GeForce 700 series: Difference between revisions

Browse history interactively ← Previous editContent deleted Content addedVisual WikitextInline

Revision as of 15:27, 20 May 2013 editEBusiness (talk \| contribs)136 edits Big round of deleting, no sources have reliably linked the GF 700 series and the GK110 chip, so it is gone.← Previous edit		Latest revision as of 16:53, 15 December 2024 edit undoKarol739 (talk \| contribs)Extended confirmed users1,543 edits ,Tag: Visual edit
(724 intermediate revisions by more than 100 users not shown)
Line 1:		Line 1:
			{{for\|GeForce cards with a model number of 7XX0\|GeForce 7 series}}
	{{Refimprove\|date=May 2013}}
			{{Short description\|Series of GPUs by Nvidia}}
			{{Use mdy dates\|date=October 2018}}
	{{Infobox GPU		{{Infobox GPU
	\| name = GeForce 700 ~~Series~~		\| name = GeForce 700 series
	\| image = ]		\| image = ]<br>
			\| caption = GTX Titan Z released in May of 2013; the series' flagship unit sporting dual Kepler GK110 processors and the final Nvidia graphics card supporting dual-GPU configuration on a single PCB board.
	\| codename =
			\| codename = {{Unbulleted list\|GK110\|GK208\|GM108\|GM107}}
	\| created =
			\| architecture = {{Unbulleted list\|]\|]\|]}}
	\| model = GeForce Series
			\| created = {{start date and age\|February 19, 2013}}
	\| model1 = GeForce GT Series
	\| ~~model2~~ = GeForce ~~GTX Series~~		\| model = GeForce series
			\| model1 = GeForce GT series
	\| transistors1 = 585M 28 nm (GF117)
			\| model2 = GeForce GTX series
	\| transistors2 = 1,270M 28 nm (GK107)
			\| transistors1 = 292M (GF119) 40 nm
	\| transistors3 = 1,270M 28 nm (GK208)
			\| transistors2 = 585M (GF117) 28 nm

			\| transistors3 = 1.02B (GK208) 28 nm
	\| arch = ]
			\| transistors4 = 1.27B (GK107) 28 nm
	\| entry =
			\| transistors5 = 2.54B (GK106) 28 nm
	\| midrange =
			\| transistors6 = 3.54B (GK104) 28 nm
	\| highend =
			\| transistors7 = 7.08B (GK110) 28 nm
	\| openglversion = ]
			\| fab = {{Unbulleted list\|] ]\|TSMC ]}}
	\| d3dversion = ]<br>]
			\| entry = {{Unbulleted list\|GeForce GT 705\|GeForce GT 710\|GeForce GT 720\|GeForce GT 730\|GeForce GT 740\|GeForce GTX 745\|}}
	\| openclversion = ]
			\| midrange = {{Unbulleted list\|GeForce GTX 750\|GeForce GTX 750 Ti\|GeForce GTX 760 192-Bit\|GeForce GTX 760\|GeForce GTX 760 Ti\|GeForce GTX 770}}
	\| predecessor = ]
	\| ~~successor~~ ~~= ]~~		\| highend = {{Unbulleted list\|GeForce GTX 780}}
			\| enthusiast = {{Unbulleted list\|GeForce GTX 780 Ti\|GeForce GTX Titan\|GeForce GTX Titan Black\|GeForce GTX Titan Z}}
			\| openglversion = ]
			\| d3dversion = ] (] 11_0)<ref name="TechReport">{{cite news \|last=Kowaliski \|first=Cyril \|date=March 21, 2014 \|title=DirectX 12 will also add new features for next-gen GPUs \|url=http://techreport.com/news/26210/directx-12-will-also-add-new-features-for-next-gen-gpus \|newspaper=The Tech Report \|access-date=April 1, 2014 }}</ref><ref>{{Cite news\|first=Hassan \|last=Mujtaba\| url=http://wccftech.com/amd-confirms-gcn-cards-feature-full-directx-12-support-feature-level-111-gcn-10-feature-level-120-gcn-1112/ \|title=AMD Confirms GCN Cards Don't Feature Full DirectX 12 Support – Feature Level 11_1 on GCN 1.0, Feature Level 12_0 on GCN 1.1/1.2\|newspaper=WCCFtech \|date=June 5, 2015 \|access-date=June 8, 2015}}</ref> ] (Maxwell), ] (Kepler) or ] (Fermi)
			\| openclversion = ]{{efn\|name="OpenCL3.0"\|In OpenCL 3.0, OpenCL 1.2 functionality has become a mandatory baseline, while all OpenCL 2.x and OpenCL 3.0 features were made optional.}}
			\| vulkanapi = ]<ref name="vulkan">{{cite web \|url=https://developer.nvidia.com/vulkan-driver \|title=Vulkan Driver Support \|work=] \|date=February 10, 2016 \|access-date=April 25, 2018}}</ref><br />]
			\| predecessor = ]
			\| variant = ]
			\| successor = ]
			\| support status = ] and ] unsupported.<br />] fully supported.
	}}		}}

	The '''GeForce 700 ~~Series~~''' ~~will~~ be a ~~family~~ of ]s developed by ]~~, to be used in desktop and laptop PCs~~. It ~~will~~ ~~serve~~ as ~~the introduction for~~ the Kepler ~~Refresh~~ ~~architecture~~ (GK-codenamed chips), ~~named~~ ~~after~~ ~~the~~ ~~German~~ ~~mathematician,~~ ~~astronomer,~~ and ~~astrologer~~ ]. ~~A number of~~ GeForce 700 series ~~chips~~ were released ~~for~~ ~~mobile~~ ~~devices~~ in ~~April~~ 2013. No ~~desktop~~ ~~graphics~~ ~~cards~~ ~~have~~ ~~been~~ released ~~yet~~		The '''GeForce 700 series''' (stylized as '''GEFORCE GTX 700 SERIES''') is a series of ]s developed by ]. While mainly a refresh of the ] (GK-codenamed chips), some cards use ] (GF) and later cards use ] (GM). GeForce 700 series cards were first released in 2013, starting with the release of the GeForce GTX Titan on February 19, 2013, followed by the GeForce GTX 780 on May 23, 2013. The first mobile GeForce 700 series chips were released in April 2013.

			== Overview ==
			GK110 was designed and marketed with computational performance in mind. It contains 7.1 billion transistors. This model also attempts to maximise energy efficiency through the execution of as many tasks as possible in parallel according to the capabilities of its streaming processors.

			With GK110, increases in memory space and bandwidth for both the register file and the L2 cache over previous models, are seen. At the SMX level, GK110's register file space has increased to 256KB composed of 64K 32bit registers, as compared to Fermi's 32K 32bit registers totaling 128 KB. As for the L2 cache, GK110 L2 cache space increased by up to 1.5MB, 2x as big as GF110. Both the L2 cache and register file bandwidth have also doubled.
			Performance in register-starved scenarios is also improved as there are more registers available to each thread. This goes in hand with an increase of total number of registers each thread can address, moving from 63 registers per thread to 255 registers per thread with GK110.

			With GK110, Nvidia also reworked the GPU ] to be used for compute. With 48KB in size, in compute the texture cache becomes a read-only cache, specializing in unaligned memory access workloads. Furthermore, error detection capabilities have been added to make it safer for use with workloads that rely on ].<ref name="anandtech-GK110-preview">{{cite web \| url=http://www.anandtech.com/show/6446/nvidia-launches-tesla-k20-k20x-gk110-arrives-at-last/3\| title=NVIDIA Launches Tesla K20 & K20X: GK110 Arrives At Last \| date=November 12, 2012 \| publisher=AnandTech}}</ref>

			Dynamic Super Resolution (DSR) was added to Kepler GPUs with the latest Nvidia drivers.<ref>{{cite web\|url=http://www.geforce.com/whats-new/articles/geforce-344-48-whql-driver-released\|title=GeForce Game Ready Driver For Civilization: Beyond Earth & Lords Of The Fallen Available Now\|website=geforce.com\|access-date=April 18, 2018}}</ref>

			== Architecture ==
			{{Main\|Fermi (microarchitecture)\|Kepler (microarchitecture)\|Maxwell (microarchitecture)}}

			] and die]]
			]

			The GeForce 700 series contains features from both GK104 and GK110. Kepler based members of the 700 series add the following standard features to the GeForce family.

			Derived from GK104:

			* ] interface
			* ] 1.2
			* ] 1.4a 4K x 2K video output
			* ] hardware video acceleration (up to 4K x 2K H.264 decode)
			* Hardware H.264 encoding acceleration block (NVENC)
			* Support for up to 4 independent 2D displays, or 3 stereoscopic/3D displays (NV Surround)
			* Bindless Textures
			* GPU Boost
			* TXAA
			* Manufactured by ] on a 28 nm process

			New Features from GK110:

			* Compute Focus SMX Improvement
			* ] Compute Capability 3.5
			* New Shuffle Instructions
			* Dynamic Parallelism
			* Hyper-Q (Hyper-Q's MPI functionality reserve for Tesla only)
			* Grid Management Unit
			* Nvidia GPUDirect (GPU Direct's RDMA functionality reserve for Tesla & Quadro only)
			* GPU-Boost 2.0

			=== Compute focus SMX improvement ===
			With GK110, Nvidia opted to increase computational performance. The single biggest change from GK104 is that rather than 8 dedicated FP64 CUDA cores, GK110 has up to 64, giving it 8x the FP64 throughput of a GK104 SMX. The SMX also sees an increase in space for register file. Register file space has increased to 256KB compared to Fermi. The texture cache are also improved. With a 48KB space, the texture cache can become a read-only cache for compute workloads.<ref name=anandtech-GK110-preview />

			=== New shuffle Instructions ===
			At a low level, GK110 sees additional instructions and operations to further improve performance. New shuffle instructions allow for threads within a warp to share data without going back to memory, making the process much quicker than the previous load/share/store method. Atomic operations are also overhauled, speeding up the execution speed of atomic operations and adding some FP64 operations that were previously only available for FP32 data.<ref name=anandtech-GK110-preview />

			=== NVENC ===
			{{Main\|Nvidia NVENC}}

			=== Hyper-Q ===
			Hyper-Q expands GK110 hardware work queues from 1 to 32. The significance of this being that having a single work queue meant that Fermi could be under occupied at times as there wasn't enough work in that queue to fill every SM. By having 32 work queues, GK110 can in many scenarios, achieve higher utilization by being able to put different task streams on what would otherwise be an idle SMX. The simple nature of Hyper-Q is further reinforced by the fact that it's easily map to MPI, a common message passing interface frequently used in HPC. As legacy MPI-based algorithms that were originally designed for multi-CPU systems that became bottlenecked by false dependencies now have a solution. By increasing the number of MPI jobs, it's possible to utilize Hyper-Q on these algorithms to improve the efficiency all without changing the code itself.<ref name=anandtech-GK110-preview />

			=== Microsoft DirectX support ===
			Nvidia Kepler GPUs of the GeForce 700 series fully support DirectX 11.0. All GeForce 700 series card also support DirectX 12.0 with ] 11_0.

