Video Coding Engine

AMD hardware accelerator for encoding MP4 H.264 videos, built into AMD GPU's From Wikipedia, the free encyclopedia

Video Code Engine (VCE, was earlier referred to as Video Coding Engine,[1] Video Compression Engine[2] or Video Codec Engine[3] in official AMD documentation) is AMD's video encoding application-specific integrated circuit implementing the video codec H.264/MPEG-4 AVC. Since 2012 it was integrated into all of their GPUs and APUs except Oland.

VCE was introduced with the Radeon HD 7000 series on 22 December 2011.[4][5][6] VCE occupies a considerable amount of the die surface at the time of its introduction[7] and is not to be confused with AMD's Unified Video Decoder (UVD).

As of AMD Raven Ridge (released January 2018), UVD and VCE were succeeded by Video Core Next (VCN).

Overview

Summarize
Perspective
In "full-fixed mode" the entire computation is done by the fixed-function VCE unit. Full-fixed mode can be accessed through the OpenMAX IL API.
The entropy encoding block of the VCE ASIC is also separately accessible, enabling "hybrid mode". In "hybrid mode" most of the computation is done by the 3D engine of the GPU. Using AMD's Accelerated Parallel Programming SDK and OpenCL developers can create hybrid encoders that pair custom motion estimation, inverse discrete cosine transform and motion compensation with the hardware entropy encoding to achieve faster than real-time encoding.

The handling of video data involves computation of data compression algorithms and possibly of video processing algorithms. As the template compression methods shows, lossy video compression algorithms involve the steps: motion estimation (ME), discrete cosine transform (DCT), and entropy encoding (EC).

AMD Video Code Engine (VCE) is a full hardware implementation of the video codec H.264/MPEG-4 AVC. It is capable of delivering 1080p at 60 frames/sec. Because its entropy encoding block is also a separately accessible Video Codec Engine, it can be operated in two modes: full-fixed mode and hybrid mode.[8][9]

By employing AMD APP SDK, available for Linux and Microsoft Windows, developers can create hybrid encoders that pair custom motion estimation, inverse discrete cosine transform and motion compensation with the hardware entropy encoding to achieve faster than real-time encoding. In hybrid mode, only the entropy encoding block of the VCE unit is used, while the remaining computation is offloaded to the 3D engine of the GPU, so the computing scales with the number of available compute units (CUs).

VCE 1.0

VCE[1] Version 1.0 supports H.264 YUV420 (I & P frames), H.264 SVC Temporal Encode VCE, and Display Encode Mode (DEM).

It can be found on:

  • Piledriver-based
    • Trinity APUs (Ax-5xxx, e.g. A10-5800K)
    • Richland APUs (Ax-6xxx, e.g. A10-6800K)
  • GPUs of the Southern Islands generation (GCN1: CAYMAN, ARUBA (Trinity/Richland), CAPE VERDE, PITCAIRN, TAHITI). These are
    • Radeon HD 7700 series (except HD 7790 with VCE 2.0)
    • Radeon HD 7800 series
    • Radeon HD 7900 series
    • Radeon HD 8570 to 8990 (except HD 8770 with VCE 2.0)
    • Radeon R7 250E, 250X, 265 / R9 270, 270X, 280, 280X
    • Radeon R7 360, 370, 455 / R9 370, 370X
    • Mobile Radeon HD 77x0M to HD 7970M
    • Mobile Radeon HD 8000-Series
    • Mobile Radeon Rx M2xx Series (except R9 M280X with VCE 2.0 and R9 M295X with VCE 3.0)
    • Mobile Radeon R5 M330 to R9 M390
    • FirePro cards with 1st Generation GCN (GCN1) (Except W2100, which is Oland XT)

VCE 2.0

Compared to the first version, VCE 2.0 adds H.264 YUV444 (I-Frames), B-frames for H.264 YUV420, and improvements to the DEM (Display Encode Mode), which results in a better encoding quality.

