GPU Comparison
RADEON
AMD FirePro W4100
CORE STATE
Cape Verde
VRAM
2 GB
CLOCK SPEED
—
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
GCN 1.0
PROCESS
28 nm
LAUNCH DATE
2014
VS
RADEON
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
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
FirePro W4100
Instinct MI300X
Core Specs
Shading Units
512
19,456
+3700.0%
Shaders
512
19,456
+3700.0%
TMUs
32
1,216
+3700.0%
ROPs
16
0
-100.0%
Compute Units
8
304
+3700.0%
Clocks
Base Clock
—
1000 MHz
Boost Clock
—
2100 MHz
GPU Clock
630 MHz
—
Memory Clock
1000 MHz
4 Gbps effective
1300 MHz 5.2 Gbps effective
Memory
Memory Size
2 GB
192 GB
VRAM (MB)
2,048
196,608
+9500.0%
Memory Type
GDDR5
HBM3
Memory Bus
128 bit
8192 bit
Bandwidth
64.00 GB/s
5.32 TB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per CU)
L2 Cache
256 KB
16 MB
L3 Cache
—
256 MB
Performance
Pixel Rate
10.08 GPixel/s
0 MPixel/s
Texture Rate
20.16 GTexel/s
2,553.6 GTexel/s
FP32 (TFLOPS)
645.1 GFLOPS
81.72 TFLOPS
FP64 (TFLOPS)
40.32 GFLOPS (1:16)
40.86 TFLOPS (1:2)
FP16 (TFLOPS)
—
81.72 TFLOPS (1:1)
AI/RT
Matrix Cores
—
1,216
Power
TDP
50 W
750 W
TDP (W)
50
750
+1400.0%
Suggested PSU
250 W
1150 W
Power Connectors
None
None
Architecture
Architecture
GCN 1.0
CDNA 3.0
GPU Name
Cape Verde
Aqua Vanjaram
Generation
FirePro GCN
(Wx100)
Instinct (MIx)
Process Size
28 nm
5 nm
Transistors
1,500 million
153,000 million
Die Size
123 mm²
1017 mm²
Foundry
TSMC
TSMC
Density
12.2M / mm²
150.4M / mm²
AMD MCM
MCM
—
2
API Support
DirectX
12 (11_1)
—
OpenGL
4.6
—
Vulkan
1.2.170
—
OpenCL
2.1 (1.2)
3.0
Shader Model
6.5 (5.1)
—
Physical
Slot Width
Single-slot
OAM Module
Length
171 mm
6.7 inches
—
Height
69 mm
2.7 inches
—
Outputs
4x mini-DisplayPort 1.2
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Production
End-of-life
—
Predecessor
FirePro Terascale
Radeon Instinct
Successor
Radeon Pro Polaris
—