NVIDIA CMP 90HX vs AMD Radeon Instinct MI355X
We compared two Desktop platform GPUs: 10GB VRAM CMP 90HX and 288GB VRAM Radeon Instinct MI355X 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 1400W)
AMD Radeon Instinct MI355X 's Advantages
Released 3 years and 6 months late
Boost Clock has increased by 23% (2100MHz vs 1710MHz)
More VRAM (288GB vs 10GB)
Larger VRAM bandwidth (8.19TB/s vs 760.3GB/s)
13056 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 90HX
21.89 TFLOPS
Radeon Instinct MI355X
+273%
81.72 TFLOPS
Graphics Card
Jul 2021
Release Date
Jan 2025
Mining GPUs
Generation
Radeon Instinct
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1000 MHz
1710 MHz
Boost Clock
2100 MHz
1188 MHz
Memory Clock
2000 MHz
Memory
10GB
Memory Size
288GB
GDDR6X
Memory Type
HBM3e
320bit
Memory Bus
8192bit
760.3GB/s
Bandwidth
8.19TB/s
Render Config
-
Compute Units
304
50
SM Count
-
6400
Shading Units
19456
200
TMUs
1216
80
ROPs
0
200
Tensor Cores
1216
50
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
5 MB
L2 Cache
16 MB
-
L3 Cache
256 MB
Theoretical Performance
136.8 GPixel/s
Pixel Rate
0 MPixel/s
342.0 GTexel/s
Texture Rate
2553.6 GTexel/s
21.89 TFLOPS
FP16 (half)
653.7 TFLOPS
21.89 TFLOPS
FP32 (float)
81.72 TFLOPS
342.0 GFLOPS
FP64 (double)
81.72 TFLOPS
Board Design
320W
TDP
1400W
700 W
Suggested PSU
1800 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
None
Graphics Processor
GA102
GPU Name
Aqua Vanjaram X
GA102-100-A1
GPU Variant
-
Ampere
Architecture
CDNA 4.0
Samsung
Foundry
TSMC
8 nm
Process Size
3 nm
28.3 billion
Transistors
153 billion
628 mm²
Die Size
1017 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.6
CUDA
-
6.8
Shader Model
N/A
