Celsius (microarchitecture)

Nvidia Celsius

Release date	1999-2005 1999
Architecture	Celsius
Fabrication process	220 nm, 180nm, 150 nm
API support
Direct3D	7.0
OpenGL	1.2 (1.5)
History
Predecessor	Fahrenheit
Successor	Kelvin
Support status
Unsupported

Celsius ^[1] is the codename for a GPU microarchitecture developed by Nvidia, and released in 1999 microarchitecture. It was named with reference to Anders Celsius and used with the GeForce 256 and GeForce 2 series.

Naming convention

While Celsius was not used as a marketing name at the time of the GeForce 256's launch in 1999, the public name was first used by the nouveau Linux driver, and much later on the Nvidia website. ^{[2] [3] [4]}

The company's naming convention using famous scientists for its microarchitectures only became standard practice starting with the Tesla/Fermi generations ^[5] .

Graphics features

Feature

• The transform and lighting hardware

API

• DirectX 7.0
• OpenGL 1.2 (1.5) ^{[6] [7]}

Memory

• Max VRAM size bumped to 128MB

Chips

GeForce 256

• NV10, 17 million transistor ^[8]

GeForce 2 series

• NV11, 20 million transistor ^[9]
• NV15, 25 million transistor ^[10]
• NV17, 29 million transistor ^[11]
• NV18, 29 million transistor
• Crush11, 20 million transistor ^[12]
• Crush17, 29 million transistor ^[13]

GPU list

GeForce 256

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory				Processing power (GFLOPS)
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	Single precision
GeForce 256 SDR	11 October 1999	NV10	TSMC 220 nm	AGP 4× PCI	120	166	4:4:4	480	480	480	0	32 64	2.656	SDR	128	50
GeForce 256 DDR	13 December 1999					150							4.8	DDR

GeForce 2 series

Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	Fillrate				Memory
								MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
GeForce2 MX IGP + nForce 220/420	4 June 2001	NV1A (IGP) / NV11 (MX)	TSMC 180 nm	FSB	175	133	2:4:2	350	350	700	0	Up to 32 system RAM	2.128 4.256	DDR	64 128
GeForce2 MX200	3 March 2001			AGP 4× PCI		166						32 64	1.328	SDR	64
GeForce2 MX	28 June 2000												2.656		128
GeForce2 MX400	3 March 2001				200	166,200 (SDR) 166 (DDR)		400	400	800			2.656, 3.200	SDR DDR	128 (SDR) 64 (DDR)
GeForce2 GTS	26 April 2000	NV15		AGP 4×		166	4:8:4	800	800	1600			5.312	DDR	128
GeForce2 Pro	5 December 2000					200							6.4
GeForce2 Ti	1 October 2001		TSMC 150 nm		250			1000	1000	2000
GeForce2 Ultra	14 August 2000	NV16	TSMC 180 nm			230						64	7.36
Model	Launch	Code name	Fab (nm)	Bus interface	Core clock (MHz)	Memory clock (MHz)	Core config1	MOperations/s	MPixels/s	MTexels/s	MVertices/s	Size (MB)	Bandwidth (GB/s)	Bus type	Bus width (bit)
								Fillrate				Memory

See also

• List of Nvidia graphics processing units
• Scalable Link Interface (SLI)
• Qualcomm Adreno

References

1. "NVIDIA Technologies & Architectures". NVIDIA. Retrieved 21 December 2025.
2. "NVIDIA Technologies & Architectures". NVIDIA. Archived from the original on 1 December 2022. Retrieved 21 December 2025.
3. "NVIDIA Technologies & Architectures". NVIDIA. Archived from the original on 2 December 2024. Retrieved 21 December 2025.
4. https://www.nvidia.com/content/pdf/fermi_white_papers/t.halfhill_lookingbeyondgraphics.pdf ^{[ bare URL PDF ]}
5. "NVIDIA nextgen Kepler and Maxwell architectures codenames unveiled" . Retrieved 21 December 2025.
6. "GPU chips — envytools git documentation". envytools.readthedocs.io. Retrieved 15 February 2021.
7. "TechPowerUp". TechPowerUp. Retrieved 15 February 2021.
8. "NVIDIA GeForce 256 DDR Specs". TechPowerUp. Retrieved 15 February 2021.
9. "NVIDIA NV11 GPU Specs". TechPowerUp. Retrieved 15 February 2021.
10. "NVIDIA NV15 GPU Specs". TechPowerUp. Retrieved 15 February 2021.
11. "NVIDIA NV17 GPU Specs". TechPowerUp. Retrieved 15 February 2021.
12. "NVIDIA GeForce2 MX + nForce 220 Specs". TechPowerUp. Retrieved 15 February 2021.
13. "NVIDIA GeForce4 MX + nForce2 Specs". TechPowerUp. Retrieved 15 February 2021.