GPU Comparison
GPU
Intel Data Center GPU Max 1350
CORE STATE
Ponte Vecchio
VRAM
96 GB
CLOCK SPEED
1550 MHz
TDP
450 W
BUS WIDTH
8192 bit
ARCHITECTURE
Generation 12.5
PROCESS
10 nm
LAUNCH DATE
2023
VS
GEFORCE
GeForce GTX 1630
CORE STATE
TU117
VRAM
4 GB
CLOCK SPEED
1785 MHz
TDP
75 W
BUS WIDTH
64 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Data Center GPU Max 1350
GTX 1630
Core Specs
Shading Units
14,336
512
-96.4%
Shaders
14,336
512
-96.4%
TMUs
896
32
-96.4%
ROPs
0
16
+∞%
SM Count
—
8
Execution Units
896
—
Clocks
Base Clock
750 MHz
1740 MHz
Boost Clock
1550 MHz
1785 MHz
Memory Clock
1200 MHz
2.4 Gbps effective
1500 MHz
12 Gbps effective
Memory
Memory Size
96 GB
4 GB
VRAM (MB)
98,304
4,096
-95.8%
Memory Type
HBM2e
GDDR6
Memory Bus
8192 bit
64 bit
Bandwidth
2.46 TB/s
96.00 GB/s
Cache
L1 Cache
64 KB (per EU)
64 KB (per SM)
L2 Cache
408 MB
1024 KB
Performance
Pixel Rate
0 MPixel/s
28.56 GPixel/s
Texture Rate
1,388.8 GTexel/s
57.12 GTexel/s
FP32 (TFLOPS)
44.44 TFLOPS
1.828 TFLOPS
FP64 (TFLOPS)
44.44 TFLOPS (1:1)
57.12 GFLOPS (1:32)
FP16 (TFLOPS)
44.44 TFLOPS (1:1)
3.656 TFLOPS (2:1)
AI/RT
RT Cores
112
—
XMX Cores
896
—
Power
TDP
450 W
75 W
TDP (W)
450
75
-83.3%
Suggested PSU
850 W
250 W
Power Connectors
—
None
Architecture
Architecture
Generation 12.5
Turing
GPU Name
Ponte Vecchio
TU117
Generation
Data Center GPU
(Ponte Vecchio)
GeForce 16
Process Size
10 nm
12 nm
Transistors
100,000 million
4,700 million
Die Size
1280 mm²
200 mm²
Foundry
Intel
TSMC
Density
78.1M / mm²
23.5M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
—
7.5
Shader Model
6.6
6.8
Physical
Slot Width
OAM Module
Single-slot
Length
—
145 mm
5.7 inches
Height
—
69 mm
2.7 inches
Outputs
No outputs
1x DVI1x HDMI 2.01x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Production
Active
End-of-life
Predecessor
—
GeForce 10
Successor
H3C Graphics
GeForce 20