It can be found on:

  • Steamroller-based
    • Kaveri APUs (Ax-7xxx, e.g. A10-7850K)
    • Godavari APUs (Ax-7xxx, e.g. A10-7890K)
  • Jaguar-based
    • Kabini APUs (e.g. Athlon 5350, Sempron 2650)
    • Temash APUs (e.g. A6-1450, A4-1200)
  • Puma-based
    • Beema and Mullins
  • GPUs of the Sea Islands generation as well Bonaire or Hawaii GPUs (2nd Generation Graphics Core Next), such as
    • Radeon HD 7790, 8770
    • Radeon R7 260, 260X / R9 290, 290X, 295X2
    • Radeon R7 360 / R9 390, 390X
    • Mobile Radeon R9 M280X
    • Mobile Radeon R9 M385, M385X
    • Mobile Radeon R9 M470, M470X
    • FirePro W4300, W5100, W8100, W9100, S9100, S9150, S9170
    • Mobile FirePro M6100, W6150M, W6170M

VCE 3.0

Video Code Engine 3.0 (VCE 3.0) technology features a new high-quality video scaling and - since version 3.4 - High Efficiency Video Coding (HEVC/H.265).[10][11]

It, together with UVD 6.0, can be found on 3rd generation of Graphics Core Next (GCN3) with "Tonga" and "Fiji" (VCE 3.0) based graphics controller hardware, which is now used AMD Radeon Rx 300 series (Pirate Islands GPU family) and VCE 3.4 by actual AMD Radeon Rx 400 series and AMD Radeon 500 series (both Polaris GPU family).

  • Tonga: Radeon R9 285, 380, 380X; Mobile Radeon R9 M390X, M395, M395X, M485X
  • Tonga XT: FirePro W7100, S7100X, S7150, S7150 X2
  • Fiji: Radeon R9 Fury, Fury X, Nano; Radeon Pro Duo (2016); FirePro S9300, W7170M; Instinct MI8
  • Polaris: RX 460, 470, 480; RX 550, 560, 570, 580; Radeon Pro Duo (2017)

AMD's Carrizo platform features VCE 3.1, retaining the same capabilities as the VCE found in "Fiji" and "Tonga".[12]

Stoney Ridge features a cut down version of VCE 3.4 without HEVC/H.265 encoding and is accompanied by a UVD 6.2 engine.[13]

VCE 3.0 removes support for H.264 B-frames.[14]

VCE 4.0

The Video Code Engine 4.0 encoder and UVD 7.0 decoder are included in the Vega-based GPUs.[15][16]

VCE 4.1

AMD's Vega20 GPU, present in the Instinct Mi50, Instinct Mi60 and Radeon VII cards, include VCE 4.1 and two UVD 7.2 instances.[17][18]

Feature overview

APUs

The following table shows features of AMD's processors with 3D graphics, including APUs (see also: List of AMD processors with 3D graphics).

More information Platform, High, standard and low power ...
Platform High, standard and low power Low and ultra-low power
CodenameServer Basic Toronto
Micro Kyoto
Desktop Performance Raphael Phoenix
Mainstream Llano Trinity Richland Kaveri Kaveri Refresh (Godavari) Carrizo Bristol Ridge Raven Ridge Picasso Renoir Cezanne
Entry
Basic Kabini Dalí
MobilePerformance Renoir Cezanne Rembrandt Dragon Range
Mainstream Llano Trinity Richland Kaveri Carrizo Bristol Ridge Raven Ridge Picasso Renoir
Lucienne
Cezanne
Barceló
Phoenix
Entry Dalí Mendocino
Basic Desna, Ontario, Zacate Kabini, Temash Beema, Mullins Carrizo-L Stoney Ridge Pollock
Embedded Trinity Bald Eagle Merlin Falcon,
Brown Falcon
Great Horned Owl Grey Hawk Ontario, Zacate Kabini Steppe Eagle, Crowned Eagle,
LX-Family
Prairie Falcon Banded Kestrel River Hawk
ReleasedAug 2011Oct 2012Jun 2013Jan 2014 2015Jun 2015Jun 2016Oct 2017Jan 2019Mar 2020 Jan 2021Jan 2022Sep 2022Jan 2023Jan 2011May 2013Apr 2014May 2015Feb 2016Apr 2019Jul 2020Jun 2022Nov 2022
CPU microarchitecture K10 Piledriver Steamroller Excavator "Excavator+"[19] Zen Zen+ Zen 2 Zen 3 Zen 3+ Zen 4 Bobcat Jaguar Puma Puma+[20] "Excavator+" Zen Zen+ "Zen 2+"
ISAx86-64 v1x86-64 v2x86-64 v3x86-64 v4x86-64 v1x86-64 v2x86-64 v3
Socket Desktop Performance AM5
Mainstream AM4
Entry FM1 FM2 FM2+ FM2+[a], AM4 AM4
Basic AM1 FP5
Other FS1 FS1+, FP2 FP3 FP4 FP5 FP6 FP7 FL1 FP7
FP7r2
FP8
FT1 FT3 FT3b FP4 FP5 FT5 FP5 FT6
PCI Express version 2.0 3.0 4.0 5.0 4.0 2.0 3.0
CXL
Fab. (nm) GF 32SHP
(HKMG SOI)
GF 28SHP
(HKMG bulk)
GF 14LPP
(FinFET bulk)
GF 12LP
(FinFET bulk)
TSMC N7
(FinFET bulk)
TSMC N6
(FinFET bulk)
CCD: TSMC N5
(FinFET bulk)

