From Wikipedia, the free encyclopedia
PowerVR is a division of
(formerly VideoLogic) that develops hardware and software for 2D and , and for , , associated
and , , , and
acceleration.
The PowerVR product line was originally introduced to compete in the desktop PC market for
with a product with a better
than existing products like those from . Rapid changes in that market, notably with the introduction of
and , led to rapid consolidation. PowerVR introduced new versions with
that were aimed at the
market. Over time, this developed into a series of designs that could be incorporated into
architectures suitable for
PowerVR accelerators are not manufactured by PowerVR, but instead their
designs and
are licensed to other companies, such as , , , , , , , , , , and many others.
The PowerVR chipset uses a method of 3D rendering known as
(often abbreviated as TBDR) which is tile-based rendering combined with PowerVR's proprietary method of Hidden Surface Removal (HSR) and Hierarchical Scheduling Technology (HST). As the polygon generating program feeds triangles to the PowerVR (driver), it stores them in memory in a
or an indexed format. Unlike other architectures, polygon rendering is (usually) not performed until all polygon information has been collated for the current . Furthermore, the expensive operations of texturing and shading of pixels (or fragments) is delayed, whenever possible, until the visible surface at a pixel is determined — hence rendering is deferred.
In order to render, the display is split into rectangular sections in a grid pattern. Each section is known as a tile. Associated with each tile is a list of the triangles that visibly overlap that tile. Each tile is rendered in turn to produce the final image.
Tiles are rendered using a process similar to . Rays are numerically simulated as if cast onto the triangles associated with the tile and a pixel is rendered from the triangle closest to the camera. The PowerVR hardware typically calculates the depths associated with each polygon for one tile row in 1 cycle.[ – ]
This method has the advantage that, unlike a more traditional early Z rejection based hierarchical systems, no calculations need to be made to determine what a polygon looks like in an area where it is obscured by other geometry. It also allows for correct rendering of partially transparent polygons, independent of the order in which they are processed by the polygon producing application. (This capability was only implemented in Series 2 including Dreamcast and one MBX variant. It is generally not included for lack of API support and cost reasons.) More importantly, as the rendering is limited to one tile at a time, the whole tile can be in fast on-chip memory, which is flushed to video memory before processing the next tile. Under normal circumstances, each tile is visited just once per frame.
PowerVR is a pioneer of tile based deferred rendering. Microsoft also conceptualised the idea with their abandoned
project. Gigapixel, a company that developed IP for tile-based deferred 3D graphics, was purchased by , which in turn was subsequently purchased by . Nvidia has now been shown to use tile rendering in the Maxwell and Pascal microarchitectures.
began developing another major tile based deferred rendering architecture known as
after their acquisition of .
Intel uses a similar concept in their integrated graphics solutions. However, their method, coined zone rendering, does not perform full
(HSR) and deferred texturing, therefore wasting fillrate and texture bandwidth on pixels that are not visible in the final image.
Recent advances in hierarchical Z-buffering have effectively incorporated ideas previously only used in deferred rendering, including the idea of being able to split a scene into tiles and of potentially being able to accept or reject tile sized pieces of polygon.
Today, the PowerVR software and hardware suite has ASICs for ,
and associated . It also has virtualisation, and , , , and
acceleration. Newest PowerVR Wizard GPUs have
Unit (RTU) hardware and support hybrid rendering.
VideoLogic Apocalypse 3Dx (NEC PowerVR PCX2 chip)
The first series of PowerVR cards was mostly designed as 3D-only accelerator boards that would use the main 2D video card's memory as framebuffer over PCI. Videologic's first PowerVR PC product to market was the 3-chip Midas3, which saw very limited availability in some OEM
PCs. This card had very poor compatibility with all but the first Direct3D games, and even most SGL games did not run. However, its internal 24-bit color precision rendering was notable for the time.
The single-chip PCX1 was released in retail as the VideoLogic Apocalypse 3D and featured an improved architecture with more texture memory, ensuring better game compatibility. This was followed by the further refined PCX2, which clocked 6 MHz higher, offloaded some driver work by including more chip functionality and added bilinear filtering, and was released in retail on the Matrox M3D and Videologic Apocalypse 3Dx cards. There was also the Videologic Apocalypse 5D Sonic, which combined the PCX2 accelerator with a
ET6100 2D core and ESS Agogo sound on a single PCI board.
