GPU Comparison
GPU
Intel Iris Xe MAX Graphics
CORE STATE
DG1
VRAM
4 GB
CLOCK SPEED
1650 MHz
TDP
25 W
BUS WIDTH
128 bit
ARCHITECTURE
Generation 12.1
PROCESS
10 nm
LAUNCH DATE
2020
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
DETAILED SPECIFICATIONS
SPECIFICATION
Iris Xe MAX Graphics
H200 NVL
Core Specs
Shading Units
768
16,896
+2100.0%
Shaders
768
16,896
+2100.0%
TMUs
48
528
+1000.0%
ROPs
24
24
0.0%
SM Count
—
132
Execution Units
96
—
Clocks
Base Clock
300 MHz
1365 MHz
Boost Clock
1650 MHz
1785 MHz
Memory Clock
2133 MHz
4.3 Gbps effective
1593 MHz
6.4 Gbps effective
Memory
Memory Size
4 GB
141 GB
VRAM (MB)
4,096
144,384
+3425.0%
Memory Type
LPDDR4X
HBM3e
Memory Bus
128 bit
6144 bit
Bandwidth
68.26 GB/s
4.89 TB/s
Cache
L1 Cache
—
256 KB (per SM)
L2 Cache
1024 KB
50 MB
L3 Cache
16 MB
—
Performance
Pixel Rate
39.60 GPixel/s
42.84 GPixel/s
Texture Rate
79.20 GTexel/s
942.5 GTexel/s
FP32 (TFLOPS)
2.534 TFLOPS
60.32 TFLOPS
FP64 (TFLOPS)
633.6 GFLOPS (1:4)
30.16 TFLOPS (1:2)
FP16 (TFLOPS)
5.069 TFLOPS (2:1)
241.3 TFLOPS (4:1)
AI/RT
Tensor Cores
—
528
Power
TDP
25 W
600 W
TDP (W)
25
600
+2300.0%
Suggested PSU
200 W
1000 W
Power Connectors
—
8-pin EPS
Architecture
Architecture
Generation 12.1
Hopper
GPU Name
DG1
GH100
Generation
Xe Graphics
Server Hopper
(Hxx)
Process Size
10 nm
5 nm
Transistors
—
80,000 million
Die Size
95 mm²
814 mm²
Foundry
Intel
TSMC
Density
—
98.3M / mm²
API Support
DirectX
12 (12_1)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
—
9.0
Shader Model
6.6
—
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Other
Production
End-of-life
Active
Predecessor
Graphics
Server Ada
Successor
Alchemist
Server Blackwell