GPU Comparison
RADEON
AMD Instinct MI300X
CORE STATE
Aqua Vanjaram
VRAM
192 GB
CLOCK SPEED
2100 MHz
TDP
750 W
BUS WIDTH
8192 bit
ARCHITECTURE
CDNA 3.0
PROCESS
5 nm
LAUNCH DATE
2023
VS
GEFORCE
Tesla P4
CORE STATE
GP104
VRAM
8 GB
CLOCK SPEED
1114 MHz
TDP
75 W
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2016
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI300X
Tesla P4
Core Specs
Shading Units
19,456
2,560
-86.8%
Shaders
19,456
2,560
-86.8%
TMUs
1,216
160
-86.8%
ROPs
0
64
+∞%
Compute Units
304
—
SM Count
—
20
Clocks
Base Clock
1000 MHz
886 MHz
Boost Clock
2100 MHz
1114 MHz
Memory Clock
1300 MHz 5.2 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
192 GB
8 GB
VRAM (MB)
196,608
8,192
-95.8%
Memory Type
HBM3
GDDR5
Memory Bus
8192 bit
256 bit
Bandwidth
5.32 TB/s
192.3 GB/s
Cache
L1 Cache
16 KB (per CU)
48 KB (per SM)
L2 Cache
16 MB
2 MB
L3 Cache
256 MB
—
Performance
Pixel Rate
0 MPixel/s
71.30 GPixel/s
Texture Rate
2,553.6 GTexel/s
178.2 GTexel/s
FP32 (TFLOPS)
81.72 TFLOPS
5.704 TFLOPS
FP64 (TFLOPS)
40.86 TFLOPS (1:2)
178.2 GFLOPS (1:32)
FP16 (TFLOPS)
81.72 TFLOPS (1:1)
89.12 GFLOPS (1:64)
AI/RT
Matrix Cores
1,216
—
Power
TDP
750 W
75 W
TDP (W)
750
75
-90.0%
Suggested PSU
1150 W
250 W
Power Connectors
None
None
Architecture
Architecture
CDNA 3.0
Pascal
GPU Name
Aqua Vanjaram
GP104
Generation
Instinct (MIx)
Tesla Pascal
(Pxx)
Process Size
5 nm
16 nm
Transistors
153,000 million
7,200 million
Die Size
1017 mm²
314 mm²
Foundry
TSMC
TSMC
Density
150.4M / mm²
22.9M / mm²
AMD MCM
MCM
2
—
API Support
DirectX
—
12 (12_1)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
6.1
Shader Model
—
6.8
Physical
Slot Width
OAM Module
Single-slot
Length
—
168 mm
6.6 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
—
End-of-life
Predecessor
Radeon Instinct
Tesla Maxwell
Successor
—
Tesla Volta