The PowerVR PCX cards were placed in the market as budget solutions and performed well in the games of their time, but weren't quite as fully featured as the
accelerators (due to certain blending modes being unvailable, for instance). However, the PowerVR approach of rendering to the 2D card's memory meant that much higher 3D rendering resolutions could be possible in theory, especially with PowerSGL games that took full advantage of the hardware.
All models support
3.0 and PowerSGL, MiniGL drivers available for select games
Core clock ()
Memory clock ()
Core config1
MOperations/s
MPolygons/s
Bandwidth (/s)
Bus width ()
2 Midas3 is 3-chip (vs. single-chip PCX series) and uses a split memory architecture: 1 MB 32-bit SDRAM (240 MB/s peak bandwidth) for textures and 1 MB 16-bit FPM DRAM for geometry data (and presumably for PCI communication). PCX series has only texture memory.
The second generation PowerVR2 ("PowerVR Series2", chip codename "CLX2") was brought to market in the
console between 1998 and 2001. As part of an internal competition at
to design the successor to the , the PowerVR2 was licensed to NEC and was chosen ahead of a rival design based on the
. The PowerVR2 was peered with the
in the Dreamcast, with the SH-4 as the
geometry engine and the PowerVR2 as the rendering engine. The PowerVR2 also powered the , the upgraded
counterpart of the Dreamcast. The quality and performance of the PowerVR2 at least matched and in some ways exceeded contemporary PC graphics cards such as the ,
However, the success of the Dreamcast meant that the PC variant, sold as Neon 250, appeared a year late to the market, in late 1999, and was by that time no better than the
or , though it managed to remain competitive. The Neon 250 features inferior hardware specifications compared to the PowerVR2 part used in Dreamcast, such as a halved tile size, among others.
All models are fabricated with a 250 nm process
All models support
PMX1 supports PowerSGL 2 and includes a MiniGL driver optimized for
Core clock ()
Memory clock ()
Core config1
MOperations/s
MPolygons/s
Bandwidth (/s)
Bus width ()
2 Fillrate for opaque polygons.
3 Fillrate for translucent polygons with hardware sort depth of 60.
geometry engine calculates
for more than 10 million triangles per second. CLX2 rendering engine throughput is 7 million triangles per second.
In 2001, the third generation PowerVR3 STG4000 KYRO was released, manufactured by new partner . The architecture was redesigned for better game compatibility and expanded to a dual-pipeline design for more performance. The refresh STM PowerVR3 KYRO II, released later in the same year, likely had a lengthened pipeline to attain higher clock speeds and was able to rival the more expensive ATI
DDR and NVIDIA
GTS in some benchmarks of the time, despite its modest specifications on paper and lack of hardware
(T&L), a fact that Nvidia especially tried to capitalize on in a confidential paper they sent out to reviewers. As games increasingly started to include more geometry with this feature in mind, the KYRO II lost its competitiveness.
The KYRO series had a decent featureset for a budget-oriented GPU in their time, including a few Direct3D 8.1-compliant features such as 8-layer multitexturing (not 8-pass) and Environment Mapped Bump Mapping (EMBM); Full Scene Anti-Aliasing (FSAA) and Trilinear/Anisotropic filtering were also present. KYRO II could also perform Dot Product (Dot3) Bump Mapping at a similar speed as GeForce 2 GTS in benchmarks. Omissions included hardware T&L (an optional feature in Direct3D 7), Cube Environment Mapping and legacy 8-bit paletted texture support. Support for the proprietary PowerSGL API was also dropped with this series.
16-bit output quality was excellent compared to most of its competitors, thanks to rendering to its internal 32-bit tile cache and downsampling to 16-bit instead of straight use of a 16-bit framebuffer. This could play a role in improving performance without losing much image quality, as memory bandwidth was not plentiful. However, due to its unique concept on the market, the architecture could sometimes exhibit flaws such as missing geometry in games, and therefore the driver had a notable amount of compatibility settings, such as switching off the internal Z-buffer. These settings would often have a negative impact on performance.
