They usually have a name that indicates the generation as well as a number, the higher the number, the better the graphics card, in NVIDIA we have for example the AD102 GPU, which has different variants, such as the AD102-225-A1 which is used in the RTX 4070 Ti SUPER, but it has a modified chip, which is the original and belongs to the RTX 4090, the AD102-300-A1.
GPU Cores
As with the GPU, trying to actually call the compute units that a graphics card offers cores is somewhat misleading, but we use them every day, even if they do not represent the same thing because they are obviously not cores like those found in processors. The GPU of a graphics card has hundreds of small elements grouped into clusters that give rise to compute units, which can be found under different names depending on the brand, CU (Compute Units) by manufacturer. AMD, Xe-cores fr Intel or multiprocessor streaming in NVIDIA.
Memory: VRAM and bandwidth
VRAM and bandwidth are probably the easiest specifications to see in today’s graphics cards, because unlike the other aspects we need to look at, video memory itself is often indicated in the name of the graphics card since we will surely have seen it. 8 GB Or 16 GB of some graphics. The type of memory used by the graphics card indicates how fast and efficient it is, for example a memory GDDR6 is less than one GDDR6X, which in turn will be surpassed by GDDR7.
On the other hand, we have the memory bandwidth, which is usually represented in GB/s, and obviously the higher it is, the better the speeds will be offered by the graphics card. The memory speed as well as the bus width (384-bit, 256-bit, 128-bit, etc.) determine the memory bandwidth.
Clock Speeds
In this case, it is not too complicated to know what this specification represents, and it is that like a CPU, the GPU also has a parameter to measure the clock speed, which is usually represented in MHz. Basically, it determines the speed at which the. The GPU is capable of processing instructions, there is not much more mystery, since as in processors, a greater amount represents greater power.
TGP
If this technical specification sounds familiar, it is because it is very similar to the TDP (Thermal Design Power) offered by processors, and in this case it refers to the maximum energy that the graphics card is capable of consuming during use. We can take as an example the RTX 4090, which offers a TGP of 450 W, which implies that this is the maximum it will consume during use, although there may be peaks that exceed it when high-performance applications are used, but they usually do not last more than a few tenths of a second.
As you can imagine, this is an aspect directly related to temperature, since in the end it indicates not only what it consumes, but also the temperatures that the component can be expected to reach while you are using it.
FP32 Performance
Finally we have the single precision floating point format, an aspect that is usually not taken into account if we do not know some technical details of the operation of this type of device. Basically, it is a mathematical way of measuring the theoretical performance offered by the GPU, and you may have seen what its unit of measurement is, TFLOPS, which refers to the billions of operations that the device is capable of performing per second.
As you can imagine, a higher number of TFLOPS indicates that the graphics card has better performance. If we have one with 9 TFLOPS and another with 35 TFLOPS (as is the case with the RTX 4070), obviously the one capable of offering us 35 would win.
Table of Contents