NVIDIA T1000 videocard review

T1000 videocard released by NVIDIA; release date: 6 May 2021. The videocard is based on Turing microarchitecture codenamed TU117.

Core clock speed - 1065 MHz. Boost clock speed - 1395 MHz. Texture fill rate - 78.12 GTexel/s. Pipelines - 896. Manufacturing process technology - 12 nm. Transistors count - 4700 million. Power consumption (TDP) - 50 Watt.

Memory type: GDDR6. Maximum RAM amount - 4 GB. Memory bus width - 128 bit. Memory clock speed - 1250 MHz, 10 Gbps effective. Memory bandwidth - 160.0 GB/s.

Benchmarks

Geekbench
OpenCL

Top 1 GPU

This GPU

345391

37636

Name	Value
Geekbench - OpenCL	37636

Specifications (specs)

Essentials
Architecture	Turing
Code name	TU117
Launch date	6 May 2021
Place in performance rating	589
Technical info
Boost clock speed	1395 MHz
Core clock speed	1065 MHz
Manufacturing process technology	12 nm
Peak Double Precision (FP64) Performance	78.12 GFLOPS (1:32)
Peak Half Precision (FP16) Performance	5.000 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	2.500 TFLOPS
Pipelines	896
Pixel fill rate	44.64 GPixel/s
Texture fill rate	78.12 GTexel/s
Thermal Design Power (TDP)	50 Watt
Transistor count	4700 million

Video outputs and ports
Display Connectors	4x mini-DisplayPort 1.4a
Compatibility, dimensions and requirements
Form factor	Single-slot
Interface	PCIe 3.0 x16
Recommended system power (PSU)	250 Watt
Supplementary power connectors	None
API support
DirectX	12 (12_1)
OpenCL	3.0
OpenGL	4.6
Shader Model	6.7 (6.4)
Vulkan
Memory
Maximum RAM amount	4 GB
Memory bandwidth	160.0 GB/s
Memory bus width	128 bit
Memory clock speed	1250 MHz, 10 Gbps effective
Memory type	GDDR6