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
GEFORCE
H200 NVL
CORE STATE
GH100
VRAM
141 GB
CLOCK SPEED
1785 MHz
TDP
600 W
BUS WIDTH
6144 bit
ARCHITECTURE
Hopper
PROCESS
5 nm
LAUNCH DATE
2024
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
FirePro W4100
H200 NVL
Core Specs
Shading Units
512
16,896
+3200.0%
Shaders
512
16,896
+3200.0%
TMUs
32
528
+1550.0%
ROPs
16
24
+50.0%
Compute Units
8
—
SM Count
—
132
Clocks
Base Clock
—
1365 MHz
Boost Clock
—
1785 MHz
GPU Clock
630 MHz
—
Memory Clock
1000 MHz
4 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
2 GB
141 GB
VRAM (MB)
2,048
144,384
+6950.0%
Memory Type
GDDR5
HBM3e
Memory Bus
128 bit
6144 bit
Bandwidth
64.00 GB/s
4.89 TB/s
Cache
L1 Cache
16 KB (per CU)
256 KB (per SM)
L2 Cache
256 KB
50 MB
Performance
Pixel Rate
10.08 GPixel/s
42.84 GPixel/s
Texture Rate
20.16 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
645.1 GFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
40.32 GFLOPS (1:16)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
—
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
—
528
Power
TDP
50 W
600 W
TDP (W)
50
600
+1100.0%
Suggested PSU
250 W
1000 W
Power Connectors
None
8-pin EPS
Architecture
Architecture
GCN 1.0
Hopper
GPU Name
Cape Verde
GH100
Generation
FirePro GCN
(Wx100)
Server Hopper
(Hxx)
Process Size
28 nm
5 nm
Transistors
1,500 million
80,000 million
Die Size
123 mm²
814 mm²
Foundry
TSMC
TSMC
Density
12.2M / mm²
98.3M / mm²
API Support
DirectX
12 (11_1)
—
OpenGL
4.6
—
Vulkan
1.2.170
—
OpenCL
2.1 (1.2)
3.0
CUDA
—
9.0
Shader Model
6.5 (5.1)
—
Physical
Slot Width
Single-slot
Dual-slot
Length
171 mm
6.7 inches
267 mm
10.5 inches
Height
69 mm
2.7 inches
111 mm
4.4 inches
Outputs
4x mini-DisplayPort 1.2
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
FirePro Terascale
Server Ada
Successor
Radeon Pro Polaris
Server Blackwell