A second refresh of the KYRO was planned for 2002, the STG4800 KYRO II SE. Samples of this card were sent to reviewers but it does not appear to have been brought to market. Apart from a clockspeed boost, this refresh was announced with a "EnT&L" HW T&L software emulation, which eventually made it into the drivers for the previous KYRO cards starting with version 2.0. The STG5500 KYRO III, based upon the next-generation PowerVR4, was completed and would have included hardware T&L but was shelved due to STMicro closing its graphics division.
All models support
Core clock ()
Memory clock ()
Core config1
MOperations/s
MPolygons/s
Bandwidth (/s)
Bus width ()
STG4000 KYRO
STG4500 KYRO II
STG4800 KYRO II SE
STG5500 KYRO III
Never Released
PowerVR achieved great success in the mobile graphics market with its low power PowerVR MBX. MBX, and its SGX successors, are licensed by seven of the top ten semiconductor manufacturers including , , , , , ,
and . The chips were used in many high-end cellphones including the original , ,
and , as well as some .
There are two variants: MBX and MBX Lite. Both have the same feature set. MBX is optimized for speed and MBX Lite is optimized for low power consumption. MBX could be paired up with an FPU, Lite FPU, VGP Lite and VGP.
Die Size (mm2)
Core config
(@ 200 MHz)
Bus width ()
MTriangles/s
4@130 nm?
7.0, VS 1.1
8@130 nm?
7.0, VS 1.1
PowerVR's VXD is used in Apple , and their PDP series is used in some , including the Sony .
PowerVR's Series5 SGX series features , , and
hardware, supporting
10.1 with Shader Model 4.1.
The SGX GPU core is included in several popular
(SoC) used in many portable devices. Apple uses the
(manufactured by Samsung) in their , , , and , and uses the
in the . '
3 and 4 series SoC's are used in the , , , , , , , , Motorola RAZR D1/D3, Droid Bionic, , , , , , and others. Samsung produces the
SoC and uses it in their , ,
and Samsung Wave III S860 devices. Hummingbird is also in
smartphone.
uses the SGX540 in its Medfield platform.
Die Size (mm2)
Core config
(@ 200 MHz)
Bus width ()
(@ 200 MHz)
MTriangles/s
2.6@65 nm
7.2@65 nm
65 nm
65 nm
65 nm
12.5@65 nm
PowerVR Series5XT SGX chips are multi-core variants of the SGX series with some updates. It is included in the
portable gaming device with the MP4+ Model of the PowerVR SGX543, the only intended difference, aside from the + indicating features customized for Sony, is the cores, where MP4 denotes 4 cores (quad-core) whereas the MP8 denotes 8 cores (octo-core). The
(quad-core mobile application processor) features the dual-core SGX544 MP2. The
SoC also feature a dual-core SGX543MP2. The
SoC features the quad-core SGX543MP4. The
SoC features the tri-core SGX543MP3. The
SoC features the quad-core SGX554MP4. The
variant of the
sports the tri-core SGX544MP3 clocked at 533 MHz.
Die Size (mm2)
Core config
(@ 200 MHz,per core)
MPolygons/s
5.4@32 nm
5.4@32 nm
8.7@32 nm
These GPU can be used in either single-core or multi-core configurations.
Introduced in 2014, the PowerVR GX5300 GPU is based on the SGX architecture and is the world’s smallest Android-capable graphics core, with substantial improvements in efficiency, providing an ideal low-power solution for entry-level smartphones, wearables, IoT and other small footprint embedded applications, including enterprise devices such as printers.
PowerVR Series6 GPUs are based on an evolution of the SGX architecture codenamed Rogue.
(now defunct) announced that its
application processors would include Imagination’s next-generation PowerVR Series6 architecture. MediaTek announced the quad-core MT8135
(SoC) (two ARM
and two ARM
cores) for tablets. Renesas announced its R-Car H2 SoC includes the G6400.
A80 SoC, (4 Cortex-A15 and 4 Cortex-A7) that is available in the Onda V989 tablet, features a PowerVR G6230 GPU. The
SoC integrates a
(GPU) which
believes to be a PowerVR G6430 in a four cluster configuration.
PowerVR Series 6 GPUs have 2 TMUs/cluster.
