Teraflops: they are everything everyone wants to talk about when the next Xbox Series X or PlayStation 5 the consoles are mentioned. Indeed, Microsoft and Sony boast big performance gains thanks, in part, to an increase in teraflops.
Consoles vs PC: the beasts in the den
The Xbox Series X GPU is based on AMD’s RDNA 2 architecture and will be capable of 12 teraflops. Meanwhile, Sony’s PlayStation 5 (also based on AMD’s RDNA 2 architecture) will have a GPU with 10.28 teraflops.
That’s a lot of flops, and it’s comparable, or better, to what high-end PC graphics cards currently offer.
Since April 2020, the Radeon RX 5700XT (around $ 400 to date) is one of the best AMD cards, with a GPU of 9.75 teraflop. the NVIDIA GeForce RTX 2080 Ti ($ 1,300 to $ 1,500 to date), meanwhile, is capable of 13.4 teraflops. There is also NVIDIA RTX Titan, with a whopping 16.31 teraflops. But, at well over $ 2,000 at the time of writing, this is out of reach for most players.
But let’s not get ahead of ourselves. Let’s see what teraflops are and why this specification is important for graphics.
What are FLOPS?
FLOPS stands for floating point operations per second. Floating point arithmetic is the most common way to calculate numbers in game development. Without getting too lost in the weeds, floating point operations allow computers to work more efficiently with a wider range of numbers.
The most common way to express flops is in the single precision floating point format, FP32. This means that the computer uses 32 bits to store data in this format. There is also a semi-precision format that takes 16 bits (FP16) instead of 32. The most common method for expressing teraflops for GPUs is simple precision. However, AMD used FP16 in its Vega GPU, and RDNA 2 allows FP16.
In the real world, floating point is much easier to use for creators of games with 3D graphics. If the games were based on fixed point operations, such as Original PlayStation, this would cause many problems. The game visuals would appear and behave badly, and the code would generally be less effective.
Well done for the floating point operations!
FLOPS inflation led to TFLOPS
Games have to process a ton of data, and that’s why flops are an important reference. The more flops a GPU can do, the faster the data can be processed and the more computing power there is to run games.
The original Sega Dreamcast (1999) had 1.4 Gigaflops, which means it could handle up to 1.4 billion floating point operations per second. A few years later, the original Xbox (2002) dumped 20 gigaflops (20 billion flops). The PlayStation 3 (2006) had almost twelve times, at 230.4 gigaflops.
Each console has improved considerably over its predecessor, thanks in large part to the graphics processing power. Specifying flops is a quick way to get an idea of the amount of power under the hood of the graphics processor or GPU of a particular console.
The 12 teraflops of computing power in the upcoming Xbox Series X means it can handle up to 12 trillion floating point operations per second. The PlayStation 5, meanwhile, reached 10.28 billion flops.
If we only relied on flops as a measure, we would conclude that the Xbox Series X will be better than the PlayStation 5, which would be a mistake.
How important is TFLOPS?
Flops count things between generations of consoles, but not as much when the gap is narrower.
Even comparing the number of teraflops for modern graphics cards like the AMD Radeon 5700 XT and the GeForce RTX 2080 Ti can be misleading. The new consoles will use AMD’s new RDNA 2 architecture. New architecture generally means better performance than previous cards, even with similar hardware specifications.
Like anything else in IT, however, it’s all about implementation. Processor specifications, RAM and even software make all the difference. When you put it all together, the consensus is that the new consoles should outperform most PC gaming platforms currently there.
Xbox Series X and PlayStation 5 will have eight-core, sixteen-core processors. It reached impressive PC gaming levels, and it took a long time to get to the set-top boxes. Both consoles also plan to use NVMe SSD, which means faster loading times for games and improved responsiveness.
The new console GPUs will also have an impressive number of computing units at high clock speeds: 52 to 1.825 GHz for the Xbox, and 36 CPUs to 2.23 GHz for the PlayStation. For comparison, the Radeon 5700 XT has 40 CPUs at 1.6 GHz.
Of course, AMD’s RDNA 2 will not only live inside new consoles. Once it hits PC graphics cards (as well as the expected Ampere architecture from NVIDIA), any advantage of consoles on PCs will disappear.
TFLOPS is not the only thing that matters
There is no doubt that the new consoles will be powerful beasts. Microsoft and Sony say their consoles will reach 60 frames per second at 4K resolution in AAA titles (usually the most demanding games for graphics).
Microsoft is also looking to strike 120 frames per second in 4K for esports games, generally less demanding in terms of graphics. However, higher refresh rates mean a smoother picture and a better understanding of what’s going on on the playing field. Given the chaos that ensues in esports, smoother visuals are a big plus.
In addition to improving performance at higher resolutions, the new consoles will also support laser tracing. We saw this new technology for the first time in NVIDIA graphics cards. Ray-tracing increases the lighting effects in a game, often with dramatic improvements. It also offers a more dynamic and realistic gaming environment in which the shadows and reflections are more realistic. The computing power (teraflops) available in future GPUs will also help these new features.
RELATED: What is ray tracing?
Teraflops aren’t the only specification you need to pay attention to. However, it will give you a general idea of how the graphics power of a console compares to that of other hardware, past and present.