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
CMP 70HX
CORE STATE
GA104
VRAM
8 GB
CLOCK SPEED
1395 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI300X
CMP 70HX
Core Specs
Shading Units
19,456
3,840
-80.3%
Shaders
19,456
3,840
-80.3%
TMUs
1,216
120
-90.1%
ROPs
0
64
+∞%
Compute Units
304
—
SM Count
—
30
Clocks
Base Clock
1000 MHz
1365 MHz
Boost Clock
2100 MHz
1395 MHz
Memory Clock
1300 MHz 5.2 Gbps effective
1188 MHz
19 Gbps effective
Memory
Memory Size
192 GB
8 GB
VRAM (MB)
196,608
8,192
-95.8%
Memory Type
HBM3
GDDR6X
Memory Bus
8192 bit
256 bit
Bandwidth
5.32 TB/s
608.3 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
16 MB
4 MB
L3 Cache
256 MB
—
Performance
Pixel Rate
0 MPixel/s
89.28 GPixel/s
Texture Rate
2,553.6 GTexel/s
167.4 GTexel/s
FP32 (TFLOPS)
81.72 TFLOPS
10.71 TFLOPS
FP64 (TFLOPS)
40.86 TFLOPS (1:2)
167.4 GFLOPS (1:64)
FP16 (TFLOPS)
81.72 TFLOPS (1:1)
10.71 TFLOPS (1:1)
AI/RT
RT Cores
—
30
Tensor Cores
—
120
Matrix Cores
1,216
—
Power
TDP
750 W
—
TDP (W)
750
—
Suggested PSU
1150 W
200 W
Power Connectors
None
1x 12-pin
Architecture
Architecture
CDNA 3.0
Ampere
GPU Name
Aqua Vanjaram
GA104
Generation
Instinct (MIx)
Mining GPUs
Process Size
5 nm
8 nm
Transistors
153,000 million
17,400 million
Die Size
1017 mm²
392 mm²
Foundry
TSMC
Samsung
Density
150.4M / mm²
44.4M / mm²
AMD MCM
MCM
2
—
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
8.6
Shader Model
—
6.8
Physical
Slot Width
OAM Module
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
112 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 1.0 x4
Other
Production
—
End-of-life
Predecessor
Radeon Instinct
—