GPU Comparison
GPU
Intel Data Center GPU Flex 140
CORE STATE
DG2-128
VRAM
6 GB
CLOCK SPEED
1950 MHz
TDP
75 W
BUS WIDTH
96 bit
ARCHITECTURE
Xe-HPG
PROCESS
6 nm
LAUNCH DATE
2022
VS
GEFORCE
GeForce RTX 3070 Ti 8 GB GA102
CORE STATE
GA102
VRAM
8 GB
CLOCK SPEED
1770 MHz
TDP
290 W
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
DETAILED SPECIFICATIONS
SPECIFICATION
Data Center GPU Flex 140
RTX 3070 Ti 8 GB GA102
Core Specs
Shading Units
1,024
6,144
+500.0%
Shaders
1,024
6,144
+500.0%
TMUs
64
192
+200.0%
ROPs
32
96
+200.0%
SM Count
—
48
Execution Units
128
—
Clocks
Base Clock
1600 MHz
1575 MHz
Boost Clock
1950 MHz
1770 MHz
Memory Clock
1937 MHz
15.5 Gbps effective
1188 MHz
19 Gbps effective
Memory
Memory Size
6 GB
8 GB
VRAM (MB)
6,144
8,192
+33.3%
Memory Type
GDDR6
GDDR6X
Memory Bus
96 bit
256 bit
Bandwidth
186.0 GB/s
608.3 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
4 MB
Performance
Pixel Rate
62.40 GPixel/s
169.9 GPixel/s
Texture Rate
124.8 GTexel/s
339.8 GTexel/s
FP32 (TFLOPS)
3.994 TFLOPS
21.75 TFLOPS
FP64 (TFLOPS)
—
339.8 GFLOPS (1:64)
FP16 (TFLOPS)
7.987 TFLOPS (2:1)
21.75 TFLOPS (1:1)
AI/RT
RT Cores
8
48
+500.0%
Tensor Cores
—
192
Power
TDP
75 W
290 W
TDP (W)
75
290
+286.7%
Suggested PSU
250 W
600 W
Power Connectors
1x 8-pin
1x 12-pin
Architecture
Architecture
Xe-HPG
Ampere
GPU Name
DG2-128
GA102
Generation
Data Center GPU
(Arctic Sound)
GeForce 30
Process Size
6 nm
8 nm
Transistors
7,200 million
28,300 million
Die Size
157 mm²
628 mm²
Foundry
TSMC
Samsung
Density
45.9M / mm²
45.1M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
—
8.6
Shader Model
6.6
6.8
Physical
Slot Width
Single-slot
Dual-slot
Length
170 mm
6.7 inches
267 mm
10.5 inches
Height
70 mm
2.8 inches
112 mm
4.4 inches
Outputs
1x HDMI 2.13x DisplayPort 2.0
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
GeForce 20
Successor
H3C Graphics
GeForce 40