KitGuru KitGuru.net – Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards
Update 15 December 2023: Since publishing this article, it has come to our attention that the Predator Orion X prebuilt system, from which we took this RTX 4090, was a late-stage engineering sample and not a finished retail product. This was unknown to us before producing this analysis and naturally the results shown must be viewed with that in mind. We will aim to get a final retail sample as soon as possible to revisit the performance. Read more on this HERE.
When I first got hands-on with Acer’s Predator Orion X prebuilt system and found out that not only does it use a custom-made RTX 4090, but one that is actually liquid cooled with a built-in pump and radiator… well, you just know I had to take a closer look! In today’s analysis, we take this card out of the Orion X and put it into our regular GPU test system to see how it stacks up against a range of RTX 4090 cards from more established brands, and it did not go how I expected…
| RTX 4090 | RTX 4080 | RTX 3090 Ti | RTX 3090 | RTX 3080 Ti | RTX 3080 | |
| Process | TSMC N4 | TSMC N4 | Samsung 8N | Samsung 8N | Samsung 8N | Samsung 8N |
| SMs | 128 | 76 | 84 | 82 | 80 | 68 |
| CUDA Cores | 16384 | 9728 | 10752 | 10496 | 10240 | 8704 |
| Tensor Cores | 512 | 304 | 336 | 328 | 320 | 272 |
| RT Cores | 128 | 76 | 84 | 82 | 80 | 68 |
| Texture Units | 512 | 304 | 336 | 328 | 320 | 272 |
| ROPs | 176 | 112 | 112 | 112 | 112 | 96 |
| GPU Boost Clock | 2520 MHz | 2505 MHz | 1860 MHz | 1695 MHz | 1665 MHz | 1710 MHz |
| Memory Data Rate | 21 Gbps | 22.4 Gbps | 21 Gbps | 19.5 Gbps | 19 Gbps | 19 Gbps |
| L2 Cache | 73729 KB | 65536 KB | 6144 KB | 6144 KB | 6144 KB | 5120 KB |
| Total Video Memory | 24GB GDDR6X | 16GB GDDR6X | 24GB GDDR6X | 24GB GDDR6X | 12GB GDDR6X | 10GB GDDR6X |
| Memory Interface | 384-bit | 256-bit | 384-bit | 384-bit | 384-bit | 320-bit |
| Memory Bandwidth | 1008 GB/Sec | 716.8 GB/Sec | 1008 GB/Sec | 936 GB/Sec | 912 GB/Sec | 760 GB/Sec |
| TGP | 450W | 320W | 450W | 350W | 350W | 320W |
First, for a quick spec recap. Using TSMC's 4N node has allowed Nvidia to vastly increase transistor count, up from 28.3 billion with GA102, to a staggering 76.3 billion with the largest Ada GPU, AD102. Accordingly, core count has gone through the roof, with the RTX 4090 home to 16384 CUDA cores, with 512 Tensor cores and 128 RT cores, with a sizeable increase to the ROP count too, up to 176.
Such a leap forward in process node has also allowed Nvidia to crank the clock speed significantly, with the RTX 4090 now sporting a 2520MHz rated boost clock. Acer has left their model at stock clocks.
Memory configuration is almost identical to the RTX 3090 Ti, with 24GB GDDR6X running at 21Gbps, operating over a 384-bit interface, totalling memory bandwidth of just over 1TB/s. That said, there has been a substantial upgrade to the L2 cache with the Ada architecture, with the RTX 4090 now offering 73MB, compared to 6MB for GA102.
Power draw also remains at 450W, as per the RTX 3090 Ti, with Acer's custom card also coming in at that stock power figure.
