GeForce 700 series

GeForce 700 Series
Cards
Release date	May 2013
Codename	GF117, GF119, GK104, GK106, GK107, GK110, GK208, GM107
Models	GeForce Series GeForce GT Series GeForce GTX Series
Fabrication process and transistors	585M 28 nm (GF117) 1,270M 28 nm (GK107) Unknown 28 nm (GK208) 3,540M 28 nm (GK104) 7,080M 28 nm (GK110)
Entry-level	GeForce GT 705 GeForce GT 710 GeForce GT 720 GeForce GT 730 GeForce GT 740
Mid-range	GeForce GTX 750 GeForce GTX 750 Ti GeForce GTX 760 (OEM) GeForce GTX 760 GeForce GTX 760 Ti
High-end	GeForce GTX 770 GeForce GTX 780
Enthusiast	GeForce GTX 780 Ti GeForce GTX Titan GeForce GTX Titan Black GeForce GTX Titan Z
Rendering support
Direct3D	Direct3D 11.0 and Direct3D 12.0 support at feature level 11_0^[1]^[2]
OpenCL	OpenCL 1.2^[3]
OpenGL	OpenGL 4.5
History
Predecessor	GeForce 600 series
Variant	GeForce 800M series
Successor	GeForce 900 series

The GeForce 700 Series is a family of graphics processing units developed by Nvidia, used in desktop and laptop PCs. It is mainly based on a refresh of the Kepler microarchitecture (GK-codenamed chips) used in the previous GeForce 600 Series, but also includes cards based on the previous Fermi (GF) and later Maxwell (GM) architectures. A number of GeForce 700 series chips were released for mobile devices in April 2013. GeForce 700 series cards were first released in May 2013, starting with the release of the GeForce GTX Titan on February 19, 2013, and the GeForce GTX 780 on May 23, 2013.

Overview

GK110 has been designed and is being 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 65K 32bit registers, as compared to Fermi's 33K 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.^[4]

This series will support DirectX 12.^[5]

Dynamic Super Resolution(DSR) was added to Kepler GPUs with the latest Nvidia drivers.^[6]

Architecture

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

A Gigabyte GTX770 graphics card

The PCB of a GTX 780

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 only)

Compute focus SMX improvement

With GK110, Nvidia opted to increase compute 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.^[4]

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.^[4]

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.^[4]

Microsoft DirectX support

NVIDIA Kepler GPUs of the GeForce 700 series fully support DirectX 11.0.

NVIDIA will partially support the DX12 API on all the DX11-class GPUs it has shipped; these belong to the Fermi, Kepler and Maxwell architectural families.^[1]

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.^[4]

Products

GeForce 700 (7xx) series

The GeForce 700 series 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).^[7]^[8]

¹ Shader Processors : Texture mapping units : Render output units
² Pixel fillrate is calculated as the number of ROPs multiplied by the base core clock speed
³ Texture fillrate is calculated as the number of TMUs multiplied by the base core clock speed.
⁴ Single precision performance is calculated as 2 times the number of shaders multiplied by the base core clock speed.
⁵ Double precision performance of the GTX Titan & 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,^[9] while other Kepler chips' double precision performance is fixed at 1/24 of single-precision performance.^[10] GeForce 700 series Maxwell chips' double precision performance is 1/32 of single-precision performance.^[11]
⁶ 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.

Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die size (mm²)	Bus interface	Core config¹	Clock speeds			Fillrate		Memory				API support (version)			Processing power (GFLOPS)		TDP (watts)	SLI support⁶	Release price (USD)
Model	Launch	Code name	Fab (nm)	Transistors (Million)	Die size (mm²)	Bus interface	Core config¹	Base core clock (MHz)	Boost core clock (MHz)	Memory (MT/s)	Pixel (GP/s)²	Texture (GT/s)³	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	DirectX	OpenGL	OpenCL	Single precision⁴	Double precision⁵	TDP (watts)	SLI support⁶	Release price (USD)
GeForce GT 710^[12]	N/A	GK208-301-A1	28	1020	87	PCIe 2.0 x8	192:16:8	954	N/A	1800	7.6	15.2	1024 2048	14.4	DDR3	64	11.0	4.5	1.2	366	15.2	19	N/A	42
GeForce GT 720^[13]	Mar 27, 2014	GK208-201-B1	28	1020	87	PCIe 2.0 x8	192:16:8	797	N/A	1800 5000	6.4	12.8	1024 2048	14.4 40	DDR3 GDDR5	64	11.0	4.5	1.2	306	12.8	19	N/A	49
GeForce GT 730 (DDR3, 128-bit)^[14]	Jun 18, 2014	GF108	40	585	116	PCIe 2.0 x16	96:16:4	700	N/A	1800	2.8	11.2	1024	28.8	DDR3	128	11.0	4.5	1.1	134	Unknown	49	N/A	Unknown
GeForce GT 730 (DDR3, 64-bit)^[14]	Jun 18, 2014	GK208-301-A1	28	1020	79	PCIe 2.0 x8	384:16:8	902	N/A	1800	7.2	14.4	2048	14.4	DDR3	64	11.0	4.5	1.2	693	28.9	23	N/A	Unknown
GeForce GT 730 (GDDR5)^[14]	Jun 18, 2014	GK208-400-A1	28	1020	79	PCIe 2.0 x8	384:16:8	902	N/A	5000	7.2	14.4	1024 2048^[15]	40	GDDR5	64	11.0	4.5	1.2	693	28.9	25	N/A	Unknown
GeForce GT 740 (DDR3)^[16]	May 29, 2014	GK107	28	1270	118	PCIe 3.0 x16	384:32:16	993	N/A	1800	15.9	31.8	2048	28.8	DDR3	128	11.0	4.5	1.2	762	31.8	64	N/A	$89
GeForce GT 740 (GDDR5)^[16]	May 29, 2014	GK107	28	1270	118	PCIe 3.0 x16	384:32:16	993	N/A	5000	15.9	31.8	2048	80	GDDR5	128	11.0	4.5	1.2	762	31.8	64	N/A	$89
GeForce GTX 745 (OEM)^[17]	Feb 18, 2014	GM107	28	1870	148	PCIe 3.0 x16	384:24:16	1033	Unknown	1800	16.5	24.8	4096	28.8	DDR3	128	11.2	4.5	1.2	793	24.8	55	N/A	OEM
GeForce GTX 750^[18]	February 29, 2014	GM107	28	1870	148	PCIe 3.0 x16	512:32:16	1020	1085	5000	16.3	32.6	1024 2048^[19]^[20] 4096^[21]	80.2	GDDR5	128	11.2	4.5	1.2	1044	32.6	55	N/A	$119
GeForce GTX 750 Ti ^[22]	February 18, 2014	GM107	28	1870	148	PCIe 3.0 x16	640:40:16	1020	1085	5400	16.3	40.8	1024 2048	86.4	GDDR5	128	11.2	4.5	1.2	1306	40.8	60	N/A	$149
GeForce GTX 760 192-bit^[23]	Unknown	GK104	28	3540	294	PCIe 3.0 x16	1152:96:24	823	888	5808	19.8	79	1536 3072	134	GDDR5	192	11.0	4.5	1.2	1896	79	130	3-way	OEM
GeForce GTX 760^[24]	June 25, 2013	GK104	28	3540	294	PCIe 3.0 x16	1152:96:32	980	1033	6008	31.4	94.1	2048 4096	192	GDDR5	256	11.0	4.5	1.2	2258	94.1	170	3-way	$249
GeForce GTX 760 Ti^[25]	Unknown	GK104	28	3540	294	PCIe 3.0 x16	1344:112:32	915	980	6008	29.3	103	2048	192	GDDR5	256	11.0	4.5	1.2	2460	103	170	3-way	OEM
GeForce GTX 770^[26]	May 30, 2013	GK104	28	3540	294	PCIe 3.0 x16	1536:128:32	1046	1085	7010	33.5	134	2048 4096	224	GDDR5	256	11.0	4.5	1.2	3213	134	230	3-way	$399^[27]
GeForce GTX 780^[28]	May 23, 2013	GK110	28	7080	561	PCIe 3.0 x16	2304:192:48	863	900	6008	41.4	166	3072	288	GDDR5	384	11.0	4.5	1.2	3977	166	250	3-way	$649^[27]
GeForce GTX 780 Ti^[29]	November 7, 2013	GK110	28	7080	561	PCIe 3.0 x16	2880:240:48	876	928	7000	42.0	210	3072	336	GDDR5	384	11.0	4.5	1.2	5046	210	250	4-way	$699^[27]
GeForce GTX Titan^[30]	February 19, 2013	GK110	28	7080	561	PCIe 3.0 x16	2688:224:48	837	876	6008	40.2	188	6144	288	GDDR5	384	11.0	4.5	1.2	4500	1500	250	4-way	$999
GeForce GTX Titan Black^[31]	February 18, 2014	GK110	28	7080	561	PCIe 3.0 x16	2880:240:48	889	980	7000	42.7	213	6144	336	GDDR5	384	11.0	4.5	1.2	5121	1707	250	4-way	$999
GeForce GTX Titan Z^[32]	March 25, 2014	2× GK110	28	2× 7080	2× 561	PCIe 3.0 x16	2× 2880:240:48	705	876	7000	2× 33.8	2× 169	2× 6144	2× 336	GDDR5	2× 384	11.0	4.5	1.2	8122	2707	375	4-way on 2 cards	$2999

GeForce 700M (7xxM) series

Some implementations may use different specifications.

