NVIDIA GA10B 32SM vs Qualcomm Adreno X2-90 7T Full Specs
2,048 Shaders 1.3GHz | 2,048 Shaders 1.7GHz |
Shared Memory204.8GB/sLPDDR5 | Shared Memory152.4GB/sLPDDR5X |
·· 5.33 TFLOPS | ·· 6.96 TFLOPS |
Form Factor iGPU | Form Factor iGPU |
TDP Shared | TDP 15W |
GA10B 32SM340.8 TOPSINT4 Tensor Sparse
Adreno X2-90 7T13.93 TFLOPSFP16Clock Speed ·· | Clock Speed ·· |
Peak OPS 340.8 TOPSINT4 Tensor Sparse | Peak OPS 13.93 TFLOPSFP16 |
Tensor FP16-16 42.6 TFLOPSFP16-16 Tensor Sparse 85.2 TFLOPSTensor FP16-32 42.6 TFLOPSFP16-32 Tensor Sparse 85.2 TFLOPS | - |
BF16 -Tensor BF16 42.6 TFLOPSBF16 Tensor Sparse 85.2 TFLOPS | BF16 13.93 TFLOPSTensor BF16 -BF16 Tensor Sparse - |
Tensor TF32 21.3 TFLOPS | Tensor TF32 - |
FP32 5.33 TFLOPS | FP32 6.96 TFLOPS |
- | FP64 1.74 TFLOPS |
Tensor INT4 170.4 TOPS | Tensor INT4 - |
Tensor INT8 85.2 TOPS | - |
Pixel Rate 41.6 GPixel/s | Pixel Rate 108.8 GPixel/s |
Texture Rate 20.8 GTexel/s | Texture Rate 217.6 GTexel/s |
Shaders 2,048 Shaders | Shaders 2,048 Shaders |
TMUs 16 TMUs | TMUs 128 TMUs |
ROPs 32 ROPs | ROPs 64 ROPs |
Tensor Cores 64 T-Cores | Tensor Cores - |
SMs 16 SMs | EUs 16 EUs |
Boost Clock 1.3GHz | Boost Clock 1.7GHz |
L2 Cache 4.1MB shared | L2 Cache 2MB shared |
L3 Cache - | L3 Cache 21MB shared |
Shared MemoryLPDDR5 | Shared MemoryLPDDR5X |
Memory Bus 256-bit | Memory Bus 128-bit |
Memory Speed 6.4GT/s | Memory Speed 9.5GT/s |
Memory Bandwidth 204.8GB/s | Memory Bandwidth 152.4GB/s |
ECC No | ECC No |
TDP Shared | TDP 15W |
Multi-Monitor - | Multi-Monitor 3 |
Encoder Model NVENC 7 | Encoder Model Hexagon AV1 |
Decoder Model NVDEC 5 | Decoder Model Hexagon AV1 |
Form Factor iGPU | Form Factor iGPU |
Foundry Samsung | Foundry TSMC |
Fabrication Node 8N | Fabrication Node N3E |
Die Size - | Die Size 288mm² |
Transistor Count 17 Billion | Transistor Count - |
No images available
No images available