStorage asset compression and decompression algorithms allow you to transfer more data than your storage media (i.e. SSD) can handle, resulting in significantly faster load times.
On the other hand, since GPU hardware handles the DirectStorage decompression algorithm differently, PCGH suggests which of the latest GPUs (AMD’s Radeon RX 7900 XT, Intel’s Arc A770, or Nvidia’s GeForce RTX 4080) is suitable for decompressing assets. I decided to find out ifThey took Compusemble’s standard I ran it on a graphics card and Intel’s Core i9-12900K CPU.
row 0 – cell 0 | PCIe 4.0 x4 (7.9GB/s) | PCIe 3.0 x4 (3.9GB/s) | SATA (0.6GB/s) |
Radeon RX 7900 XT | 14.6GB/s | 12.6GB/s | 1.47GB/s |
Ark A770 16GB | 16.8GB/s | 13.9GB/s | 1.64GB/s |
GeForce RTX 4080 | 15.3GB/s | 12.7GB/s | 1.47GB/s |
Core i9-12900K @ 5.20GHz | 5.2GB/s | 5.2GB/s | 1.47GB/s |
The first thing that catches your eye is that all GPUs handle decompression at least 2.4x better than the Core i9-12900K processor. On the other hand, Intel’s Arc A770 outperforms AMD’s Radeon RX 7900 XT and Nvidia’s GeForce RTX 4080 significantly when it comes to decompressing GPU assets. Best case scenario the A770 can transfer/decompress assets at a rate of 16.8 GB/s while the RX 7900 XT has a rate of 14.6 GB/s which puts him in third place (13% behind the leader) .
According to PCGH, the actual load time is significantly reduced from 5 seconds to 0.5 seconds whether using an AMD, Intel or Nvidia GPU. So it doesn’t matter which GPU you use, given how close the decompression speed results for your graphics processor are. They’re all up to the task and generally powerful enough to greatly improve your gaming experience.