¹ Unified shaders : Texture mapping units : Render output units

Model	Launch	Code name	Fab (nm)	Bus interface	Core config¹	Clock speed			Fillrate		Memory				API support (version)			Processing power² (GFLOPS)	TDP (watts)	Notes
Model	Launch	Code name	Fab (nm)	Bus interface	Core config¹	Core (MHz)	Shader (MHz)	Memory (MT/s)	Pixel (GP/s)	Texture (GT/s)	Size (MiB)	Bandwidth (GB/s)	Bus type	Bus width (bit)	DirectX	OpenGL	OpenCL	Processing power² (GFLOPS)	TDP (watts)	Notes
GeForce 705M ^[33]	June 1, 2013	GF119	40	PCIe 2.0 x16	48:8:4	775	1550	1800	1.48	5.9	up to 2048	?	DDR3	64	11.0	4.5	1.1	141.7	12W	Rebadged 520M
GeForce 710M ^[34]	April 1, 2013	GF117	28	PCIe 2.0 x16	96:16:4	775	1550	1800	3.1	12.4	up to 2048	14.4	DDR3	64	11.0	4.5	1.1	297.6	15W
GeForce GT 720M ^[35]	April 1, 2013	GF117	28	PCIe 2.0 x16	96:16:4	800	1600	1600	2.5	10	up to 2048	12.8	DDR3	64	11.0	4.4	1.1	240	33W
GeForce GT 720M ^[35]	Dec 25, 2013	GK208	28	PCIe 2.0 x16	192:16:8	800	800	1600	2.9	11.5	up to 2048	12.8	DDR3	64	12.0	4.5	1.2	276	33
GeForce GT 730M ^[36]	April 1, 2013	GK107	28	PCIe 3.0 x16	384:32:16	725	725	1800	5.8	23	up to 2096	14.4 - 64.0	DDR3 GDDR5	128	11.0	4.5	1.1	552.2	33W
GeForce GT 730M ^[36]	Mar 6, 2014	GK208	28	PCIe 2.0 x8	384:16:8	725	725	1800	5.8	11.5	up to 2096	14.4 - 64.0	DDR3 GDDR5	64	11.0	4.5	1.1	552.2	33W
GeForce GT 735M ^[37]	April 1, 2013	GK208	28	PCIe 2.0 x8	384:32:8	889	889	2000	4.6	9.2	up to 2048	16.0	DDR3	64	11.0	4.5	1.2	441.6	33W
GeForce GT 740M ^[38]	April 1, 2013	GK107	28	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	11.0	4.5	1.1	622.1	45W
GeForce GT 740M ^[38]	Jun 20, 2013	GK208	28	PCIe 3.0 x8	384:16:8	980-1033	980-1033	1800/3600	7.84	15.7	up to 2048	14.4 - 57.6	DDR3 GDDR5	64	11.0	4.5	1.2	752.6	33
GeForce GT 745M ^[39]	April 1, 2013	GK107	28	PCIe 3.0 x16	384:32:16	837	837	2000 - 5000	4.39	17.6	up to 2048	32.0 - 80.0	DDR3 GDDR5	128	11.0	4.5	1.2	421.6	45W
GeForce GT 750M ^[40]	April 1, 2013	GK107	28	PCIe 3.0 x16	384:32:16	967	967	2000 - 5000	7.53	30.1	up to 4096	32 - 80	DDR3 GDDR5	128	11.0	4.5	1.1	722.7	50W
GeForce GT 755M ^[41]	Unknown	GK107	28	PCIe 3.0 x16	384:32:16	1020	1020	5400	15.7	31.4	up to 2048	86.4	GDDR5	128	11.0	4.5	1.1	752.6	50W
GeForce GTX 760M ^[42]	May 30, 2013	GK106	28	PCIe 3.0 x16	768:64:16	657	657	4008	10	40.2	2048	64.1	GDDR5	128	11.0	4.5	1.1	964.6	55W
GeForce GTX 765M ^[43]	May 30, 2013	GK106	28	PCIe 3.0 x16	768:64:16	850	850	4008	12.8	51	2048	64.1	GDDR5	128	11.0	4.5	1.2	1224	75W
GeForce GTX 770M ^[44]	May 30, 2013	GK106	28	PCIe 3.0 x16	960:80:24	811	811	4008	14.1	56.5	3072	96.2	GDDR5	192	11.0	4.5	1.2	1356	75W
GeForce GTX 780M ^[45]	May 30, 2013	GK104	28	PCIe 3.0 x16	1536:128:32	823	823	5000	24.7	98.7	4096	160.0	GDDR5	256	11.0	4.5	1.2	2369	100W