Die Size (mm2)
Core config
(@ 600 MHz)
MPolygons/s
??@28 nm
38.4(FP32) / 57.6(FP16)
??@28 nm
??@28 nm
76.8 / 115.2
??@28 nm
153.6/153.6
??@28 nm
153.6 / 230.4
??@28 nm
230.4 / 345.6
PowerVR Series6XE GPUs are based around Series6 and designed as entry-level chips aimed at offering roughly the same fillrate compared to the Series5XT series. They however feature refreshed API support such as Vulkan, OpenGL ES 3.1, OpenCL 1.2 and DirectX 9.3 (9.3 L3). Rockchip and Realtek have used Series6XE GPUs in their SoCs.
PowerVR Series 6XE GPUs were announced on January 6, 2014.
Die Size (mm2)
Core config
(@ 600 MHz)
MPolygons/s
??@28 nm
?? / ??
??@28 nm
?? / ??
G6100 (XE)
??@28 nm
??@28 nm
PowerVR Series6XT GPUs aims at reducing power consumption further through die area and performance optimization providing a boost of up to 50% compared to Series6 GPUs. Those chips sport PVR3C triple compression system-level optimizations and Ultra HD deep color. The Apple ,
SoC feature the quad-core GX6450. The MediaTek MT8173 and Renesas R-Car H3 SoCs use Series6XT GPUs.
PowerVR Series 6XT GPUs were unveiled on January 6, 2014.
Die Size (mm2)
Core config
(@ 650 MHz)
MPolygons/s
??@28 nm
83.2 / 166.4
??@28 nm
83.2/166.4
19.1mm2@28 nm
166.4/332.8
??@28 nm
PowerVR Series7XE GPUs are available in half cluster and single cluster configurations, enabling the latest games and apps on devices which require high quality UIs at optimum price points.
PowerVR Series 7XE GPUs were announced on 10 November 2014. When announced, the 7XE series contained the smallest
compliant GPU.
Die Size (mm2)
Core config
(@ 600 MHz)
MPolygons/s
1.2 embedded profile
PowerVR Series7XT GPUs are available in configurations ranging from two to 16 clusters, offering dramatically scalable performance from 100 GFLOPS to 1.5 TFLOPS. Use in The Apple iPhone 6s and iPhone 6s Plus model year .
PowerVR Series 7XT GPUs were unveiled on 10 November 2014.
Die Size (mm2)
Core config
(@ 650 MHz) FP32/FP16
(@ 800 MHz) FP32/FP16
(@ 1 GHz) FP32/FP16
MPolygons/s
3.3 (4.4 optional)
1.2 embedded profile (FP optional)
10.0 (11.2 optional)
83.2 / 166.4
102.5 / 205
166.5 / 333
512 / 1024
666 / 1332
819.2 / 1638.4
1024 / 2048
PowerVR Series7XT Plus GPUs are an evolution of the Series7XT family and add specific features designed to accelerate computer vision on mobile and embedded devices, including new INT16 and INT8 data paths that boost performance by up to 4x for OpenVX kernels. Further improvements in shared virtual memory also enable OpenCL 2.0 support.
PowerVR Series 7XT Plus GPUs were announced on International CES, Las Vegas – 6 January 2016.
Series7XT Plus achieve up to 4x performance increase for vision applications.
Die Size (mm2)
Core config
(@ 1 GHz) FP32/FP16
MPolygons/s
GT7200 Plus
January 2016
3.3 (4.4 optional)
GT7400 Plus
January 2016
GT7600 Plus
10 nm
The GPUs are designed to offer improved in-system efficiency, improved power efficiency and reduced bandwidth for vision and computational photography in consumer devices, mid-range and mainstream smartphones, tablets and automotive systems such as advanced driver assistance systems (ADAS), infotainment, computer vision and advanced processing for instrument clusters.
The new GPUs include new feature set enhancements with a focus on next-generation compute:
Up to 4x higher performance for OpenVX/vision algorithms compared to the previous generation through improved integer (INT) performance (2x INT16; 4x INT8) Bandwidth and latency improvements through shared virtual memory (SVM) in OpenCL 2.0 Dynamic parallelism for more efficient execution and control through support for device enqueue in OpenCL 2.0
PowerVR Series8XE GPUs support OpenGL ES 3.2 and Vulkan 1.x and are available in 4 pixel/clock and 2 pixel/clock configurations, enabling the latest games and apps and further driving down the cost of high quality UIs on cost sensitive devices.
