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
GPU
Arc Pro A60
CORE STATE
DG2-256
VRAM
12 GB
CLOCK SPEED
2050 MHz
TDP
130 W
BUS WIDTH
192 bit
ARCHITECTURE
Xe-HPG
PROCESS
6 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Instinct MI300X
Pro A60
Core Specs
Shading Units
19,456
2,048
-89.5%
Shaders
19,456
2,048
-89.5%
TMUs
1,216
128
-89.5%
ROPs
0
64
+∞%
Compute Units
304
—
Execution Units
—
256
Clocks
Base Clock
1000 MHz
900 MHz
Boost Clock
2100 MHz
2050 MHz
Memory Clock
1300 MHz 5.2 Gbps effective
2000 MHz
16 Gbps effective
Memory
Memory Size
192 GB
12 GB
VRAM (MB)
196,608
12,288
-93.8%
Memory Type
HBM3
GDDR6
Memory Bus
8192 bit
192 bit
Bandwidth
5.32 TB/s
384.0 GB/s
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
16 MB
12 MB
L3 Cache
256 MB
—
Performance
Pixel Rate
0 MPixel/s
131.2 GPixel/s
Texture Rate
2,553.6 GTexel/s
262.4 GTexel/s
FP32 (TFLOPS)
81.72 TFLOPS
8.397 TFLOPS
FP64 (TFLOPS)
40.86 TFLOPS (1:2)
—
FP16 (TFLOPS)
81.72 TFLOPS (1:1)
16.79 TFLOPS (2:1)
AI/RT
RT Cores
—
16
XMX Cores
—
256
Matrix Cores
1,216
—
Power
TDP
750 W
130 W
TDP (W)
750
130
-82.7%
Suggested PSU
1150 W
300 W
Power Connectors
None
—
Architecture
Architecture
CDNA 3.0
Xe-HPG
GPU Name
Aqua Vanjaram
DG2-256
Generation
Instinct (MIx)
Alchemist
(Pro Series)
Process Size
5 nm
6 nm
Transistors
153,000 million
11,500 million
Die Size
1017 mm²
269 mm²
Foundry
TSMC
TSMC
Density
150.4M / mm²
42.8M / mm²
AMD MCM
MCM
2
—
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
Shader Model
—
6.6
Physical
Slot Width
OAM Module
Single-slot
Outputs
No outputs
4x DisplayPort 2.0
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Production
—
Active
Predecessor
Radeon Instinct
—