NVIDIA CMP 90HX vs NVIDIA TITAN Ada
We compared two Desktop platform GPUs: 10GB VRAM CMP 90HX and 48GB VRAM TITAN Ada to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 90HX 's Advantages
Lower TDP (320W vs 800W)
NVIDIA TITAN Ada 's Advantages
Boost Clock has increased by 47% (2520MHz vs 1710MHz)
More VRAM (48GB vs 10GB)
Larger VRAM bandwidth (1.15TB/s vs 760.3GB/s)
12032 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 90HX
21.89 TFLOPS
TITAN Ada
+324%
92.9 TFLOPS
Graphics Card
Jul 2021
Release Date
Unknown
Mining GPUs
Generation
GeForce 40
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 4.0 x16
Clock Speeds
1500 MHz
Base Clock
2235 MHz
1710 MHz
Boost Clock
2520 MHz
1188 MHz
Memory Clock
1500 MHz
Memory
10GB
Memory Size
48GB
GDDR6X
Memory Type
GDDR6X
320bit
Memory Bus
384bit
760.3GB/s
Bandwidth
1.15TB/s
Render Config
-
-
-
50
SM Count
144
6400
Shading Units
18432
200
TMUs
576
80
ROPs
192
200
Tensor Cores
576
50
RT Cores
144
128 KB (per SM)
L1 Cache
128 KB (per SM)
5 MB
L2 Cache
96 MB
-
-
-
Theoretical Performance
136.8 GPixel/s
Pixel Rate
483.8 GPixel/s
342.0 GTexel/s
Texture Rate
1452 GTexel/s
21.89 TFLOPS
FP16 (half)
92.90 TFLOPS
21.89 TFLOPS
FP32 (float)
92.90 TFLOPS
342.0 GFLOPS
FP64 (double)
1452 GFLOPS
Board Design
320W
TDP
800W
700 W
Suggested PSU
1200 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
2x 16-pin
Graphics Processor
GA102
GPU Name
AD102
GA102-100-A1
GPU Variant
AD102-450-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
28.3 billion
Transistors
76.3 billion
628 mm²
Die Size
609 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
8.9
6.8
Shader Model
6.8