Chipset table

Main article: Comparison table of GeForce 700 Series

References

1 2 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.
↑ https://compubench.com/device.jsp?benchmark=compu20&os=Windows&api=cl&D=NVIDIA+GeForce+GTX+TITAN+Black&testgroup=info
1 2 3 4 5 "NVIDIA Launches Tesla K20 & K20X: GK110 Arrives At Last". AnandTech. 12 November 2012.
↑ http://blogs.nvidia.com/blog/2014/03/20/directx-12/
↑ http://www.geforce.com/whats-new/articles/geforce-344-48-whql-driver-released
↑ NVIDIA Kepler not fully compliant with DirectX 11.1
↑ Nvidia Doesn't Fully Support DirectX 11.1 with Kepler GPUs, But… - Bright Side Of News
↑ GK110 The True Tank - Nvidia GeForce GTX Titan 6 GB GK110 On A Gaming Card
↑ Nvidia GeForce GTX 780 Ti Review GK110, Fully Unlocked - GK110, Unleashed The Wonders Of Tight Binning
↑ 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.
↑ GeForce GT 710 | Specifications | GeForce
↑ GeForce GT 720 | Specifications | GeForce
1 2 3 GeForce GT 730 | Specifications | GeForce
↑ "Inno3D GeForce GT 730 2GB GDDR5 LP". Inno3D. Retrieved 21 May 2015.
1 2 GeForce GT 740 | Specifications | GeForce
↑ GeForce GTX 745 (OEM) | Specifications | GeForce
↑ GeForce GTX 750 | Specifications | GeForce
↑ "GeForce GTX 750 EVGA Superclocked 2GB Edition". Game Debate. Retrieved 26 May 2015.
↑ Kirsch, Nathan (28 February 2014). "EVGA GeForce GTX 750 with 2GB GDDR5 Memory Announced". Legit Reviews. Retrieved 26 May 2015.
↑ "GTX750-OC-4GD5". ASUS. Retrieved 6 June 2015.
↑ GeForce GTX 750 Ti | Specifications | GeForce
↑ GeForce GTX 760 192-bit | Specifications | GeForce
↑ GeForce GTX 760 | Specifications | GeForce
↑ GeForce GTX 760 Ti | Specifications | GeForce
↑ GeForce GTX 770 | Specifications | GeForce
1 2 3 http://www.bit-tech.net/news/hardware/2013/10/28/nvidia-geforce-gtx-780-ti-price-and-release/1
↑ GeForce GTX 780 | Specifications | GeForce
↑ GeForce GTX 780 Ti | Specifications | GeForce
↑ GeForce GTX TITAN | Specifications | GeForce
↑ GeForce GTX Titan Black | Specifications | GeForce
↑ Walker, Justin (25 March 2014). "Two GPUs, One Insane Graphics Card: Introducing the GeForce GTX TITAN Z". Nvidia Blog. Nvidia Corporation. Retrieved 25 March 2014.
↑ GeForce 705M | Specifications | GeForce
↑ GeForce 710M | Specifications | GeForce
↑ GeForce GT 720M | Specifications | GeForce
↑ GeForce GT 730M | Specifications | GeForce
↑ GeForce GT 735M | Specifications | GeForce
↑ GeForce GT 740M | Specifications | GeForce
↑ GeForce GT 745M | Specifications | GeForce
↑ GeForce GT 750M | Specifications | GeForce
↑ GeForce GT 755M | Specifications | GeForce
↑ GeForce GTX 760M | Specifications | GeForce
↑ GeForce GTX 765M | Specifications | GeForce
↑ GeForce GTX 770M | Specifications | GeForce
↑ GeForce GTX 780M | Specifications | GeForce

External links

Wikimedia Commons has media related to Nvidia GeForce 700 series video cards.

Nvidia

GeForce (List of GPUs)

Fixed pixel pipeline(s)

Fixed T&L and pixel pipelines

Vertex and fragment shaders

Unified shaders

Tesla	GeForce 8 9 100 200 300

Fermi	GeForce 400 500

Kepler	GeForce 600 700 800M

Maxwell	GeForce 700 800M 900

Unified shaders
& memory

Pascal	To be announced

Volta	To be announced

Software and technologies

Multimedia acceleration	Nvidia NVENC Nvidia PureVideo

Software	Cg CUDA Gelato Nvidia GameWorks OptiX PhysX Nvidia System Tools VDPAU

Technologies	Nvidia 3D Vision Nvidia Optimus Nvidia Surround Scalable Link Interface TurboCache

Other products

Workstations and supercomputers	Nvidia Quadro Quadro Plex Nvidia Tesla

Console components	NV2A (Xbox) RSX 'Reality Synthesizer' (PlayStation 3)

NVidia Shield	Shield Portable Shield Tablet Shield Console

SoCs	GoForce 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 Icera Mental Images PortalPlayer Exluna MediaQ Stexar

This article is issued from Wikipedia - version of the Monday, February 15, 2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.