This page contains information about Intel's GPUs and motherboard graphics chipsets in table form. In 1982 Intel licensed the NEC µPD7220 and announced it as the Intel 82720 Graphics Display Controller.
First generation
Intel's first generation GPUs.
Second generation
Intel marketed its second generation using the brand Extreme Graphics. These chips added support for texture combiners allowing support for OpenGL 1.3.
Third generation
Intel started delivering Direct3D 9 Shader 2.0 GPUs to the integrated chipsets. They featured full Direct3D 9 Shader 2.0 support, but Vertex Shaders were rendered in Software mode.
Fourth generation
Intel released its latest generation of integrated GMA chipsets. With the fourth generation, they included full hardware shaders. With full Direct3D 9.0c / Direct3D 10 support, more games were playable, but were never used for gaming because they were too slow to process DirectX 10 graphics.
Fifth generation
- Each EU has a 128-bit wide FPU that natively executes eight 16-bit or four 32-bit operations per clock cycle.
Sixth generation
- Each EU has a 128-bit wide FPU that natively executes eight 16-bit or four 32-bit operations per clock cycle.
- Double peak performance per clock cycle compared to previous generation due to fused multiply-add instruction.
- The entire GPU shares a sampler and an ROP.
Seventh generation
- 1 FP32 ALUs : EUs : Subslices
- Each EU contains 2 × SIMD-4 FPUs and has double peak performance per clock cycle compared to previous generation.
- Each Subslice contains 6 or 8 (or 10 in Haswell GPUs) EUs and a sampler, and has 64KiB shared memory.
- 64bit floating-point performance is 1/4 of 32bit floating-point performance.
Eighth generation
- 1 FP32 ALUs : EUs : Subslices
- Each EU contains 2 x SIMD-4 FPUs.
- Each Subslice contains 8 EUs and a sampler (4 tex/clk), and has 64KiB shared memory.
- 64bit floating-point performance is 1/4 of 32bit floating-point performance.
- 16bit floating-point (or integer) performance is 2x 32bit floating-point (or integer) performance.
- Intel Quick Sync Video
- For Windows 10, the total system memory that is available for graphics use is half the system memory. For Windows 8, it is up to 3840 MB. On Windows 7, it is up to about 1.7 GB through DVMT.
Ninth generation
- 1 FP32 ALUs : EUs : Subslices
- Each EU contains 2 x SIMD-4 FPUs.
- Each Subslice contains 8 EUs (two of which are disabled in GT1) and a sampler (4 tex/clk), and has 64KiB shared memory.
- 64bit floating-point performance is 1/4 (1/8 in Apollo Lake) of 32bit floating-point performance.
- 16bit floating-point (or integer) performance is 2x 32bit floating-point (or integer) performance.
- Intel Quick Sync Video
- For Windows 10, the total system memory that is available for graphics use is half the system memory. For Windows 8, it is up to 3840 MB. On Windows 7, it is up to about 1.7 GB through DVMT.
PowerVR based
See also
- Intel Quick Sync Video
- Comparison of AMD graphics processing units
- Comparison of Nvidia graphics processing units
- Comparison of Intel processors
- List of Intel chipsets
- Intel Larrabee GPU
- Xeon Phi
Notes
- Acronyms
- The following acronyms are used throughout the article.
- EU: Execution Unit
- iDCT: Inverse discrete cosine transform
- iMDCT: Inverse modified discrete cosine transform
- LF: In-loop deblocking filter
- MC: Motion compensation
- VLD: Variable-length code (sometimes referred to as slice-level acceleration)
- WMV9: Windows Media Video 9 codec
- Full hardware acceleration techniques
- Intel graphic processing units employ the following techniques in hardware acceleration of digital video playback.
- Calculation
- The raw performance of integrated GPU, in single-precision FLOPS, can be calculated as follows:
- Fourth generation (GMA 3, 4) - EU * 2 * 2 [multiply + accumulate] * clock speed
- Fifth generation (HD Graphics) - EU * 2 * 2 [multiply + accumulate] * clock speed
- Sixth generation (HD Graphics 2000, 3000) - EU * 4 [dual-issue x 2 SP] * 2 [multiply + accumulate] * clock speed
- Seventh generation (HD Graphics 2500, 4000 ~ 5200) - EUs * 8 [2 x SIMD-4 FPU] * 2 [MUL + ADD] * clock speed
- Eighth generation (HD Graphics 5300 ~ 6300) - EUs * 8 [2 x SIMD-4 FPU] * 2 [MUL + ADD] * clock speed
- Ninth generation (HD Graphics 5xx) - EUs * 8 [2 x SIMD-4 FPU] * 2 [MUL + ADD] * clock speed
- Double-precision FLOPS:
- Seventh generation (HD Graphics 2500, 4000 ~ 5200) - EUs * 4 [SIMD-4 FPU] * 2 [MUL + ADD] * clock speed / 2
- Eighth generation (HD Graphics 5300 ~ 6300) - EUs * 4 [SIMD-4 FPU] * 2 [MUL + ADD] * clock speed / 2
- Ninth generation (HD Graphics 5xx) - EUs * 4 [SIMD-4 FPU] * 2 [MUL + ADD] * clock speed / 2
- For example, the HD Graphics 3000 is rated at 125 GFLOPS, which is consistent with the formula (12 * 4 * 2 * 1,300Â MHz).