			=== Dynamic parallelism ===
			Dynamic parallelism ability is for kernels to be able to dispatch other kernels. With Fermi, only the CPU could dispatch a kernel, which incurs a certain amount of overhead by having to communicate back to the CPU. By giving kernels the ability to dispatch their own child kernels, GK110 can both save time by not having to go back to the CPU, and in the process free up the CPU to work on other tasks.<ref name=anandtech-GK110-preview />

	==Products==		==Products==

			===GeForce 700 (7xx) series===
			]
			The GeForce 700 series was designed for desktop architecture. Cheaper and lower performing products were expected to be released over time. Kepler supports 11.1 features with 11_0 feature level through the DirectX 11.1 API, however Nvidia did not enable four non-gaming features in Hardware in Kepler (for 11_1).<ref>{{cite web\|url=http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html\|title=NVIDIA Kepler not fully compliant with DirectX 11.1\|website=Guru3D.com\|access-date=April 18, 2018\|archive-date=December 22, 2015\|archive-url=https://web.archive.org/web/20151222113454/http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html\|url-status=dead}}</ref><ref>. {{webarchive\|url=https://web.archive.org/web/20121229062851/http://www.brightsideofnews.com/news/2012/11/21/nvidia-doesnt-fully-support-directx-111-with-kepler-gpus2c-bute280a6.aspx\|date=December 29, 2012}}.</ref>

			* <sup>1</sup> ] : ]s : ]s
			* <sup>2</sup> Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed
			* <sup>3</sup> Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
			* <sup>4</sup> Single precision performance is calculated as 2 times the number of shaders multiplied by the base core clock speed.
			* <sup>5</sup> Double precision performance of the '''GTX Titan''' and '''GTX Titan Black''' is either 1/3 or 1/24 of single-precision performance depending on a user-selected configuration option in the driver that boosts single-precision performance if double-precision is set to 1/24 of single-precision performance,<ref>{{cite web\|url=http://www.tomshardware.com/reviews/geforce-gtx-titan-gk110-review,3438-2.html\|title=GK110: The True Tank - Nvidia GeForce GTX Titan 6 GB: GK110 On A Gaming Card\|date=February 19, 2013\|website=tomshardware.com\|access-date=April 18, 2018}}</ref> while other '''Kepler''' chips' double precision performance is fixed at 1/24 of single-precision performance.<ref>{{cite web\|url=http://www.tomshardware.com/reviews/geforce-gtx-780-ti-review-benchmarks,3663.html\|title=Nvidia GeForce GTX 780 Ti Review: GK110, Fully Unlocked\|date=November 7, 2013\|website=tomshardware.com\|access-date=April 18, 2018}}</ref> GeForce 700 series '''Maxwell''' chips' double precision performance is 1/32 of single-precision performance.<ref>{{cite news \|last1=Smith \|first1=Ryan \|last2=T S \|first2=Ganesh \|date=February 18, 2014 \|title=The NVIDIA GeForce GTX 750 Ti and GTX 750 Review: Maxwell Makes Its Move \|url=http://www.anandtech.com/show/7764/the-nvidia-geforce-gtx-750-ti-and-gtx-750-review-maxwell/5 \|newspaper=] \|page=5 \|access-date=February 18, 2014}}</ref>
			* <sup>6</sup> SLI supports connecting up to 4 identical graphics cards for a 4-way SLI configuration. Those supporting 4-way SLI can support 3-way & 2-way SLI, however a dual-GPU card already implements 2-way SLI internally, thus only 2 dual-GPU cards can be used in SLI to give a 4-way SLI configuration.

	===GeForce 700M (7xxM) series===		===GeForce 700M (7xxM) series===
	Some implementations may use different specifications.		Some implementations may use different specifications.

