| |
Vivante Graphics Processor IP
Vivante offers smaller, faster, cooler GPU designs for a wide array of consumer products: smart phones and cell phones, MIDs and netbooks, digital picture frames, portable navigation systems, personal media players, cameras, automotive display and entertainment, set-top boxes, HDTV, and gaming systems.
2D Graphics: (raster) GC200, GC300 (vector) GC350
3D Graphics: GC400, GC600, GC800, GC1000
API support
- OpenGL ES 2.0 including all extensions
- OpenGL ES 1.1
- OpenVG 1.1
- DirectFB
- GDI/DirectDraw
- Flash
Operating System and Application Platform support
- Embedded Linux, kernel 2.6.21 and higher
- Windows CE 5.0 and 6.0
- Windows Mobile 6.1
- Android
Hardware features
- ScalarMorphic(TM) architecture means less area with no drop in performance
- Ultra-threaded, unified shader maximizes graphics processing speed
- Smallest die area in every GPU class
- Very low power with battery-saving innovations
- Highest graphics performance per sq. mm
- Superior image quality with high-definition detail, MSAA, and high dynamic range
- Depth texturing to enable dynamic shadow generation
- High-definition screen resolutions of HD 1080p and beyond
- Optimized to minimize bandwidth and reduce CPU load
- Simple integration using standard AHB and AMBA AXI bus SoC interconnects
Unified Shader
- Unified vertex and fragment/pixel shader means no wasted GPU cycle
- Full OpenGL ES 2.0 Shading Language support for unrestricted programmability
- IEEE 32-bit high-precision computing yields more detail, supports long instructions
- Massively parallel multi-threading virtually eliminates graphics pipeline latency
- Fully backward-compatible with all OpenGL ES 1.1 applications
Texture Mapping
- Texture support includes 2D, Cubic environment, Projective, YUY2, and High Dynamic Range (HDR)
- Point sample, bi-linear, and tri-linear texture filters
- Bump mapping support
- Depth map up to 24-bit
- Compressed texture standards ETC1 and DXT1-DXT5
- Dependent texture operation with high performance
- Supports 4 vertex shader and 8 pixel shader simultaneous textures
- Supports texture size up to 8K x 8K
Video post-processing and peripherals
- YUV-to-RGB color space conversion
- High-quality image and video scaling with 9-tap, 32-phase programmable filter
- Camera preview
Optional dedicated 2D unit
- All programmable 2D features
AHB interface
- 256K addressable register space
- 32-bit data bus
- Handles error response for illegal accesses
- Bus speed up to 400MHz in 65LP
AXI interface
- AMBA AXI protocol-compliant
- 32-bit address bus and 64-bit data bus
- Multiple burst length (8, 16, 32, or 64 bytes)
- High-performance out-of-order / multiple outstanding access
- Supports out-of-order return data from multiple slaves
- Bus speed up to 400MHz in 65LP
- Asynchronous interface to the graphics core
GC400
| GC400 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
864K |
864K |
| Memory Bits |
35 KB |
35 KB |
| Synthesis Area (std. cells + memory) |
2.00 mm2 |
2.00 mm2 |
| Silicon Area |
2.5 mm2 |
2.5 mm2 |
| Clock Frequency in Silicon |
250-300 MHz |
375-450 MHz |
| Active Power |
49-59 mW |
65-78 mW |
| Leakage Power |
0.04 mW |
0.35 mW |
| Geometry Rate |
13-15 M tri/s |
19-23 M tri/s |
| Pixel Rate, Depth-only |
250-300 M pix/s |
375-450 M pix/s |
| Pixel Rate, Textured |
125-150 M pix/s |
188-225 M pix/s |
| Vertex Rate |
63-76 M vert/s |
94-113 M vert/s |
GC600
| GC600 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
1.2 M |
1.2 M |
| Memory Bits |
57 KB |
57 KB |
| Synthesis Area (std. cells + memory) |
3.20 mm2 |
3.20 mm2 |
| Silicon Area |
4.2 mm2 |
4.2 mm2 |
| Clock Frequency in Silicon |
250 MHz |
375 MHz |
| Active Power |
82 mW |
109 mW |
| Leakage Power |
0.07 mW |
0.59 mW |
| Geometry Rate |
13 M tri/s |
19 M tri/s |