cIOD: TSMC N6
(FinFET bulk)
TSMC 4nm
(FinFET bulk)
TSMC N40
(bulk)
TSMC N28
(HKMG bulk)
GF 28SHP
(HKMG bulk)
GF 14LPP
(FinFET bulk)
GF 12LP
(FinFET bulk)
TSMC N6
(FinFET bulk)
Die area (mm2)228246245245250210[21]156 180210CCD: (2x) 70
cIOD: 122
17875 (+ 28 FCH)107 ?125149~100
Min TDP (W)351712101565354.543.95106128
Max APU TDP (W)10095654517054182565415
Max stock APU base clock (GHz)33.84.14.13.73.83.63.73.84.03.34.74.31.752.222.23.22.61.23.352.8
Max APUs per node[b]11
Max core dies per CPU1211
Max CCX per core die1211
Max cores per CCX482424
Max CPU[c] cores per APU481682424
Max threads per CPU core1212
Integer pipeline structure3+32+24+24+2+11+3+3+1+21+1+1+12+24+24+2+1
i386, i486, i586, CMOV, NOPL, i686, PAE, NX bit, CMPXCHG16B, AMD-V, RVI, ABM, and 64-bit LAHF/SAHFYes Yes
IOMMU[d]v2v1v2
BMI1, AES-NI, CLMUL, and F16C YesYes
MOVBEYes
AVIC, BMI2, RDRAND, and MWAITX/MONITORX Yes
SME[e], TSME[e], ADX, SHA, RDSEED, SMAP, SMEP, XSAVEC, XSAVES, XRSTORS, CLFLUSHOPT, CLZERO, and PTE CoalescingYes Yes
GMET, WBNOINVD, CLWB, QOS, PQE-BW, RDPID, RDPRU, and MCOMMITYes Yes
MPK, VAESYes
SGX
FPUs per core10.5110.51
Pipes per FPU22
FPU pipe width128-bit256-bit80-bit128-bit256-bit
CPU instruction set SIMD levelSSE4a[f]AVX AVX2AVX-512SSSE3AVXAVX2
3DNow!3DNow!+
PREFETCH/PREFETCHWYes Yes
GFNIYes
AMX
FMA4, LWP, TBM, and XOPYes Yes
FMA3Yes Yes
AMD XDNAYes
L1 data cache per core (KiB)64163232
L1 data cache associativity (ways)2488
L1 instruction caches per core10.51 10.51
Max APU total L1 instruction cache (KiB)256128192256512256 64128 96 128
L1 instruction cache associativity (ways)2348 2 3 4 8
L2 caches per core10.5110.51
Max APU total L2 cache (MiB)424161212
L2 cache associativity (ways)168168
Max on-die L3 cache per CCX (MiB)416324
Max 3D V-Cache per CCD (MiB)64
Max total in-CCD L3 cache per APU (MiB)4816644
Max. total 3D V-Cache per APU (MiB)64
Max. board L3 cache per APU (MiB)
Max total L3 cache per APU (MiB)48161284
APU L3 cache associativity (ways)1616
L3 cache schemeVictimVictim
Max. L4 cache
Max stock DRAM supportDDR3-1866DDR3-2133DDR3-2133, DDR4-2400DDR4-2400DDR4-2933DDR4-3200, LPDDR4-4266DDR5-4800, LPDDR5-6400DDR5-5200DDR5-5600, LPDDR5x-7500DDR3L-1333DDR3L-1600DDR3L-1866DDR3-1866, DDR4-2400DDR4-2400DDR4-1600DDR4-3200LPDDR5-5500
Max DRAM channels per APU21212
Max stock DRAM bandwidth (GB/s) per APU29.86634.13238.40046.93268.256102.40083.200120.000 10.66612.80014.93319.20038.40012.80051.20088.000
GPU microarchitectureTeraScale 2 (VLIW5)TeraScale 3 (VLIW4)GCN 2nd genGCN 3rd genGCN 5th gen[22]RDNA 2RDNA 3TeraScale 2 (VLIW5)GCN 2nd genGCN 3rd gen[22]GCN 5th genRDNA 2
GPU instruction setTeraScale instruction setGCN instruction setRDNA instruction setTeraScale instruction setGCN instruction setRDNA instruction set
Max stock GPU base clock (MHz)60080084486611081250140021002400400 538600 ?847900120060013001900
Max stock GPU base GFLOPS[g]480614.4648.1886.71134.517601971.22150.43686.4102.4 86 ? ? ?345.6460.8230.41331.2486.4
3D engine[h]Up to 400:20:8Up to 384:24:6Up to 512:32:8Up to 704:44:16[23]Up to 512:32:8768:48:8128:8:480:8:4128:8:4Up to 192:12:8Up to 192:12:4192:12:4Up to 512:?:?128:?:?
IOMMUv1IOMMUv2IOMMUv1 ?IOMMUv2
Video decoderUVD 3.0UVD 4.2UVD 6.0VCN 1.0[24]VCN 2.1[25] VCN 2.2[25]VCN 3.1 ?UVD 3.0UVD 4.0UVD 4.2UVD 6.2VCN 1.0VCN 3.1
Video encoderVCE 1.0VCE 2.0VCE 3.1VCE 2.0VCE 3.4
AMD Fluid Motion No Yes No No Yes No
GPU power savingPowerPlayPowerTunePowerPlayPowerTune[26]
TrueAudioYes[27] ? Yes
FreeSync1
2
1
2
HDCP[i] ?1.42.22.3 ?1.42.22.3
PlayReady[i]3.0 not yet3.0 not yet
Supported displays[j]2–32–433 (desktop)
4 (mobile, embedded)
42344
/drm/radeon[k][29][30]Yes Yes
/drm/amdgpu[k][31]Yes[32] Yes[32]
Close
  1. For FM2+ Excavator models: A8-7680, A6-7480 & Athlon X4 845.
  2. A PC would be one node.
  3. An APU combines a CPU and a GPU. Both have cores.
  4. Requires firmware support.
  5. Requires firmware support.
  6. No SSE4. No SSSE3.
  7. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  8. To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
  9. To feed more than two displays, the additional panels must have native DisplayPort support.[28] Alternatively active DisplayPort-to-DVI/HDMI/VGA adapters can be employed.
  10. DRM (Direct Rendering Manager) is a component of the Linux kernel. Support in this table refers to the most current version.