	* <sup>1</sup> ] ~~(]/]/])~~ : ] : ]		* <sup>1</sup> ] : ]s : ]s

			{{row hover highlight}}
	{\| class="wikitable" style="font-size: 85%; text-align: center; width: auto;"
			{{sort under}}
			{\| class="wikitable sortable sort-under mw-datatable" style="font-size: 85%; text-align: center;"
	\|-		\|-
	! rowspan=2 \| Model		! rowspan=2 \| Model
Line 38:		Line 123:
	! rowspan=2 \| Fab (])		! rowspan=2 \| Fab (])
	! rowspan=2 \| ] ]		! rowspan=2 \| ] ]
	! rowspan=2 \| ~~Memory~~ ~~(])~~		! rowspan=2 \| Core config<sup>1</sup>
			! colspan=3 \| Clock speed
	! rowspan=2 \| Config core<sup>1</sup>
	! colspan=~~3 style="text-align:center;"~~ \| ~~Clock speed~~		! colspan=2 \| ]
	! colspan=~~2 style="text-align:center;"~~ \| ]		! colspan=4 \| Memory
			! colspan=4 \| ] support (version)
	! colspan=3 style="text-align:center;" \| Memory
			! rowspan=2 \| Processing power<sup>2</sup><br> (GFLOPS)
	! colspan=3 style="text-align:center;" \| ] support (version)
	! rowspan=2 \| Processing Power<sup>2</sup><br> (GFLOPS)
	! rowspan=2 \| ] (watts)		! rowspan=2 \| ] (watts)
	! rowspan=2 \| Notes		! rowspan=2 \| Notes
Line 53:		Line 137:
	! Pixel (]/s)		! Pixel (]/s)
	! Texture (]/s)		! Texture (]/s)
			! Size (])
	! Bandwidth (]/s)		! Bandwidth (]/s)
			! Type
	! Bus type
	! Bus width (])		! Bus width (])
	! ]		! ]
	! ]		! ]
	! ]		! ]
			! ]
	\|-		\|-
	! style="text-align:left;" \| GeForce ~~710M~~ <ref>http://www.notebookcheck.net/NVIDIA-GeForce-~~710M~~.~~84746~~.0.html~~</ref><ref>http://www~~.~~geforce.com/hardware/notebook~~-~~gpus/geforce-710m/specifications~~</ref>		! style="text-align:left;" \| GeForce 705M<ref>{{cite web\|url=http://www.notebookcheck.net/NVIDIA-GeForce-705M.92914.0.html\|title=NVIDIA GeForce 705M\|website=notebookcheck.net\|access-date=April 18, 2018}}</ref>
			\| June 1, 2013
	\| ?
			\| GF119{{efn\|name="nohwenc"\|Lacks hardware video encoder}}
	\| GF117
	\| 28		\| 40
	\| PCIe 2.0 x16		\| rowspan="4" \| PCIe 2.0 x16
			\| 48:8:4
			\| 775
			\| 1550
			\| 1800
			\|1.48
			\|5.9
	\| up to 2048		\| up to 2048
			\|?
			\| rowspan="4" \| DDR3
			\| 64
			\| rowspan="16" \| 12.0 (11_0)
			\| rowspan="16" \| 4.6
			\| rowspan="3" \| 1.1
			\| rowspan="16" \| 1.3
			\|141.7
			\| 12
			\| Rebadged 520M
			\|-
			! style="text-align:left;" \| GeForce 710M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-710m/specifications\|title=GeForce 710M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| April 1, 2013
			\| rowspan="2" \| GF117{{efn\|name="nohwenc"}}
			\| rowspan="15" \| 28
	\| 96:16:4		\| 96:16:4
	\| ?		\| 775
	\| ?		\| 1550
	\| 1800		\| 1800
	\| ?		\|3.1
			\|12.4
	\| ?
			\| up to 2048
	\| 14.4		\| 14.4
	\| DDR3
	\| 64		\| 64
			\|297.6
	\| 11
			\|15
	\| 4.1
	\| Yes
	\| ?
	\| ?
	\|		\|
	\|-		\|-
	! style="text-align:left;" \| GeForce GT 720M ~~<ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-720M.90247.0.html</ref>~~<ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-720m/specifications</ref>		! style="text-align:left;" rowspan=2 \| GeForce GT 720M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-720m/specifications\|title=GeForce GT 720M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
	\| GF117
	\| 28
	\| PCIe 2.0 x16
	\| up to 2048
	\| 96:16:4		\| 96:16:4
			\| rowspan=2 \| 800
	\| 938
	\| ~~1876~~		\| 1600
			\| rowspan=2 \| 1600
	\| 2000
	\| ?		\|2.5
	\| ?		\|10
			\| rowspan=2 \| up to 2048
	\| 16.0
			\| rowspan=2 \| 12.8
	\| DDR3
	\| 64		\| rowspan=2 \| 64
	\| 11		\|240
			\|33
	\| 4.3
			\|
			\|-
			\| December 25, 2013
			\| GK208
			\| 192:16:8
			\| 800
			\| 2.9
			\| 11.5
	\| 1.2		\| 1.2
	\| ?		\| 276
	\| ?		\| 33
	\|		\|
	\|-		\|-
	! style="text-align:left;" \| GeForce GT 730M ~~<ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-730M.84681.0.html</ref>~~<ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-730m/specifications</ref>		! style="text-align:left;" rowspan=2 \| GeForce GT 730M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-730m/specifications\|title=GeForce GT 730M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
	\| GK107~~/GK208~~		\| GK107
			\| PCIe 3.0 x16
	\| 28
	\| PCIe 2.0/3.0 x16
	\| up to 4096
	\| 384:32:16		\| 384:32:16
	\| 725		\| rowspan=2 \| 725
	\| 725		\| rowspan=2 \| 725
	\| ~~1800~~ - ~~4000~~		\| rowspan=2 \| 1800
	\| ?		\|5.8
	\| ?		\|23
			\| rowspan=2 \| up to 2048
	\| 14.4 - 64.0
			\| rowspan=2 \| 14.4 – 64.0
	\| DDR3/GDDR5
			\| rowspan=2 \| DDR3 GDDR5
	\| 64/128
	\| 11		\| 128
	\| 4.1		\| rowspan=2 \| 1.1
			\| rowspan=2 \| 552.2
	\| Yes
			\| rowspan=2 \| 33
	\| ?
	\| ?
	\|		\|
	\|-		\|-
			\| March 6, 2014
	! style="text-align:left;" \| GeForce GT 735M <ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-735M.90246.0.html</ref><ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-735m/specifications</ref>
			\| rowspan="2" \| GK208
			\| PCIe 2.0 x8
			\| 384:16:8
			\| 5.8
			\| 11.5
			\| 64
			\|
			\|-
			! style="text-align:left;" \| GeForce GT 735M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-735m/specifications\|title=GeForce GT 735M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
			\| PCIe 2.0 x8
	\| GK208
			\| 384:32:8
	\| 28
	\| PCIe 3.0 x16
	\| up to 2048
	\| 384:32:16
	\| 889		\| 889
	\| 889		\| 889
	\| 2000		\| 2000
	\| ?		\|4.6
	\| ?		\|9.2
			\| up to 2048
	\| 16.0		\| 16.0
	\| DDR3		\| DDR3
	\| 64		\| 64
	\| 11
	\| 4.3
	\| 1.2		\| 1.2
			\|441.6
	\| ?
	\| ?		\|33
	\|		\|
	\|-		\|-
	! style="text-align:left;" \| GeForce GT 740M ~~<ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-740M.89900.0.html</ref>~~<ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-740m/specifications</ref>		! style="text-align:left;" rowspan=2 \| GeForce GT 740M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-740m/specifications\|title=GeForce GT 740M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
	\| GK107/?		\| GK107
	\| 28
	\| PCIe 3.0 x16		\| PCIe 3.0 x16
	\| ?
	\| 384:32:16		\| 384:32:16
	\| 810		\| 810-1033
	\| 810		\| 810-1033
	\| 1800/3600		\| rowspan=2 \| 1800/3600
	\| ?		\| 6.48
	\| ?		\| 25.9
			\| rowspan=2 \| up to 2048
	\| ?
			\| rowspan=2 \| 14.4 – 57.6
	\| DDR3/GDDR5
			\| rowspan="4" \| DDR3 GDDR5
	\| 128/?
	\| 11		\| 128
	\| 4.3		\| 1.1
	\| 1.2		\|622.1
	\| ?		\|45
	\| ?
	\|		\|
	\|-		\|-
			\| June 20, 2013
	! style="text-align:left;" \| GeForce GT 745M <ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-745M.90244.0.html</ref><ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-745m/specifications</ref>
			\| GK208
			\| PCIe 3.0 x8
			\| 384:32:8
			\| 980-1033
			\| 980-1033
			\| 8.3
			\| 33.1
			\| 64
			\| rowspan="2" \| 1.2
			\| 752.6
			\| 33
			\|
			\|-
			! style="text-align:left;" \| GeForce GT 745M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-745m/specifications\|title=GeForce GT 745M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
	\| GK107		\| rowspan="3" \| GK107
			\| rowspan="7" \| PCIe 3.0 x16
	\| 28
	\| PCIe 3.0 x16
	\| up to 2048
	\| 384:32:16		\| 384:32:16
	\| 837		\| 837
	\| 837		\| 837
	\| 2000 - 5000		\| 2000 – 5000
			\|4.39
	\| ?
			\|17.6
	\| ?
	\| ~~32.0~~ - ~~80.0~~		\| up to 2048
			\| 32.0 – 80.0
	\| DDR3/GDDR5
	\| 128		\| 128
	\| 11		\| 642.8
			\|45
	\| 4.2
	\| 1.2
	\| ?
	\| ?
	\|		\|
	\|-		\|-
	! style="text-align:left;" \| GeForce GT 750M ~~<ref>http://www.notebookcheck.net/NVIDIA-GeForce-GT-750M.90245.0.html</ref>~~<ref>http://www.geforce.com/hardware/notebook-gpus/geforce-gt-750m/specifications</ref>		! style="text-align:left;" \| GeForce GT 750M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-750m/specifications\|title=GeForce GT 750M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
	\| April 1, 2013		\| April 1, 2013
	\| GK107
	\| 28
	\| PCIe 3.0 x16
	\| up to 2048
	\| 384:32:16		\| 384:32:16
	\| 967		\| 967
	\| 967		\| 967
	\| 2000 - 5000		\| 2000 – 5000
			\|7.53
	\| ?
			\|30.1
	\| ?
	\| 32 - 80		\| up to 4096
			\| 32 – 80
	\| DDR3/GDDR5
	\| 128		\| 128
			\| rowspan="3" \| 1.1
	\| 11
	\| 4.2		\| 722.7
			\|50
	\| 1.2
	\| ?		\|
	\| ?		\|-
			! style="text-align:left;" \| GeForce GT 755M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gt-755m/specifications\|title=GeForce GT 755M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| {{unk}}
			\| 384:32:16
			\| 1020
			\| 1020
			\| 5400
			\|15.7
			\|31.4
			\| up to 2048
			\| 86.4
			\| rowspan="5" \| GDDR5
			\| 128
			\|752.6
			\|50
			\|
			\|-
			! style="text-align:left;" \| GeForce GTX 760M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gtx-760m/specifications\|title=GeForce GTX 760M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| May 30, 2013
			\| rowspan="3" \| GK106
			\| 768:64:16
			\| 657
			\| 657
			\| 4008
			\|10
			\|40.2
			\| 2048
			\| 64.1
			\| 128
			\|964.6
			\|55
			\|
			\|-
			! style="text-align:left;" \| GeForce GTX 765M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gtx-765m/specifications\|title=GeForce GTX 765M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| May 30, 2013
			\| 768:64:16
			\| 850
			\| 850
			\| 4008
			\|12.8
			\|51
			\| 2048
			\| 64.1
			\| 128
			\| rowspan="3" \| 1.2
			\|1224
			\|75
			\|
			\|-
			! style="text-align:left;" \| GeForce GTX 770M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gtx-770m/specifications\|title=GeForce GTX 770M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| May 30, 2013
			\| 960:80:24
			\| 811
			\| 811
			\| 4008
			\|14.1
			\|56.5
			\| 3072
			\| 96.2
			\| 192
			\|1356
			\|75
			\|
			\|-
			! style="text-align:left;" \| GeForce GTX 780M<ref>{{cite web\|url=http://www.geforce.com/hardware/notebook-gpus/geforce-gtx-780m/specifications\|title=GeForce GTX 780M - Specifications - GeForce\|website=www.geforce.com\|access-date=April 18, 2018}}</ref>
			\| May 30, 2013
			\| GK104
			\| 1536:128:32
			\| 823
			\| 823
			\| 5000
			\|24.7
			\|98.7
			\| 4096
			\| 160.0
			\| 256
			\|2369
			\|100
	\|		\|
	\|-		\|-
	\|}		\|}

