That impossible, no way, 24GB GDDR5X was demoed working at SIGGRAPH last month. Not shipping yet, though, probably because as you say that dense...
I have long suspected the P100 doesn't even have the rasterizers needed for graphics and it's truly compute-only. The saved die space was used for...
But remember NVidia dropped both the GeForce and GTX labels for the new Pascal Titan X. The annoucement and the product page both carefully label...
A relevant comment from Tech Report gives an interesting contrarian data point to these Mercury and Peddie reports by looking at monthly Steam...
That's an excellent point! Tom's hardware shows GTX1080 load power between 180 and 210 watts. It's probably not a doubling because the ROP ratio...
Current indications are Vega's performance will compete with GTX 1070 and 1080, not with GP102 Titan X. You can conclude this from power...
Does Pascal's hardware texture compression reduce actual storage size of textures in RAM? The compression's main utility is to boost effective...
You must have inside info on this fast Vega rollout plan! Polaris's events started with the first proclamation in November 2015. Unveiled in...
There's an amusing admission buried inside. It's no surprise to any even casual Imagination observer, but the company's complete dependence on...
On the CPU side, PMADDWD does four parallel 16 bit weighted pair summations, so it's like 4 DP2As. It goes all the way back to MMX, so it's...
The vmad instruction in CUDA performs bytewise multiply-and-accumulate. Describing throughput rate ratios isn't as straightforward as fp32 since...
That chart would be more useful if you added a DP4A row, which is the simple but useful new integer instruction in non-P100 Pascal. Ryan did a...
It's really a good match for the GTX 950 in both price and speed... a tie, not an AMD loss. The interesting observation from TR's article is...
Not peanuts at all. Not a tiny market at all. NVidia's current HPC revenue is about 20% of the gaming segment and growing. Add in the fact that...
I keep seeing this misconception from multiple posters that fast INT8 and INT16 support is new to Pascal. It's not. All Kepler, Maxwell, and...
That's a really interesting and perceptive question. The energy needed to compute a FP64 FMA is about four times the energy needed for FP32. So...
The killer app of the Radeon Pro SSG is video editing, as evidenced by the Nuke support announcement. The market may be niche, but it also has...
AMD confirmed today that they have finished testing and are now prepared for production use of Samsung's 14nm fabs. That doesn't mean they're...
There's a credible second-hand report that DP4A's design just didn't make it in time for P100. I'm not a machine learning expert, but there is a...
Ryan, Is GP102's vaguely described "INT8" feature different than GP104's DP4A instruction? I suspect they're the same and you're mistaken about...
A second blog post from NVidia, more about machine learning with Titan X. New fun detail is that multiple Titan X's were handed out to random...
The specs of the new Titan X are online from NVidia. Also a blog post from Nvidia. Summary: 11 TFLOPS FP32 44 TOPS INT8 (new deep learning...
PC Perspective has analyzed the RX 480 PCIE slot power use changes from the new driver. It's still over spec in all three games they tested, but...
I was surprised the VRMs can be user programmed to change current draw, but it's obviously possible with the user Afterburner demonstration and...
Ashraf Eassa from Motley fool writes about Volta and muses whether it will use 16nm or 10nm TSMC. His point that NVidia has to supply Volta...
Especially if the channel is supplied with mostly 8GB and not 4GB SKUs. This provides the $199 anchor price to help perception and demand, but...
Is the power distribution on a GPU card programmable from software? (For any vendor/generation, not just RX 480). Certainly the output VRM voltage...
We can test that assertion by looking at this excellent review comparing the RX 480 4GB at 7GT/sec to the same 4GB at 8GT/sec and finally to 8GB...
The official PCIE specification says that an x16 graphics card can consume a maximum of 9.9 watts from the 3.3V slot supply, a maximum of 66 watts...
The over-spec PCIE power use seems pretty substantiated, but most people are focusing on anticipated dramatic consequences like blown...
RX 480 has the new Quick Reponse Queue allowing you to partition off some of the GCN units for your exclusive use, leaving the rest available for...
Raja's "2.8x" slide was an oblique comparison to NVidia's similar improvement=process+architecture claim. Raja showing perf/watt, and NVidia's...
Sure. GK104 third tier was used in OEM GTX 660s. GM104 third tier was used in OEM GTX 960s. But neither were launch products. They were just a...
Back in April, HardwareBattle in Korea had oddly specific model detail info about three GP104 SKUs. This 1060 picture could be fake, but if its...
Of course they'll bother. Their goal is to create demand for their flavor of the card over someone else's. If people prefer flashy water coolers...
Agreed! And taking that concept on a tangent, when the RX 480 reviews and benches come out in a few days, try to use AMD's own products as a...
SLI was introduced for NVidia cards in 2004, back when AGP slots were the standard. PCIe 1.0 came out enabling installing multiple cards...
Excellent meta-analysis by videocardz.com who accumulated the statistics from 330 different submitted early-bird RX 480 Firestrike benchmarks....
pharma, great find! A solid comparison is with the R9 390 which is effectively a dead heat between the two, which is what you'd expect from...
Ah.. I realized that they were vertical sliders, but I was interpreting the controls as a graph, with fixed frequencies on the X axis and vertical...
Not joking: That AMD RX480 tool appears to be designed as an underclocking tool to optimize wattage in low load situations, not an overclocking...
It's far more limited than that. Maxwell (and earlier generations) switch between graphics and compute loads on an even coarser whole-device...
An SM can concurrently compute multiple independent CUDA kernels, even on Kepler and Maxwell, as long as the resources (registers and shared...
If you double GP104, you still have fewer transistors than P100 so it's quite fab-able. But a 1.5 scaleup is almost certain due to wattage limits....
GK110B (née GK180) is different than GK110 with improved L1 and GPU Boost. But that was an upgrade that replaced GK110, not a parallel chip line.
The simplest answer to this confusion is simply that Drive PX2 is a configurable hosting platform. It's a motherboard hosting discrete swappable...
A total guess to explain the extra GP107 variant: supporting a single HBM2 module would be a powerful 4GB discrete mobile GPU, and HBM2 would...
A memory size of 3 or 6GB implies that the memory bus is 192 bits wide. This does not match with the Drive PX 2 board, showing a GP106 with 8...
Seems reasonable to me. The lower clocks on the reported 1070m balance out the higher SP count so the performance of the two SKUs are within a...
A student recognizes Einstein in a train and asks: Excuse me, professor, but does New York stop at this train?