AIDA64 GPGPU Benchmark
We are running AIDA64 Engineer version 6.70 and its GPGPU Benchmark. It runs OpenCL tests and tests various functions of GPGPU Compute performance on GPUs. We have graphed out each test separately, to compare the video cards.
The memory read to measure the maximum achievable memory data transfer bandwidth. The AMD Radeon RX 6950 XT has a 6% higher memory read bandwidth compared to the GeForce RTX 3090 Ti FE.
The Radeon RX 6950 XT has a 5% higher memory write bandwidth compared to the GeForce RTX 3090 Ti FE.
The memory copy bandwidth is significantly different. The Radeon RX 6950 XT is 34% faster on memory copy performance compared to the GeForce RTX 3090 Ti FE.
In Single-Precision FLOPS performance the GeForce RTX 3090 Ti FE is 57% faster than the Radeon RX 6950 XT.
In Double-Precision FLOPS performance the Radeon RX 6950 XT is 154% faster than the GeForce RTX 3090 Ti FE.
In 24-bit Integer IOPS performance the Radeon RX 6950 XT is 17% faster than the GeForce RTX 3090 Ti FE.
In 32-bit Integer IOPS performance the GeForce RTX 3090 Ti FE is 301% faster than the Radeon RX 6950 XT.
In 64-bit Integer IOPS the GeForce RTX 3090 Ti FE is 193% faster than the Radeon RX 6950 XT.
In AES-256 performance the GeForce RTX 3090 Ti FE is 48% faster than the Radeon RX 6950 XT.
In SHA-1 Hash performance the GeForce RTX 3090 Ti FE is 38% faster than the Radeon RX 6950 XT.
In Single-Precision Julia performance the GeForce RTX 3090 Ti FE is 25% faster than the Radeon RX 6950 XT.
In Double-Precision Mandel the Radeon RX 6950 XT is 206% faster than the GeForce RTX 3090 Ti FE.