			{{notelist}}
	== Chipset table ==

	{{Main\|Comparison of Nvidia graphics processing units#GeForce 700 Series\|l1=Comparison table of GeForce 700 Series}}
			==Chipset table==
			===GeForce 700 (7xx) series===
			{{See also\|List of Nvidia graphics processing units#GeForce 700 series\|l1=Comparison table of GeForce 700 Series}}
			{{row hover highlight}}
			{{sort under}}
			{\| class="wikitable sortable sort-under mw-datatable" style="font-size: 80%; text-align: center;"
			\|-
			! rowspan="2" \| Model
			! rowspan="2" \| Launch
			! rowspan="2" \| ]
			! rowspan="2" \| Fab (])
			! rowspan="2" \| Transistors (million)
			! rowspan="2" \| Die size (mm<sup>2</sup>)
			! rowspan="2" \| ] ]
			! rowspan="2" \| SMX count
			! rowspan="2" \| Core config{{efn\|name=geforce 700 1\|]: ]s: ]s}}
			! colspan="4" \| Clock rate
			! colspan="2" \| ]
			! colspan="4" \| Memory configuration
			! colspan="4" \| Supported ] version
			! colspan="2" \| Processing power (]){{efn\|name=geforce 700 9\|To calculate the processing power see ], or ].}}
			! rowspan="2" \| ] (Watts)
			! rowspan="2" \| Release Price (USD)
			\|-
			! Base (])
			! Average Boost (])
			! Max Boost{{efn\|name=geforce 700 2}} (])
			! Memory (])
			! Pixel (]/s)
			! Texture (]/s)
			! Size (])
			! Bandwidth (]/s)
			! DRAM type
			! Bus width (])
			! ]{{efn\|name=geforce 700 11\|Maxwell supports Vulkan version 1.3, while Kepler only support Vulkan version 1.2, Fermi does not support the Vulkan API at all.<ref name="vulkandrv">{{cite web \| url=https://www.khronos.org/conformance/adopters/conformant-products \| title=The Khronos Group \| date=31 May 2022 }}</ref>}}
			! ]{{efn\|name=geforce 700 3\|Kepler supports some optional 11.1 features on ] 11_0 through the Direct3D 11.1 API, however Nvidia did not enable four non-gaming features to qualify Kepler for level 11_1.<ref>{{cite web \|url=http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html \|title=Nvidia Kepler not fully compliant with Direct3D 11.1 \|website=Guru3d.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151222113454/http://www.guru3d.com/news_story/nvidia_kepler_not_fully_compliant_with_directx_11_1.html \|archive-date=2015-12-22 \|url-status=live }}</ref><ref> {{webarchive \|url=https://web.archive.org/web/20130903174514/http://www.brightsideofnews.com/news/2012/11/21/nvidia-doesnt-fully-support-directx-111-with-kepler-gpus2c-bute280a6.aspx \|date=September 3, 2013 }}</ref>}}
			! ]
			! ]
			! ]
			! ]
			\|-
			! style="text-align:left;" \| GeForce GT 705<ref>{{cite web \|url=http://www.techpowerup.com/gpudb/2578/geforce-gt-705.html \|title=Nvidia GeForce GT 705 {{pipe}} techPowerUp GPU Database \|website=Techpowerup.com \|access-date=2015-12-11 \|archive-url=https://archive.today/20140615091732/http://www.techpowerup.com/gpudb/2578/geforce-gt-705.html \|archive-date=2014-06-15 \|url-status=live }}</ref>{{efn\|name=geforce 700 4\|The GeForce GT 705 (OEM) is a rebranded GeForce GT 610, which itself is a rebranded GeForce GT 520.}}
			\| rowspan="2" \| March 27, 2014
			\| GF119-300-A1
			\| ] 40 nm
			\| 292
			\| 79
			\| PCIe 2.0 x16
			\| rowspan="4" \| 1
			\| 48:8:4
			\| 810
			\| {{n/a}}
			\| {{n/a}}
			\| 898<br />(1796)
			\| 3.24
			\| 6.5
			\| 512<br />1024
			\| rowspan="2" \| 14.4
			\| rowspan="2" \| DDR3
			\| 64
			\| n/a
			\| rowspan="21" \| 12
			\| rowspan="20" \| 4.6
			\| 1.1
			\| 155.5
			\| 19.4
			\| 29
			\| rowspan="2" \| OEM
			\|-
			! rowspan="2" style="text-align:left;" \| GeForce GT 710<ref>{{cite web \|url=http://www.techpowerup.com/gpudb/1990/geforce-gt-710.html \|title=Nvidia GeForce GT 710 {{pipe}} techPowerUp GPU Database \|website=Techpowerup.com \|access-date=2015-12-11 \|archive-url=https://archive.today/20140615091722/http://www.techpowerup.com/gpudb/1990/geforce-gt-710.html \|archive-date=2014-06-15 \|url-status=live }}</ref>
			\| GK208-301-A1
			\| rowspan="5" \| TSMC 28 nm
			\| rowspan="5" \| 1020
			\| rowspan="5" \| 79
			\| PCIe 2.0 x8
			\| 192:16:8
			\| 823
			\| {{n/a}}
			\| {{n/a}}
			\| 900 (1800)
			\| 6.6
			\| 13.2
			\| 512
			\| rowspan="5" \| 64
			\| rowspan="5" \| 1.2
			\| rowspan="5" \| 1.2
			\| 316.0
			\| 13.2
			\|
			\|-
			\| January 26, 2016
			\| GK208-203-B1
			\| PCIe 2.0 x8, PCIe x1
			\| 192:16:8
			\| 954
			\| {{n/a}}
			\| {{n/a}}
			\| 900 (1800)<br />1253 (5010)
			\| 7.6
			\| 15.3
			\| 1024<br />2048
			\| 14.4<br />40.0
			\| rowspan="2" \| DDR3<br />GDDR5
			\| 366
			\| 15.3
			\| rowspan="2" \| 19
			\| $35–45
			\|-
			! style="text-align:left;" \| GeForce GT 720<ref>{{cite web \|url=http://www.techpowerup.com/gpudb/1989/geforce-gt-720.html \|title=Nvidia GeForce GT 720 {{pipe}} techPowerUp GPU Database \|website=Techpowerup.com \|access-date=2015-12-11 \|archive-url=https://archive.today/20140615091724/http://www.techpowerup.com/gpudb/1989/geforce-gt-720.html \|archive-date=2014-06-15 \|url-status=live }}</ref>
			\| March 27, 2014
			\| GK208-201-B1
			\| rowspan="3" \| PCIe 2.0 x8
			\| 192:16:8
			\| 797
			\| {{n/a}}
			\| {{n/a}}
			\| 900 (1800)<br />1253 (5010)
			\| 6.4
			\| 12.8
			\| 1024<br />2048
			\| 14.4<br />40.0
			\| 306
			\| 12.8
			\| $49–59
			\|-
			! rowspan="3" style="text-align:left;" \| GeForce GT 730<br /><ref name="gt730">{{cite web \|url=http://www.geforce.com/hardware/desktop-gpus/geforce-gt-730/specifications \|title=GT 730 {{pipe}} Specifications \|website=GeForce.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151212232644/http://www.geforce.com/hardware/desktop-gpus/geforce-gt-730/specifications \|archive-date=2015-12-12 \|url-status=live }}</ref>{{efn\|name=geforce 700 5\|The GeForce GT 730 (DDR3, 64-bit) is a rebranded GeForce GT 630 (Rev. 2).}}{{efn\|name=geforce 700 6\|The GeForce GT 730 (DDR3, 128-bit) is a rebranded GeForce GT 630 (128-bit).}}
			\| rowspan="3" \| June 18, 2014
			\| GK208-301-A1
			\| rowspan="5" \| 2
			\| 384:16:8
			\| 902
			\| {{n/a}}
			\| {{n/a}}
			\| 900<br />(1800)
			\| 7.22
			\| 14.44
			\| 1024<ref name="1GBgt730">{{cite web\|url=https://www.zotac.com/product/graphics_card/gt-730-1gb\|title=GeForce GT 730 1GB-ZOTAC\|work=]\|access-date=July 12, 2017\|archive-url=https://web.archive.org/web/20160719212714/https://www.zotac.com/product/graphics_card/gt-730-1gb\|archive-date=July 19, 2016\|url-status=live}}</ref><br />2048<br />4096
			\| 14.4
			\| DDR3
			\| rowspan="2" \| 692.7
			\| rowspan="2" \| 28.9
			\| 23
			\| rowspan="3" \| $69–79
			\|-
			\| GK208-400-A1
			\| 384:16:8
			\| 902
			\| {{n/a}}
			\| {{n/a}}
			\| 1250<br />(5000)
			\| 7.22
			\| 14.44
			\| 1024<br />2048<ref>{{cite web \|url=http://www.evga.com/products/product.aspx?pn=02G-P3-3733-KR \|title=EVGA - Products - EVGA GeForce GT 730 2GB (Low Profile) - 02G-P3-3733-KR \|access-date=2017-04-29 \|archive-url=https://web.archive.org/web/20170215122047/http://www.evga.com/Products/Product.aspx?pn=02G-P3-3733-KR \|archive-date=2017-02-15 \|url-status=live }}</ref>
			\| 40.0
			\| GDDR5
			\| 25
			\|-
			\| GF108
			\| TSMC 40 nm
			\| 585
			\| 116
			\| PCIe 2.0 x16
			\| 96:16:4
			\| 700
			\| {{n/a}}
			\| {{n/a}}
			\| 900<br />(1800)
			\| 2.8
			\| 11.0
			\| rowspan="3" \| 1024<br />2048<br />4096
			\| 28.8
			\| rowspan="2" \| DDR3
			\| 128
			\| n/a
			\| 1.1
			\| 268.8
			\| 33.6
			\| 49
			\|-
			! rowspan="2" style="text-align:left;" \| GeForce GT 740{{efn\|name=geforce 700 7\|The GeForce GT 740 (OEM) is a rebranded GeForce GTX 650.}}
			\| rowspan="2" \| May 29, 2014
			\| rowspan="2" \| GK107-425-A2
			\| rowspan="14" \| ]<br />28HP
			\| rowspan="2" \| 1270
			\| rowspan="2" \| 118
			\| rowspan="14" \| PCIe 3.0 x16
			\| 384:32:16
			\| 993
			\| {{n/a}}
			\| {{n/a}}
			\| 891<br />(1782)
			\| 15.9
			\| 31.8
			\| 28.5
			\| rowspan="5" \| 128
			\| rowspan="2" \| 1.2
			\| rowspan="14" \| 1.2
			\| rowspan="2" \| 762.6
			\| rowspan="2" \| 31.8
			\| rowspan="2" \| 64
			\| rowspan="2" \| $89–99
			\|-
			\| 384:32:16
			\| 993
			\| {{n/a}}
			\| {{n/a}}
			\| 1252<br />(5008)
			\| 15.9
			\| 31.8
			\| 80.1
			\| GDDR5
			\|-
			! style="text-align:left;" \| GeForce GTX 745
			\| rowspan="3" \| February 18, 2014
			\| GM107-220-A2
			\| rowspan="3" \| 1870
			\| rowspan="3" \| 148
			\| 3
			\| 384:24:16
			\| 1033
			\| {{unk}}
			\| {{unk}}
			\| 900<br />(1800)
			\| 16.5
			\| 24.8
			\| 1024<br />4096
			\| 28.8
			\| DDR3
			\| rowspan="3" \| 1.3
			\| 793.3
			\| 24.8
			\| rowspan="2" \| 55
			\| OEM
			\|-
			! style="text-align:left;" \| GeForce GTX 750
			\| GM107-300-A2
			\| 4
			\| 512:32:16
			\| 1020
			\| 1085
			\| 1163
			\| 1250<br />(5000)
			\| 16.3
			\| 32.6
			\| 1024<br />2048<br />4096<ref>{{cite web\|title=AFOX GTX 750 4 GB Specs\|url=https://www.techpowerup.com/gpu-specs/afox-gtx-750-4-gb.b9074\|access-date=2021-08-11\|website=TechPowerUp\|language=en}}</ref>