| Pixel Rate, Depth-only |
250 M pix/s |
375 M pix/s |
| Pixel Rate, Textured |
250 M pix/s |
375 M pix/s |
| Vertex Rate |
63 M vert/s |
94 M vert/s |
GC800
| GC800 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
1.5 M |
1.5 M |
| Memory Bits |
60 KB |
60 KB |
| Synthesis Area (std. cells + memory) |
3.38 mm2 |
3.38 mm2 |
| Silicon Area |
4.7 mm2 |
4.7 mm2 |
| Clock Frequency in Silicon |
250 MHz |
375 MHz |
| Active Power |
92 mW |
122 mW |
| Leakage Power |
0.07 mW |
0.66 mW |
| Geometry Rate |
25 M tri/s |
38 M tri/s |
| Pixel Rate, Depth-only |
250 M pix/s |
375 M pix/s |
| Pixel Rate, Textured |
250 M pix/s |
375 M pix/s |
| Vertex Rate |
125 M vert/s |
188 M vert/s |
GC1000
| GC1000 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
1.9 M |
1.9 M |
| Memory Bits |
76 KB |
76 KB |
| Synthesis Area (std. cells + memory) |
4.26 mm2 |
4.26 mm2 |
| Silicon Area |
5.6 mm2 |
5.6 mm2 |
| Clock Frequency in Silicon |
500 MHz |
750 MHz |
| Active Power |
219 mW |
269 mW |
| Leakage Power |
0.09 mW |
0.79 mW |
| Geometry Rate |
39 M tri/s |
58 M tri/s |
| Pixel Rate, Depth-only |
500 M pix/s |
750 M pix/s |
| Pixel Rate, Textured |
500 M pix/s |
750 M pix/s |
| Vertex Rate |
250 M vert/s |
375 M vert/s |
Raster Graphics 2D GPUs: GC200, GC300
- BitBlt, rectangle fill, line, StretchBlt, and monochrome expansion support
- ROP2, ROP3, ROP4 (transparency) support
- Full alpha blending support
- High-quality 9-tap filter for scaling
- YUV-to-RGB conversion and 8-bit color lookup
- 90°,180°, 270° rotation on every primitive
- Full asynchronous operation through DMA command stream
- Support for clipping rectangle
- Supports up to 255 rectangles per primitive call
- Simple programming interface
- Very low CPU overhead – no need to wait until 2D engine is finished before changing states or issuing new commands
- Allows batching of commands to further reduce CPU overhead (begin/end paradigm)
- High-quality image and video scalar
- Filter kernel size is programmable from 1x1 to 9x9
- Vertical and horizontal kernel sizes are independently programmable
- Filter coefficient can be programmed for any type of filter
- Supports 32 filter phases
- Programmable format conversion
- Supports 11 source formats
- Standard configuration supports 7 destination formats
- Display resolution HD 1080p
GC200
| GC200 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
243 K |
243 K |
| Memory Bits |
9 KB |
9 KB |
| Synthesis Area (std. cells + memory) |
0.57 mm2 |
0.57 mm2 |
| Silicon Area |
0.75 mm2 |
0.75 mm2 |
| Clock Frequency in Silicon |
250 MHz |
375 MHz |
| Active Power |
15 mW |
19 mW |
| Leakage Power |
0.01 mW |
0.11 mW |
| Pixel Rate, Textured |
250 M pix/s |
375 M pix/s |
GC300
| GC300 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
334 K |
334 K |
| Memory Bits |
11 KB |
11 KB |
| Synthesis Area (std. cells + memory) |
0.72 mm2 |
0.72 mm2 |
| Silicon Area |
0.96 mm2 |
0.96 mm2 |
| Clock Frequency in Silicon |
250 MHz |
375 MHz |
| Active Power |
19 mW |
25 mW |
| Leakage Power |
0.02 mW |
0.14 mW |
| Pixel Rate, Textured |
250 M pix/s |
375 M pix/s |
Vector Graphics 2D GPU: GC350
- Coordinate systems and transformations
- Viewport clipping, Scissoring, and Alpha masking
- Rotation to any angle
- YUY2 and YUV420 video image conversion
- Path and stroke generation
- Image interpolation and filters
- Gradient paint
- Pattern paint
- Blending
GC350
| GC350 |
65nm LP |
65nm G+ |
| Synthesis Gate Count (ND2D1 gates) |
451 K |
451 K |
| Memory Bits |
10 KB |
10 KB |
| Synthesis Area (std. cells + memory) |
0.91 mm2 |
0.91 mm2 |
| Silicon Area |
1.22 mm2 |
1.22 mm2 |
| Clock Frequency in Silicon |
300 MHz |
450 MHz |
| Active Power |
29 mW |
37 mW |
| Leakage Power |
0.02 mW |
0.17 mW |
| Pixel Rate, Textured |
300 M pix/s |
450 M pix/s |
|
|
