Nvidia Geforce GTX 970 Specs Updated: Only 56 ROPs and Less than 2MB L2 Cache

Nvidia has finally given a very detailed and technical explanation to PCPer on why the GTX 970 faces retentiveness allocation issues. The reason lies in the fact that the GTX 970 technically has fewer ROPs than the GTX 980 too as less than the full 2MB cache of its older brother. Basically, the GTX 970 merely has 56 ROPs and about i.7MB of L2 cache available to it. It can still hitting the theoretical acme bandwidth of 224 GB/s only that is just while using both blocks of memory . GM204_arch_0

A portion of the official specification of the Nvidia Geforce GTX 970 is wrong

Nvidia'southward Jonah Alben, SVP of GPU Engineering science over at Nvidia drew the post-obit diagram for PCPer which shows the existent reason why the GTX 970 behaves as it does. If y'all look closely you will notice exactly three things grayed out. 1) Iii SMM blocks and 2) i L2 Cache block. While the SMM blocks are expected the interesting thing to note is the disabled L2/ROP cluster at the bottom left. Before nosotros go any further here is an extract giving the rundown:

Despite initial reviews and data from NVIDIA, the GTX 970 really has fewer ROPs and less L2 cache than the GTX 980. NVIDIA says this was an mistake in the reviewer'southward guide and a misunderstanding between the engineering squad and the technical PR team on how the architecture itself functioned. That means the GTX 970 has 56 ROPs and 1792 KB of L2 cache compared to 64 ROPs and 2048 KB of L2 cache for the GTX 980. - Nvidia via PCPer

The bodily problem here isn't the lowered ROP count I might add together since 56 ROPs output 56 pixels/clock while equally the 13SMMs output 52 pixels/clock. The clogging in this equation are the SMMs not the ROPs. Withal, the way Nvidia has configured memory fetching actually does impact performance. As you tin can come across in the diagram the last Batten port really has two memory attached to it. Under normal usage that would result in twice the amount of requests resulting in clogging under heavy utilize. To solve this result, Nvidia separated the 0.5GB cake from the 3.5GB one leaving it up to the OS to correctly utilize. Basically the 0.5GB block will take i/7th the speed of the 3.5GB cake although it will even so be faster than retentiveness over PCIe by about four times. So is the GTX 970 a 4GB carte or not? Well, yes and no, it certainly has 4GB of memory that can be effectively utilized just 0.five of that GB will exist slower than the rest, in whatsoever case misquotation of technical specifications did occur. I would encourage enthusiasts to read the PCPer article in detail for a more elaborated rundown.