			\| 80
			\| rowspan="11" \| GDDR5
			\| 1044.5
			\| 32.6
			\| $119
			\|-
			! style="text-align:left;" \| GeForce GTX 750 Ti
			\| GM107-400-A2
			\| 5
			\| 640:40:16
			\| 1020
			\| 1085
			\| 1200
			\| 1350<br />(5400)
			\| 16.3
			\| 40.8
			\| 1024<br />2048<br />4096
			\| 86.4
			\| 1305.6
			\| 40.8
			\| 60
			\| $149
			\|-
			! style="text-align:left;" \| GeForce GTX 760 192-bit
			\| October 17, 2013
			\| GK104-200-KD-A2
			\| rowspan="4" \| 3540
			\| rowspan="4" \| 294
			\| rowspan="2" \| 6
			\| 1152:96:24
			\| 824
			\| 888
			\| 889
			\| 1450<br />(5800)
			\| 19.8
			\| 79.1
			\| 1536<br />3072
			\| 139.2
			\| 192
			\| rowspan="9" \| 1.2
			\| 1896.2
			\| 79.0
			\| 130
			\| OEM
			\|-
			! style="text-align:left;" \| GeForce GTX 760
			\| June 25, 2013
			\| GK104-225-A2
			\| 1152:96:32
			\| 980
			\| 1033
			\| 1124
			\| 1502<br />(6008)
			\| 31.4{{efn\|name=geforce 700 10}}
			\| 94
			\| 2048<br />4096
			\| 192.3
			\| rowspan="3" \| 256
			\| 2257.9
			\| 94.1
			\| rowspan="2" \| 170
			\| $249 ($219)
			\|-
			! style="text-align:left;" \| GeForce GTX 760 Ti{{efn\|name=geforce 700 8\|The GeForce GTX 760 Ti (OEM) is a rebranded GeForce GTX 670.}}
			\| September 27, 2013<ref>{{cite web \|url=https://www.techpowerup.com/gpudb/2491/geforce-gtx-760-ti-oem \|title=NVIDIA GeForce GTX 760 Ti OEM Specs \|access-date=2018-08-06 \|archive-url=https://archive.today/20160530101755/http://www.techpowerup.com/gpudb/2491/geforce-gtx-760-ti-oem \|archive-date=2016-05-30 \|url-status=live }}</ref>
			\| GK104
			\| 7
			\| 1344:112:32
			\| 915
			\| 980
			\| 1084
			\| 1502<br />(6008)
			\| 29.3
			\| 102.5
			\| 2048
			\| 192.3
			\| 2459.5
			\| 102.5
			\| OEM
			\|-
			! style="text-align:left;" \| GeForce GTX 770
			\| May 30, 2013
			\| GK104-425-A2
			\| 8
			\| 1536:128:32
			\| 1046
			\| 1085
			\| 1130
			\| 1752.5<br />(7010)
			\| 33.5
			\| 134
			\| 2048 4096
			\| 224
			\| 3213.3
			\| 133.9
			\| rowspan="5" \| 230
			\| $399 ($329)
			\|-
			! style="text-align:left;" \| GeForce GTX 780
			\| May 23, 2013
			\| GK110-300-A1
			\| rowspan="4" \| 7080
			\| rowspan="4" \| 561
			\| 12
			\| 2304:192:48
			\| 863
			\| 900
			\| 1002
			\| 1502<br />(6008)
			\| 41.4{{efn\|name=geforce 700 10}}
			\| 160.5
			\| 3072 6144<ref>{{cite web \|url=http://www.evga.com/articles/00830/ \|title=Articles - EVGA GeForce GTX 780 6GB Step-Up Available Now! \|publisher=EVGA \|date=2014-03-21 \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20160113203734/http://www.evga.com/articles/00830/ \|archive-date=2016-01-13 \|url-status=live }}</ref>
			\| 288.4
			\| rowspan="4" \| 384
			\| 3976.7
			\| 165.7
			\| $649 ($499)
			\|-
			! style="text-align:left;" \| GeForce GTX 780 Ti<ref>{{cite web \|url=http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-780-ti/specifications \|title=GeForce GTX780 Ti. Specifications \|website=Geforce.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151212021141/http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-780-ti/specifications \|archive-date=2015-12-12 \|url-status=live }}</ref><ref>{{cite web \|url=http://videocardz.com/47508/videocardz-nvidia-geforce-gtx-780-ti-2880-cuda-cores \|title=Nvidia GeForce GTX 780 Ti has 2880 CUDA cores \|website=Videocardz.com \|date=31 October 2013 \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151222120538/http://videocardz.com/47508/videocardz-nvidia-geforce-gtx-780-ti-2880-cuda-cores \|archive-date=2015-12-22 \|url-status=live }}</ref><ref>{{cite web \|url=http://web-engage.augure.com/pub/link/282593/04601926874847631383752919307-hl-com.com.html \|title=PNY dévoile son nouveau foudre de guerre: la GeForce GTX 780 TI. \|website=Web-engage.augure.com \|access-date=2015-12-11 \|url-status=dead \|archive-url=https://web.archive.org/web/20131109211440/http://web-engage.augure.com/pub/link/282593/04601926874847631383752919307-hl-com.com.html \|archive-date=November 9, 2013 }}</ref>
			\| November 7, 2013
			\| GK110-425-B1
			\| 15
			\| 2880:240:48
			\| 876
			\| 928
			\| 1019
			\| 1752.5<br />(7010)
			\| 42.0{{efn\|name=geforce 700 10\|As a Kepler GPC is able to rasterize 8 pixels per clock, fully enabled GK110 GPUs (780 Ti/TITAN Black) can only output 40 pixels per clock (5 GPCs), despite 48 ROPs and all SMX units being physically present. For GTX 780 and GTX 760, multiple GPC configurations with differing pixel fillrate are possible, depending on which SMXs were disabled in the chip: 5/4 GPCs, or 4/3 GPCs, respectively.}}
			\| 210.2
			\| 3072
			\| 336.5
			\| 5045.7
			\| 210.2
			\| $699
			\|-
			! style="text-align:left;" \| GeForce GTX TITAN<ref>{{cite web \|url=http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-titan \|title=GeForce GTX TITAN \|website=Geforce.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151205173714/http://www.geforce.com/hardware/desktop-gpus/geforce-gtx-titan \|archive-date=2015-12-05 \|url-status=live }}</ref><ref>{{cite web \|url=http://www.nvidia.com/titan-graphics-card \|title=TITAN Graphics Card \|website=Nvidia.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20130224082627/http://www.nvidia.com/titan-graphics-card \|archive-date=2013-02-24 \|url-status=live }}</ref><ref>{{cite web \|url=http://www.anandtech.com/show/6760/nvidias-geforce-gtx-titan-part-1 \|title=Nvidia's GeForce GTX Titan, Part 1: Titan For Gaming, Titan For Compute \|website=Anandtech.com \|access-date=2015-12-11 \|archive-url=https://web.archive.org/web/20151204225432/http://www.anandtech.com/show/6760/nvidias-geforce-gtx-titan-part-1 \|archive-date=2015-12-04 \|url-status=live}}</ref>
			\| February 21, 2013
			\| GK110-400-A1
			\| 14
			\| 2688:224:48
			\| 837
			\| 876
			\| 993
			\| 1502<br />(6008)
			\| 40.2
			\| 187.5
			\| rowspan="2" \| 6144
			\| 288.4
			\| 4499.7
			\| 1300<ref>{{cite web \|url=http://www.anandtech.com/show/6774/nvidias-geforce-gtx-titan-part-2-titans-performance-unveiled/3 \|title=Titan's Compute Performance (aka Ph.D Lust) - Nvidia's GeForce GTX Titan Review, Part 2: Titan's Performance Unveiled \|website=Anandtech.com \|access-date=2015-12-11 \|quote=the calculated fp64 peak of Titan is 1.5 TFlops. However, under heavy load in fp64 mode, the card may underclock below the listed 837MHz to remain within the power and thermal specifications \|archive-url=https://web.archive.org/web/20151222141607/http://www.anandtech.com/show/6774/nvidias-geforce-gtx-titan-part-2-titans-performance-unveiled/3 \|archive-date=2015-12-22 \|url-status=live }}</ref>-1499.9
			\| rowspan="2" \| $999
			\|-
			! style="text-align:left;" \| GeForce GTX TITAN Black
			\| February 18, 2014
			\| GK110-430-B1
			\| 15
			\| 2880:240:48
			\| 889
			\| 980
			\| 1058
			\| 1752.5<br />(7010)
			\| 42.7
			\| 213.4
			\| 336.5
			\| 5120.6
			\| 1706.9
			\|-
			! style="text-align:left;" \| GeForce GTX TITAN Z
			\| May 28, 2014
			\| 2x GK110-350-B1<ref>{{cite web\|url=https://diy.pconline.com.cn/488/4883359_all.html\|title=售价21999元！NV旗舰GTX TITAN Z评测-太平洋电脑网\|date=5 June 2014\|access-date=2020-08-16}}</ref>
			\| 2x 7080
			\| 2x 561
			\| 2x 15
			\| 2x 2880:240:48
			\| 705
			\| 876
			\| {{unk}}
			\| 1752.5<br />(7010)
			\| 2x 33.8
			\| 2x 169
			\| 2x 6144
			\| 2x 336.5
			\| 2x 384
			\| 4.5
			\| 5046x2
			\| 1682x2<ref>{{cite web\|url=https://www.techpowerup.com/gpu-specs/geforce-gtx-titan-z.c2575\|title=NVIDIA GeForce GTX TITAN Z Specs\|website=TechPowerUp\|language=en\|access-date=2020-02-26}}</ref>
			\| 375
			\| $2999
			\|-
			! rowspan="2" \| Model
			! rowspan="2" \| Launch
			! rowspan="2" \| ]
			! rowspan="2" \| Fab (])
			! rowspan="2" \| Transistors (million)
			! rowspan="2" \| Die size (mm<sup>2</sup>)
			! rowspan="2" \| ] ]
			! rowspan="2" \| SMX count
			! rowspan="2" \| Core config{{efn\|name=geforce 700 1\|]: ]s: ]s}}
			! colspan="4" \| Clock rate
			! colspan="2" \| ]
			! colspan="4" \| Memory configuration
			! colspan="4" \| Supported ] version
			! colspan="2" \| Processing power (]){{efn\|name=geforce 700 8\|The GeForce GTX 760 Ti (OEM) is a rebranded GeForce GTX 670.}}
			! rowspan="2" \| ] (Watts)
			! rowspan="2" \| Release Price (USD)
			\|-
			! Base (])
			! Average Boost (])
			! Max Boost{{efn\|name=geforce 700 2\|Max Boost depends on ASIC quality. For example, some GTX TITAN with over 80% ASIC quality can hit 1019 MHz by default, lower ASIC quality will be 1006 MHz or 993 MHz.}} (])
			! Memory (])
			! Pixel (]/s)
			! Texture (]/s)
			! Size (])
			! Bandwidth (]/s)
			! DRAM type
			! Bus width (])
			! ]
			! ]{{efn\|name=geforce 700 3}}
			! ]
			! ]
			! ]
			! ]
			\|}
			{{notelist}}