PowerVR Series 8XE were announced February 22, 2016 at the Mobile World Congress 2016. There are an iteration of the Rogue microarchitecture and target entry-level SoC GPU market. New GPUs improve the performance/mm2 for the smallest silicon footprint and power profile, while also incorporating hardware virtualization and multi-domain security.Newer model were later release in January 2017, with a new low end and high end part.
Die Size (mm2)
Core config
(@ 650 MHz) FP32/FP16
MPolygons/s
January 2017
 ? / ?
February 2016
20.8 / 41.6
February 2016
41.6 / 83.2
February 2016
 ? / ?
January 2017
 ? / ?
PowerVR Series 8XE Plus were announced January 2017. There are an iteration of the Rogue microarchitecture and target the mid range SoC GPU market, targeting 1080p. The 8XE Plus remains focused on die size and performance per unit
Die Size (mm2)
Core config
(@ 650 MHz) FP32/FP16
MPolygons/s
January 2017
41.6 / 83.2
January 2017
 ? / ?
January 2017
83.2 / 166.4
Announced on 8 March 2017, Furian is the first new PowerVR architecture since Rogue was introduced five years earlier.
PowerVR Series 8XT were announced March 8, 2017. It's the first series GPU's based on the new Furian architecture. According to Imagination, GFLOPS/mm2 is improved 35% and Fill rate/mm2 is improved 80% compared to the 7XT Plus series on the same node. Specific designs aren't announced as of March 2017.
Die Size (mm2)
Core config
MPolygons/s
March 2017
Announced on September 2017, Series9XE family of GPUs benefit from up to 25% Bandwidth savings over the previous generation GPUs.
Die Size (mm2)
Core config
MPolygons/s
September 2017
September 2017
September 2017
September 2017
The Series9XM family of GPUs achieve up to 50% better performance density than the previous 8XEP generation.
Die Size (mm2)
Core config
MPolygons/s
September 2017
September 2017
Official Imgtec data
USSE ( Scalable Shader Engine) lanes/
USSE2 (Universal Scalable Shader Engine 2) lanes/
USC (Unified Shading Cluster) lanes/ per cluster
All models support Tile based deferred rendering (TBDR)
The PowerVR
variants can be found in the following systems on chips ():
PowerVR chipset
110 MHz
Sitara AM335x
200 MHz
Sitara AM3715
Sitara AM3891
DaVinci DM3730
Integra C6A8168
EMMA Mobile/EV2
SH-Mobile G3
SH-Navi3 (SH7776)
200 MHz
281 MHz
HiDTV PRO-SX5
522 MHz
NaviEngine EC-4260
NaviEngine EC-4270
CE 3100 (Canmore)
SCH US15/W/L (Poulsbo)
CE4100 (Sodaville)
CE4110 (Sodaville)
200 MHz
CE4130 (Sodaville)
CE4150 (Sodaville)
400 MHz
CE4170 (Sodaville)
CE4200 (Groveland)
APL0298C05
April 3, 2010
200 MHz
250 MHz
SH-Mobile G4
SH-Mobile APE4 (R8A73720)
R-Car E2 (R8A7794)
Exynos 3110
200 MHz
307 MHz
384 MHz
Atom Z2420
400 MHz
500 MHz
600 MHz
November 13, 2014
March 11, 2011
SGX543 MP2
200 MHz
March 2012
250 MHz
SGX543 MP2
400 MHz
R-Car H1 (R8A77790)
SGX543 MP2
September 12, 2012
SGX543 MP3
250 MHz
March 7, 2012
SGX543 MP4
CXD53155GG ()
SGX543 MP4+
41-222 MHz
5.248-28.416
Nova A9540
NovaThor L9540
NovaThor L8540
500 MHz
NovaThor L8580
600 MHz
156 MHz
March 2013
286 MHz
300 MHz
357 MHz
384 MHz
Broadcom M320
Broadcom M340
450 MHz
Allwinner A31
SGX544 MP2
Allwinner A31S
Atom Z2520
SGX544 MP2
300 MHz
Atom Z2560
400 MHz
Atom Z2580
533 MHz
SGX544 MP2
Allwinner A83T
SGX544 MP2
700 MHz
Allwinner H8
Exynos 5410
SGX544 MP3
533 MHz
Atom Z2460
533 MHz
Atom Z2760
Atom CE5310
Atom CE5315
Atom CE5318
Atom CE5320
Atom CE5328
Atom CE5335
Atom CE5338
Atom CE5343
Atom CE5348
October 23, 2012
SGX554 MP4
300 MHz
September, 2016
Series6 (G;?)
