GPU Comparison

i

Intel

GPU

Intel Xeon Phi SE10X

CORE STATE Knights Corner

VRAM 8 GB

CLOCK SPEED —

TDP 300 W

BUS WIDTH 512 bit

ARCHITECTURE Knights

nm

PROCESS 22 nm

LAUNCH DATE 2012

VS

NVIDIA

GEFORCE

GeForce RTX 2060 SUPER

CORE STATE TU106

VRAM 8 GB

CLOCK SPEED 1650 MHz

TDP 175 W

BUS WIDTH 256 bit

ARCHITECTURE Turing

nm

PROCESS 12 nm

LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12

N/A

2,011

geekbench_opencl

N/A

87,670

geekbench_vulkan

N/A

83,503

passmark_directx_10

N/A

111

passmark_directx_11

N/A

130

passmark_directx_12

N/A

61

passmark_directx_9

N/A

218

passmark_g2d

N/A

854

passmark_g3d

N/A

16,462

passmark_gpu_compute

N/A

6,721

DETAILED SPECIFICATIONS

SPECIFICATION

Phi SE10X

RTX 2060 SUPER

Core Specs

Shading Units

976

2,176 +123.0%

Shaders

976

2,176 +123.0%

TMUs

32

136 +325.0%

ROPs

0

64 +∞%

SM Count

—

34

Execution Units

61

—

Clocks

Base Clock

—

1470 MHz

Boost Clock

—

1650 MHz

GPU Clock

1100 MHz

—

Memory Clock

1375 MHz 5.5 Gbps effective

1750 MHz 14 Gbps effective

Memory

Memory Size

8 GB

8 GB

VRAM (MB)

8,192

8,192 0.0%

Memory Type

GDDR5

GDDR6

Memory Bus

512 bit

256 bit

Bandwidth

352.0 GB/s

448.0 GB/s

Cache

L1 Cache

—

64 KB (per SM)

L2 Cache

—

4 MB

Performance

Pixel Rate

0 MPixel/s

105.6 GPixel/s

Texture Rate

35.20 GTexel/s

224.4 GTexel/s

FP32 (TFLOPS)

2.147 TFLOPS

7.181 TFLOPS

FP64 (TFLOPS)

—

224.4 GFLOPS (1:32)

FP16 (TFLOPS)

—

14.36 TFLOPS (2:1)

AI/RT

RT Cores

—

34

Tensor Cores

—

272

Power

TDP

300 W

175 W

TDP (W)

300

175 -41.7%

Suggested PSU

700 W

450 W

Power Connectors

—

1x 8-pin

Architecture

Architecture

Knights

Turing

GPU Name

Knights Corner

TU106

Generation

Knights Corner

GeForce 20

Process Size

22 nm

12 nm

Transistors

5,000 million

10,800 million

Die Size

720 mm²

445 mm²

Foundry

Intel

TSMC

Density

6.9M / mm²

24.3M / mm²

API Support

DirectX

—

12 Ultimate (12_2)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

1.2

3.0

CUDA

—

7.5

Shader Model

5.0

6.8

Physical

Slot Width

Dual-slot

Dual-slot

Length

248 mm 9.8 inches

229 mm 9 inches

Height

—

113 mm 4.4 inches

Outputs

No outputs

1x DVI1x HDMI 2.02x DisplayPort 1.4a1x USB Type-C

Bus Interface

PCIe 3.0 x16

PCIe 3.0 x16

Other

Launch Price

—

399 USD

Production

End-of-life

End-of-life

Predecessor

Knights Ferry

GeForce 10

Successor

H3C Graphics

GeForce 30

View Xeon Phi SE10X Details View GeForce RTX 2060 SUPER Details