			== Discontinued support ==
			Nvidia stopped releasing 32-bit drivers for 32-bit operating systems after the last Release 390.x driver, 391.35, was released in March 2018.<ref>{{cite web\|url=http://nvidia.custhelp.com/app/answers/detail/a_id/4604/\|title=Support Plan for 32-bit and 64-bit Operating Systems - NVIDIA\|website=nvidia.custhelp.com\|access-date=April 18, 2018}}</ref>

			Kepler notebook GPUs moved to legacy support in April 2019 and stopped receiving security updates in April 2020.<ref>{{Cite web\|url=https://nvidia.custhelp.com/app/answers/detail/a_id/4779\|title = Support Plan for Kepler-series GeForce GPUs for notebooks \| NVIDIA}}</ref> All notebook GPUs from the 7xxM family were affected by this change.

			Nvidia announced that after Release 470 drivers, it would transition driver support for the Windows 7 and Windows 8.1 operating systems to legacy status and continue to provide critical security updates for these operating systems through September 2024.<ref>{{Cite web\|url=https://nvidia.custhelp.com/app/answers/detail/a_id/5201\|title = Support Plan for Windows 7 and Windows 8/8.1 \| NVIDIA}}</ref>

			Nvidia announced that all remaining Kepler desktop GPUs would transition to legacy support from September 2021 onwards and be supported for critical security updates through September 2024.<ref>{{Cite web\|url=https://nvidia.custhelp.com/app/answers/detail/a_id/5202\|title = Support Plan for Kepler-series GeForce GPUs for Desktop \| NVIDIA}}</ref> The Nvidia GeForce GTX 745, 750 and 750 Ti from the 7xx desktop GPU family would not be affected by this change.

			In Windows ,the last driver to fully support CUDA with 64-Bit Compute Capability 3.5 for Kepler in Windows 7 and Windows 8.1 64-bit is 388.71, tested with latest CUDA-Z and GPU-Z, after that driver, the 64-Bit CUDA support becomes broken for GeForce 700 series GK110 with Kepler architecture.

			The last driver where monitor type detection is working properly on Windows XP is 352.86.<ref>{{Cite web\|title=Anyway to Change Monitor Type Shown in Nvidia Control Panel? \ VOGONS\|url=https://www.vogons.org/viewtopic.php?p=827282#p827282\|access-date=2021-01-31\|website=www.vogons.org}}</ref>

	== See also ==		== See also ==
	* ]		* ]
	* ]		* ]
	* ]		* ]
	* ]		* ]
	* ]		* ]
	* ]		* ]
	* ]		* ]
	* ]		* ]

			==Notes==
			{{Notelist}}

	== References ==		== References ==
	{{Reflist}}		{{Reflist\|30em}}

	==External links==		==External links==
			{{commons category\|Nvidia GeForce 700 series video cards}}
	{{refbegin\|4}}
			{{refbegin\|20em}}
	*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
			*
	*		*
	*		*
Line 240:		Line 942:
	*		*
	*		*
			*
			*
			*
	{{refend}}		{{refend}}

	{{Nvidia}}		{{Nvidia}}

	]		]
	]		]
	]		]
	]

	]
	]
	]

Latest revision as of 16:53, 15 December 2024

For GeForce cards with a model number of 7XX0, see GeForce 7 series. Series of GPUs by Nvidia

GeForce 700 series
Cards
GTX Titan Z released in May of 2013; the series' flagship unit sporting dual Kepler GK110 processors and the final Nvidia graphics card supporting dual-GPU configuration on a single PCB board.
Release date	February 19, 2013; 11 years ago (February 19, 2013)
Codename	GK110 GK208 GM108 GM107
Architecture	Fermi Kepler Maxwell
Models	GeForce series GeForce GT series GeForce GTX series
Transistors	292M (GF119) 40 nm 585M (GF117) 28 nm 1.02B (GK208) 28 nm 1.27B (GK107) 28 nm 2.54B (GK106) 28 nm 3.54B (GK104) 28 nm 7.08B (GK110) 28 nm
Fabrication process	TSMC 40 nm TSMC 28 nm
Entry-level	GeForce GT 705 GeForce GT 710 GeForce GT 720 GeForce GT 730 GeForce GT 740 GeForce GTX 745
Mid-range	GeForce GTX 750 GeForce GTX 750 Ti GeForce GTX 760 192-Bit GeForce GTX 760 GeForce GTX 760 Ti GeForce GTX 770
High-end	GeForce GTX 780
Enthusiast	GeForce GTX 780 Ti GeForce GTX Titan GeForce GTX Titan Black GeForce GTX Titan Z
API support
DirectX	Direct3D 12.0 (feature level 11_0) Shader Model 6.7 (Maxwell), Shader Model 6.5 (Kepler) or Shader Model 5.1 (Fermi)
OpenCL	OpenCL 3.0
OpenGL	OpenGL 4.6
Vulkan	Vulkan 1.2 SPIR-V
History
Predecessor	GeForce 600 series
Variant	GeForce 800M series
Successor	GeForce 900 series
Support status
Fermi and Kepler unsupported. Maxwell fully supported.

The GeForce 700 series (stylized as GEFORCE GTX 700 SERIES) is a series of graphics processing units developed by Nvidia. While mainly a refresh of the Kepler microarchitecture (GK-codenamed chips), some cards use Fermi (GF) and later cards use Maxwell (GM). GeForce 700 series cards were first released in 2013, starting with the release of the GeForce GTX Titan on February 19, 2013, followed by the GeForce GTX 780 on May 23, 2013. The first mobile GeForce 700 series chips were released in April 2013.

Overview

GK110 was designed and marketed with computational performance in mind. It contains 7.1 billion transistors. This model also attempts to maximise energy efficiency through the execution of as many tasks as possible in parallel according to the capabilities of its streaming processors.

With GK110, increases in memory space and bandwidth for both the register file and the L2 cache over previous models, are seen. At the SMX level, GK110's register file space has increased to 256KB composed of 64K 32bit registers, as compared to Fermi's 32K 32bit registers totaling 128 KB. As for the L2 cache, GK110 L2 cache space increased by up to 1.5MB, 2x as big as GF110. Both the L2 cache and register file bandwidth have also doubled. Performance in register-starved scenarios is also improved as there are more registers available to each thread. This goes in hand with an increase of total number of registers each thread can address, moving from 63 registers per thread to 255 registers per thread with GK110.

With GK110, Nvidia also reworked the GPU texture cache to be used for compute. With 48KB in size, in compute the texture cache becomes a read-only cache, specializing in unaligned memory access workloads. Furthermore, error detection capabilities have been added to make it safer for use with workloads that rely on ECC.

Dynamic Super Resolution (DSR) was added to Kepler GPUs with the latest Nvidia drivers.

Architecture

Main articles: Fermi (microarchitecture), Kepler (microarchitecture), and Maxwell (microarchitecture)

The GeForce 700 series contains features from both GK104 and GK110. Kepler based members of the 700 series add the following standard features to the GeForce family.

Derived from GK104:

PCI Express 3.0 interface
DisplayPort 1.2
HDMI 1.4a 4K x 2K video output
Purevideo VP5 hardware video acceleration (up to 4K x 2K H.264 decode)
Hardware H.264 encoding acceleration block (NVENC)
Support for up to 4 independent 2D displays, or 3 stereoscopic/3D displays (NV Surround)
Bindless Textures
GPU Boost
TXAA
Manufactured by TSMC on a 28 nm process

New Features from GK110:

Compute Focus SMX Improvement
CUDA Compute Capability 3.5
New Shuffle Instructions
Dynamic Parallelism
Hyper-Q (Hyper-Q's MPI functionality reserve for Tesla only)
Grid Management Unit
Nvidia GPUDirect (GPU Direct's RDMA functionality reserve for Tesla & Quadro only)
GPU-Boost 2.0

Compute focus SMX improvement

With GK110, Nvidia opted to increase computational performance. The single biggest change from GK104 is that rather than 8 dedicated FP64 CUDA cores, GK110 has up to 64, giving it 8x the FP64 throughput of a GK104 SMX. The SMX also sees an increase in space for register file. Register file space has increased to 256KB compared to Fermi. The texture cache are also improved. With a 48KB space, the texture cache can become a read-only cache for compute workloads.

New shuffle Instructions

At a low level, GK110 sees additional instructions and operations to further improve performance. New shuffle instructions allow for threads within a warp to share data without going back to memory, making the process much quicker than the previous load/share/store method. Atomic operations are also overhauled, speeding up the execution speed of atomic operations and adding some FP64 operations that were previously only available for FP32 data.

NVENC

Main article: Nvidia NVENC

Hyper-Q

Hyper-Q expands GK110 hardware work queues from 1 to 32. The significance of this being that having a single work queue meant that Fermi could be under occupied at times as there wasn't enough work in that queue to fill every SM. By having 32 work queues, GK110 can in many scenarios, achieve higher utilization by being able to put different task streams on what would otherwise be an idle SMX. The simple nature of Hyper-Q is further reinforced by the fact that it's easily map to MPI, a common message passing interface frequently used in HPC. As legacy MPI-based algorithms that were originally designed for multi-CPU systems that became bottlenecked by false dependencies now have a solution. By increasing the number of MPI jobs, it's possible to utilize Hyper-Q on these algorithms to improve the efficiency all without changing the code itself.

Microsoft DirectX support

Nvidia Kepler GPUs of the GeForce 700 series fully support DirectX 11.0. All GeForce 700 series card also support DirectX 12.0 with feature level 11_0.

Dynamic parallelism

Dynamic parallelism ability is for kernels to be able to dispatch other kernels. With Fermi, only the CPU could dispatch a kernel, which incurs a certain amount of overhead by having to communicate back to the CPU. By giving kernels the ability to dispatch their own child kernels, GK110 can both save time by not having to go back to the CPU, and in the process free up the CPU to work on other tasks.

Products

GeForce 700 (7xx) series

The GeForce 700 series was designed for desktop architecture. Cheaper and lower performing products were expected to be released over time. Kepler supports 11.1 features with 11_0 feature level through the DirectX 11.1 API, however Nvidia did not enable four non-gaming features in Hardware in Kepler (for 11_1).

Shader Processors : Texture mapping units : Render output units
Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed
Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
Single precision performance is calculated as 2 times the number of shaders multiplied by the base core clock speed.
Double precision performance of the GTX Titan and GTX Titan Black is either 1/3 or 1/24 of single-precision performance depending on a user-selected configuration option in the driver that boosts single-precision performance if double-precision is set to 1/24 of single-precision performance, while other Kepler chips' double precision performance is fixed at 1/24 of single-precision performance. GeForce 700 series Maxwell chips' double precision performance is 1/32 of single-precision performance.
SLI supports connecting up to 4 identical graphics cards for a 4-way SLI configuration. Those supporting 4-way SLI can support 3-way & 2-way SLI, however a dual-GPU card already implements 2-way SLI internally, thus only 2 dual-GPU cards can be used in SLI to give a 4-way SLI configuration.

GeForce 700M (7xxM) series

Some implementations may use different specifications.