600 MHz
G6200 (2 Clusters)
450 MHz
Helio X10 (MT6795M)
550 MHz
Helio X10 (MT6795T)
600 MHz
700 MHz
G6200 (2 Clusters)
600 MHz
Allwinner A80
G6230 (2 Clusters)
533 MHz
Allwinner A80T
G6230 (2 Clusters)
600 MHz
GX6250 (2 Clusters)
700 MHz
600 MHz
Atom Z3460
G6400 (4 Clusters)
533 MHz
Atom Z3480
R-Car H2 (R8A7790x)
G6400 (4 Clusters)
600 MHz
R-Car H3 (R8A7795)
GX6650 (6 Clusters)
September 10, 2013
G6430 (4 Clusters)
450 MHz
Atom Z3530
G6430 (4 Clusters)
457 MHz
Atom Z3560
533 MHz
Atom Z3570
Atom Z3580
September 9, 2014
GX6450 (4 Clusters)
533 MHz
October 16, 2014
GX6850 (8 Clusters)
September 9, 2015
Series 7XT GT7600 (6 Clusters)
600 MHz
Series 7XT GT7800 (12 Clusters)
&652 MHz
September 7, 2016
Series 7XT GT7600 Plus (6 Clusters)
900 MHz
Helio X30 (MT6799)
Series 7XT GT7400 Plus (4 Clusters)
800 MHz
June 5, 2017
Series 7XT GT7600 Plus (12 Clusters)
– GPU developed by Qualcomm
– available as SIP block to 3rd parties
– available as SIP block to 3rd parties
– family of SoCs for mobile computers, the graphics core could be available as SIP block to 3rd parties
– family of SOCs, by Broadcom, for mobile computers, the graphics core could be available as SIP block to 3rd parties
– with Intel graphics core, not licensed to 3rd parties
– with AMD graphics core, not licensed to 3rd parties
, By Amar Toor, June 2, 2011, Engadget
. Imagination Technologies Limited 2013.
. Imagination Technologies Limited.
. Imagination Technologies Limited 2013.
. Imagination Technologies Limited.
Hagiwara, S Oliver, Ian (November–December 1999). . IEEE Micro. . 19 (6): 29–35. Archived from the original on .
, by Anand Lal Shimpi, January 10, 2012, anandtech
, by Anand Lal Shimpi, , Anandtech
, by Brian Klug, 6/2/2011, AnandTech, Inc.
. Imagination Technologies.
. Imagination Technologies.
. 15 February 2011., Imagination Technologies Ltd.
., MediaTek Inc.
., Renesas Electronics Corporation Ltd
Lal Shimpi, Anand (September 17, 2013). . AnandTech 2013.
. Imagination Technologies.
, January 6, 2014, AnandTech
, January 6, 2014, Imagination
. Imagination Technologies.
, January 6, 2014, Imagination
. Chipworks. September 19, .
Smith, Ryan (September 23, 2014). . AnandTech 2014.
. Imagination Technologies. .
. Imagination Technologies. January 6, 2014.
Smith, Ryan (January 6, 2014). . AnandTech.
Voica, Alexandru (10 November 2014). . Imagination Technologies 2014.
. Imagination Technologies.
Voica, Alexandru (10 November 2014). . Imagination Technologies 2014.
. Imagination Technologies. .
Smith, Ryan (17 January 2017). . Anandtech 2017.
. Imagination Technologies.
. Imagination Technologies.
Smith, Ryan. .
Humrick, Ryan Smith, Matt. . check references 44.
: Hidden categories: