NVIDIA GeForce RTX 4080 Super vs Qualcomm Adreno 612 vs Qualcomm Adreno 640

NVIDIA GeForce RTX 4080 Super

The Nvidia GeForce RTX 4080 Super is a high-end desktop graphics card based on the Ada Lovelace architecture. It uses the AD103 chip in full configuration with 10,240 cores and 16 GB GDDR6X graphics memory (256-bit bus with 23 Gbits).

Performance

The ray tracing performance is outstanding, thanks to 80 dedicated cores, and the 320 Tensor cores can be used for DLSS 3.

The gaming performance without DLSS is ideal for 4k with around 60fps and 2k with higher frame rates in demanding games without ray tracing effects (e.g. F1 22 or Cyberpunk 2077). With ray tracing, the use of DLSS is recommended. Compared to the competition, the performance without DLSS and ray tracing is slightly better than the significantly cheaper AMD Radeon RX 7900 XT.

The currently available RTX 4080 cards are very large (2.5 or 3 slots) and use the new 12VHPWR connector (which has caused some problems with adapters).

Power consumption

The AD103 chip is produced at TSMC in 5nm (4N with EUV) and is specified with a TGP (Total Graphics Power) of 320 watts (Nvidia recommends at least a 750-watt power supply).

Qualcomm Adreno 612

The Qualcomm Adreno 612 is a mobile graphics card for mid-range smartphones and tablets (mostly Android based). It is included in the Qualcomm Snapdragon 675 SoCs and based on the Adreno 600 architecture (like the Adreno 630, which should be fully compatible in software).

The performance is similar to the old Adreno 512 graphics card and therefore only in the lower mid-range of modern smartphone SoCs.

The GPU supports modern standards like Vulkan 1.0 (according to Wikipedia), OpenGL ES 3.2, OpenCL 2.0 and DirectX 11 (FL 11_1).

Qualcomm Adreno 640

The Qualcomm Adreno 640 is a smartphone and tablet GPU that is integrated within the Qualcomm Snapdragon 855 SoC. The chip will be available from early 2019 and will be used mainly in high-end Android devices.

According to Qualcomm, the Adreno 640 GPU offers a 20% improved performance over the Adreno 630, its predecessor, which is integrated in the Snapdragon 845 SoC. The enhanced performance is achieved by the Adreno 640 having 50% more FP16 and FP32 compute units (ALUs) than the Adreno 630, while its 7 nm FinFET manufacturing process makes it 20% more efficient too.

The Adreno 640 will also support the Vulkan 1.1 API, something which is possible for other Adreno 600 series GPUs too.