Unified shaders : Texture mapping units : Render output units

Model	Launch	Code name	Fab (nm)	Bus interface	Core config	Clock speed			Fillrate		Memory				API support (version)				Processing power (GFLOPS)	TDP (watts)	Notes
Model	Launch	Code name	Fab (nm)	Bus interface	Core config	Core (MHz)	Shader (MHz)	Memory (MT/s)	Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	Type	Bus width (bit)	DirectX	OpenGL	OpenCL	Vulkan	Processing power (GFLOPS)	TDP (watts)	Notes
GeForce 705M	June 1, 2013	GF119	40	PCIe 2.0 x16	48:8:4	775	1550	1800	1.48	5.9	up to 2048	?	DDR3	64	12.0 (11_0)	4.6	1.1	1.3	141.7	12	Rebadged 520M
GeForce 710M	April 1, 2013	GF117	28		96:16:4	775	1550	1800	3.1	12.4	up to 2048	14.4		64					297.6	15
GeForce GT 720M	April 1, 2013	GF117			96:16:4	800	1600	1600	2.5	10	up to 2048	12.8		64					240	33
GeForce GT 720M	December 25, 2013	GK208			192:16:8	800	800	1600	2.9	11.5	up to 2048	12.8		64			1.2		276	33
GeForce GT 730M	April 1, 2013	GK107		PCIe 3.0 x16	384:32:16	725	725	1800	5.8	23	up to 2048	14.4 – 64.0	DDR3 GDDR5	128			1.1		552.2	33
GeForce GT 730M	March 6, 2014	GK208		PCIe 2.0 x8	384:16:8	725	725	1800	5.8	11.5	up to 2048	14.4 – 64.0	DDR3 GDDR5	64			1.1		552.2	33
GeForce GT 735M	April 1, 2013	GK208		PCIe 2.0 x8	384:32:8	889	889	2000	4.6	9.2	up to 2048	16.0	DDR3	64			1.2		441.6	33
GeForce GT 740M	April 1, 2013	GK107		PCIe 3.0 x16	384:32:16	810-1033	810-1033	1800/3600	6.48	25.9	up to 2048	14.4 – 57.6	DDR3 GDDR5	128			1.1		622.1	45
GeForce GT 740M	June 20, 2013	GK208		PCIe 3.0 x8	384:32:8	980-1033	980-1033	1800/3600	8.3	33.1	up to 2048	14.4 – 57.6		64			1.2		752.6	33
GeForce GT 745M	April 1, 2013	GK107		PCIe 3.0 x16	384:32:16	837	837	2000 – 5000	4.39	17.6	up to 2048	32.0 – 80.0		128			1.2		642.8	45
GeForce GT 750M	April 1, 2013				384:32:16	967	967	2000 – 5000	7.53	30.1	up to 4096	32 – 80		128			1.1		722.7	50
GeForce GT 755M	Unknown				384:32:16	1020	1020	5400	15.7	31.4	up to 2048	86.4	GDDR5	128					752.6	50
GeForce GTX 760M	May 30, 2013	GK106			768:64:16	657	657	4008	10	40.2	2048	64.1		128					964.6	55
GeForce GTX 765M	May 30, 2013				768:64:16	850	850	4008	12.8	51	2048	64.1		128			1.2		1224	75
GeForce GTX 770M	May 30, 2013				960:80:24	811	811	4008	14.1	56.5	3072	96.2		192					1356	75
GeForce GTX 780M	May 30, 2013	GK104			1536:128:32	823	823	5000	24.7	98.7	4096	160.0		256					2369	100

In OpenCL 3.0, OpenCL 1.2 functionality has become a mandatory baseline, while all OpenCL 2.x and OpenCL 3.0 features were made optional.
^ Lacks hardware video encoder

Chipset table

GeForce 700 (7xx) series

Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm)	Bus interface	SMX count	Core config	Clock rate				Fillrate		Memory configuration				Supported API version				Processing power (GFLOPS)		TDP (Watts)	Release Price (USD)
Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm)	Bus interface	SMX count	Core config	Base (MHz)	Average Boost (MHz)	Max Boost (MHz)	Memory (MHz)	Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	DRAM type	Bus width (bit)	Vulkan	Direct3D	OpenGL	OpenCL	Single precision	Double precision	TDP (Watts)	Release Price (USD)
GeForce GT 705	March 27, 2014	GF119-300-A1	TSMC 40 nm	292	79	PCIe 2.0 x16	1	48:8:4	810	—	—	898 (1796)	3.24	6.5	512 1024	14.4	DDR3	64	n/a	12	4.6	1.1	155.5	19.4	29	OEM
GeForce GT 710	March 27, 2014	GK208-301-A1	TSMC 28 nm	1020	79	PCIe 2.0 x8		192:16:8	823	—	—	900 (1800)	6.6	13.2	512	14.4	DDR3	64	1.2			1.2	316.0	13.2		OEM
GeForce GT 710	January 26, 2016	GK208-203-B1				PCIe 2.0 x8, PCIe x1		192:16:8	954	—	—	900 (1800) 1253 (5010)	7.6	15.3	1024 2048	14.4 40.0	DDR3 GDDR5						366	15.3	19	$35–45
GeForce GT 720	March 27, 2014	GK208-201-B1				PCIe 2.0 x8		192:16:8	797	—	—	900 (1800) 1253 (5010)	6.4	12.8	1024 2048	14.4 40.0	DDR3 GDDR5						306	12.8	19	$49–59
GeForce GT 730	June 18, 2014	GK208-301-A1					2	384:16:8	902	—	—	900 (1800)	7.22	14.44	1024 2048 4096	14.4	DDR3						692.7	28.9	23	$69–79
		GK208-400-A1						384:16:8	902	—	—	1250 (5000)	7.22	14.44	1024 2048	40.0	GDDR5						692.7	28.9	25
		GF108	TSMC 40 nm	585	116	PCIe 2.0 x16		96:16:4	700	—	—	900 (1800)	2.8	11.0	1024 2048 4096	28.8	DDR3	128	n/a			1.1	268.8	33.6	49
GeForce GT 740	May 29, 2014	GK107-425-A2	TSMC 28HP	1270	118	PCIe 3.0 x16		384:32:16	993	—	—	891 (1782)	15.9	31.8		28.5	DDR3	128	1.2			1.2	762.6	31.8	64	$89–99
GeForce GT 740	May 29, 2014	GK107-425-A2		1270	118			384:32:16	993	—	—	1252 (5008)	15.9	31.8		80.1	GDDR5		1.2				762.6	31.8	64	$89–99
GeForce GTX 745	February 18, 2014	GM107-220-A2		1870	148		3	384:24:16	1033	Unknown	Unknown	900 (1800)	16.5	24.8	1024 4096	28.8	DDR3		1.3				793.3	24.8	55	OEM
GeForce GTX 750		GM107-300-A2					4	512:32:16	1020	1085	1163	1250 (5000)	16.3	32.6	1024 2048 4096	80	GDDR5						1044.5	32.6	55	$119
GeForce GTX 750 Ti		GM107-400-A2					5	640:40:16	1020	1085	1200	1350 (5400)	16.3	40.8	1024 2048 4096	86.4							1305.6	40.8	60	$149
GeForce GTX 760 192-bit	October 17, 2013	GK104-200-KD-A2		3540	294		6	1152:96:24	824	888	889	1450 (5800)	19.8	79.1	1536 3072	139.2		192	1.2				1896.2	79.0	130	OEM
GeForce GTX 760	June 25, 2013	GK104-225-A2					6	1152:96:32	980	1033	1124	1502 (6008)	31.4	94	2048 4096	192.3		256					2257.9	94.1	170	$249 ($219)
GeForce GTX 760 Ti	September 27, 2013	GK104					7	1344:112:32	915	980	1084	1502 (6008)	29.3	102.5	2048	192.3							2459.5	102.5	170	OEM
GeForce GTX 770	May 30, 2013	GK104-425-A2					8	1536:128:32	1046	1085	1130	1752.5 (7010)	33.5	134	2048 4096	224							3213.3	133.9	230	$399 ($329)
GeForce GTX 780	May 23, 2013	GK110-300-A1		7080	561		12	2304:192:48	863	900	1002	1502 (6008)	41.4	160.5	3072 6144	288.4		384					3976.7	165.7		$649 ($499)
GeForce GTX 780 Ti	November 7, 2013	GK110-425-B1					15	2880:240:48	876	928	1019	1752.5 (7010)	42.0	210.2	3072	336.5							5045.7	210.2		$699
GeForce GTX TITAN	February 21, 2013	GK110-400-A1					14	2688:224:48	837	876	993	1502 (6008)	40.2	187.5	6144	288.4							4499.7	1300-1499.9		$999
GeForce GTX TITAN Black	February 18, 2014	GK110-430-B1					15	2880:240:48	889	980	1058	1752.5 (7010)	42.7	213.4	6144	336.5							5120.6	1706.9		$999
GeForce GTX TITAN Z	May 28, 2014	2x GK110-350-B1		2x 7080	2x 561		2x 15	2x 2880:240:48	705	876	Unknown	1752.5 (7010)	2x 33.8	2x 169	2x 6144	2x 336.5		2x 384			4.5		5046x2	1682x2	375	$2999
Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm)	Bus interface	SMX count	Core config	Clock rate				Fillrate		Memory configuration				Supported API version				Processing power (GFLOPS)		TDP (Watts)	Release Price (USD)
Model	Launch	Code name	Fab (nm)	Transistors (million)	Die size (mm)	Bus interface	SMX count	Core config	Base (MHz)	Average Boost (MHz)	Max Boost (MHz)	Memory (MHz)	Pixel (GP/s)	Texture (GT/s)	Size (MB)	Bandwidth (GB/s)	DRAM type	Bus width (bit)	Vulkan	Direct3D	OpenGL	OpenCL	Single precision	Double precision	TDP (Watts)	Release Price (USD)

^ Unified shaders: texture mapping units: render output units
To calculate the processing power see Maxwell (microarchitecture)#Performance, or Kepler (microarchitecture)#Performance.
^ Max Boost depends on ASIC quality. For example, some GTX TITAN with over 80% ASIC quality can hit 1019 MHz by default, lower ASIC quality will be 1006 MHz or 993 MHz.
Maxwell supports Vulkan version 1.3, while Kepler only support Vulkan version 1.2, Fermi does not support the Vulkan API at all.
^ Kepler supports some optional 11.1 features on feature level 11_0 through the Direct3D 11.1 API, however Nvidia did not enable four non-gaming features to qualify Kepler for level 11_1.
The GeForce GT 705 (OEM) is a rebranded GeForce GT 610, which itself is a rebranded GeForce GT 520.
The GeForce GT 730 (DDR3, 64-bit) is a rebranded GeForce GT 630 (Rev. 2).
The GeForce GT 730 (DDR3, 128-bit) is a rebranded GeForce GT 630 (128-bit).
The GeForce GT 740 (OEM) is a rebranded GeForce GTX 650.
^ As a Kepler GPC is able to rasterize 8 pixels per clock, fully enabled GK110 GPUs (780 Ti/TITAN Black) can only output 40 pixels per clock (5 GPCs), despite 48 ROPs and all SMX units being physically present. For GTX 780 and GTX 760, multiple GPC configurations with differing pixel fillrate are possible, depending on which SMXs were disabled in the chip: 5/4 GPCs, or 4/3 GPCs, respectively.
^ The GeForce GTX 760 Ti (OEM) is a rebranded GeForce GTX 670.

