AMD Radeon Instinct MI300X vs NVIDIA Tesla C870
We compared two Professional market GPUs: 192GB VRAM Radeon Instinct MI300X and 1536MB VRAM Tesla C870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI300X 's Advantages
Released 16 years and 7 months late
Boost Clock2100MHz
More VRAM (192GB vs 1536GB)
Larger VRAM bandwidth (5171GB/s vs 76.80GB/s)
19328 additional rendering cores
NVIDIA Tesla C870 's Advantages
Lower TDP (171W vs 750W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI300X
+23518%
81.72 TFLOPS
Tesla C870
0.346 TFLOPS
Graphics Card
Dec 2023
Release Date
May 2007
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1000 MHz
Base Clock
-
2100 MHz
Boost Clock
-
2525 MHz
Memory Clock
800 MHz
Memory
192GB
Memory Size
1536MB
HBM3
Memory Type
GDDR3
8192bit
Memory Bus
384bit
5171GB/s
Bandwidth
76.80GB/s
Render Config
304
Compute Units
-
-
SM Count
16
19456
Shading Units
128
1216
TMUs
32
0
ROPs
24
1216
Tensor Cores
-
-
-
-
16 KB (per CU)
L1 Cache
-
16 MB
L2 Cache
96 KB
256 MB
L3 Cache
-
Theoretical Performance
0 MPixel/s
Pixel Rate
14.40 GPixel/s
2554 GTexel/s
Texture Rate
38.40 GTexel/s
653.7 TFLOPS
FP16 (half)
-
81.72 TFLOPS
FP32 (float)
345.6 GFLOPS
81.72 TFLOPS
FP64 (double)
-
Board Design
750W
TDP
171W
1150 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
None
Power Connectors
2x 6-pin
Graphics Processor
Aqua Vanjaram
GPU Name
G80
-
-
-
CDNA 3.0
Architecture
Tesla
TSMC
Foundry
TSMC
5 nm
Process Size
90 nm
153 billion
Transistors
0.681 billion
1017 mm²
Die Size
484 mm²
Graphics Features
N/A
DirectX
11.1 (10_0)
N/A
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
N/A
Vulkan
N/A
-
CUDA
1.0
N/A
Shader Model
4.0