Discontinued support

Nvidia stopped releasing 32-bit drivers for 32-bit operating systems after the last Release 390.x driver, 391.35, was released in March 2018.

Kepler notebook GPUs moved to legacy support in April 2019 and stopped receiving security updates in April 2020. All notebook GPUs from the 7xxM family were affected by this change.

Nvidia announced that after Release 470 drivers, it would transition driver support for the Windows 7 and Windows 8.1 operating systems to legacy status and continue to provide critical security updates for these operating systems through September 2024.

Nvidia announced that all remaining Kepler desktop GPUs would transition to legacy support from September 2021 onwards and be supported for critical security updates through September 2024. The Nvidia GeForce GTX 745, 750 and 750 Ti from the 7xx desktop GPU family would not be affected by this change.

In Windows ,the last driver to fully support CUDA with 64-Bit Compute Capability 3.5 for Kepler in Windows 7 and Windows 8.1 64-bit is 388.71, tested with latest CUDA-Z and GPU-Z, after that driver, the 64-Bit CUDA support becomes broken for GeForce 700 series GK110 with Kepler architecture.

The last driver where monitor type detection is working properly on Windows XP is 352.86.

Notes

References

"Vulkan Driver Support". Nvidia. February 10, 2016. Retrieved April 25, 2018.
Kowaliski, Cyril (March 21, 2014). "DirectX 12 will also add new features for next-gen GPUs". The Tech Report. Retrieved April 1, 2014.
Mujtaba, Hassan (June 5, 2015). "AMD Confirms GCN Cards Don't Feature Full DirectX 12 Support – Feature Level 11_1 on GCN 1.0, Feature Level 12_0 on GCN 1.1/1.2". WCCFtech. Retrieved June 8, 2015.
^ "NVIDIA Launches Tesla K20 & K20X: GK110 Arrives At Last". AnandTech. November 12, 2012.
"GeForce Game Ready Driver For Civilization: Beyond Earth & Lords Of The Fallen Available Now". geforce.com. Retrieved April 18, 2018.
"NVIDIA Kepler not fully compliant with DirectX 11.1". Guru3D.com. Archived from the original on December 22, 2015. Retrieved April 18, 2018.
Nvidia Doesn't Fully Support DirectX 11.1 with Kepler GPUs, But… - Bright Side Of News . Archived December 29, 2012, at the Wayback Machine.
"GK110: The True Tank - Nvidia GeForce GTX Titan 6 GB: GK110 On A Gaming Card". tomshardware.com. February 19, 2013. Retrieved April 18, 2018.
"Nvidia GeForce GTX 780 Ti Review: GK110, Fully Unlocked". tomshardware.com. November 7, 2013. Retrieved April 18, 2018.
Smith, Ryan; T S, Ganesh (February 18, 2014). "The NVIDIA GeForce GTX 750 Ti and GTX 750 Review: Maxwell Makes Its Move". AnandTech. p. 5. Retrieved February 18, 2014.
"NVIDIA GeForce 705M". notebookcheck.net. Retrieved April 18, 2018.
"GeForce 710M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 720M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 730M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 735M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 740M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 745M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 750M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GT 755M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GTX 760M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GTX 765M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GTX 770M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"GeForce GTX 780M - Specifications - GeForce". www.geforce.com. Retrieved April 18, 2018.
"The Khronos Group". May 31, 2022.
"Nvidia Kepler not fully compliant with Direct3D 11.1". Guru3d.com. Archived from the original on December 22, 2015. Retrieved December 11, 2015.
Nvidia Doesn't Fully Support DirectX 11.1 with Kepler GPUs, But... - BrightSideOfNews.com Archived September 3, 2013, at the Wayback Machine
"Nvidia GeForce GT 705 | techPowerUp GPU Database". Techpowerup.com. Archived from the original on June 15, 2014. Retrieved December 11, 2015.
"Nvidia GeForce GT 710 | techPowerUp GPU Database". Techpowerup.com. Archived from the original on June 15, 2014. Retrieved December 11, 2015.
"Nvidia GeForce GT 720 | techPowerUp GPU Database". Techpowerup.com. Archived from the original on June 15, 2014. Retrieved December 11, 2015.
"GT 730 | Specifications". GeForce.com. Archived from the original on December 12, 2015. Retrieved December 11, 2015.
"GeForce GT 730 1GB-ZOTAC". ZOTAC. Archived from the original on July 19, 2016. Retrieved July 12, 2017.
"EVGA - Products - EVGA GeForce GT 730 2GB (Low Profile) - 02G-P3-3733-KR". Archived from the original on February 15, 2017. Retrieved April 29, 2017.
"AFOX GTX 750 4 GB Specs". TechPowerUp. Retrieved August 11, 2021.
"NVIDIA GeForce GTX 760 Ti OEM Specs". Archived from the original on May 30, 2016. Retrieved August 6, 2018.
"Articles - EVGA GeForce GTX 780 6GB Step-Up Available Now!". EVGA. March 21, 2014. Archived from the original on January 13, 2016. Retrieved December 11, 2015.
"GeForce GTX780 Ti. Specifications". Geforce.com. Archived from the original on December 12, 2015. Retrieved December 11, 2015.
"Nvidia GeForce GTX 780 Ti has 2880 CUDA cores". Videocardz.com. October 31, 2013. Archived from the original on December 22, 2015. Retrieved December 11, 2015.
"PNY dévoile son nouveau foudre de guerre: la GeForce GTX 780 TI". Web-engage.augure.com. Archived from the original on November 9, 2013. Retrieved December 11, 2015.
"GeForce GTX TITAN". Geforce.com. Archived from the original on December 5, 2015. Retrieved December 11, 2015.
"TITAN Graphics Card". Nvidia.com. Archived from the original on February 24, 2013. Retrieved December 11, 2015.
"Nvidia's GeForce GTX Titan, Part 1: Titan For Gaming, Titan For Compute". Anandtech.com. Archived from the original on December 4, 2015. Retrieved December 11, 2015.
"Titan's Compute Performance (aka Ph.D Lust) - Nvidia's GeForce GTX Titan Review, Part 2: Titan's Performance Unveiled". Anandtech.com. Archived from the original on December 22, 2015. Retrieved December 11, 2015. the calculated fp64 peak of Titan is 1.5 TFlops. However, under heavy load in fp64 mode, the card may underclock below the listed 837MHz to remain within the power and thermal specifications
"售价21999元！NV旗舰GTX TITAN Z评测-太平洋电脑网". June 5, 2014. Retrieved August 16, 2020.
"NVIDIA GeForce GTX TITAN Z Specs". TechPowerUp. Retrieved February 26, 2020.
"Support Plan for 32-bit and 64-bit Operating Systems - NVIDIA". nvidia.custhelp.com. Retrieved April 18, 2018.
"Support Plan for Kepler-series GeForce GPUs for notebooks | NVIDIA".
"Support Plan for Windows 7 and Windows 8/8.1 | NVIDIA".
"Support Plan for Kepler-series GeForce GPUs for Desktop | NVIDIA".
"Anyway to Change Monitor Type Shown in Nvidia Control Panel? \ VOGONS". www.vogons.org. Retrieved January 31, 2021.

External links

Nvidia

GeForce (List of GPUs)

Fixed pixel pipeline

Pre-GeForce

Vertex and pixel shaders

GeForce 3

4 Ti

Unified shaders

Unified shaders & NUMA

Ray tracing & Tensor Cores

Software and technologies

Multimedia acceleration	NVENC (video encoding) NVDEC (video decoding) PureVideo (video decoding)
Software	Cg (shading language) CUDA Nvidia GameWorks OptiX (ray tracing API) PhysX (physics SDK) Nvidia Omniverse (3D graphics) Nvidia RTX (ray tracing platform) Nvidia System Tools VDPAU (video decode API)
Technologies	Nvidia 3D Vision (stereo 3D) Nvidia G-Sync (variable refresh rate) Nvidia Optimus (GPU switching) Nvidia Surround (multi-monitor) MXM (module/socket) SXM (module/socket) NVLink (protocol) Scalable Link Interface (multi-GPU) TurboCache (framebuffer in system memory) Video Super Resolution (live video upscaling)
GPU microarchitectures	Celsius Kelvin Rankine Curie Tesla Fermi Kepler Maxwell Pascal Volta Turing Ampere Hopper Ada Lovelace Blackwell Rubin

Other products

Graphics Workstation cards	Nvidia Quadro Quadro Plex
GPGPU	Nvidia Tesla DGX
Console components	NV2A (Xbox) RSX 'Reality Synthesizer' (PlayStation 3) Tegra NX-SoC (Nintendo Switch)
Nvidia Shield	Shield Portable Shield Tablet Shield Android TV GeForce Now
SoCs and embedded	GoForce Drive Jetson Tegra
CPUs	Project Denver
Computer chipsets	nForce

Company

Key people	Jen-Hsun Huang Chris Malachowsky Curtis Priem David Kirk Bill Dally Debora Shoquist Ranga Jayaraman Jonah M. Alben
Acquisitions	3dfx Interactive Ageia ULi Bright Computing Cumulus Networks DeepMap Icera Mellanox Technologies Mental Images PortalPlayer Exluna MediaQ Stexar

Categories:

Latest revision as of 16:53, 15 December 2024

Overview

Architecture

Compute focus SMX improvement

New shuffle Instructions

NVENC

Hyper-Q

Microsoft DirectX support

Dynamic parallelism

Products

GeForce 700 (7xx) series

GeForce 700M (7xxM) series

Chipset table

GeForce 700 (7xx) series

Discontinued support

See also

Notes

References

External links