GPUs

The following table shows features of AMD/ATI's GPUs (see also: List of AMD graphics processing units).

More information Name of GPU series, Wonder ...
Name of GPU series Wonder Mach 3D Rage Rage Pro Rage 128 R100 R200 R300 R400 R500 R600 RV670 R700 Evergreen Northern
Islands
Southern
Islands
Sea
Islands
Volcanic
Islands
Arctic
Islands
/Polaris
Vega Navi 1x Navi 2x Navi 3x Navi 4x
Released 1986 1991 Apr
1996
Mar
1997
Aug
1998
Apr
2000
Aug
2001
Sep
2002
May
2004
Oct
2005
May
2007
Nov
2007
Jun
2008
Sep
2009
Oct
2010
Dec
2010
Jan
2012
Sep
2013
Jun
2015
Jun 2016, Apr 2017, Aug 2019 Jun 2017, Feb 2019 Jul
2019
Nov
2020
Dec
2022
Feb
2025
Marketing Name Wonder Mach 3D
Rage
Rage
Pro
Rage
128
Radeon
7000
Radeon
8000
Radeon
9000
Radeon
X700/X800
Radeon
X1000
Radeon
HD 2000
Radeon
HD 3000
Radeon
HD 4000
Radeon
HD 5000
Radeon
HD 6000
Radeon
HD 7000
Radeon
200
Radeon
300
Radeon
400/500/600
Radeon
RX Vega, Radeon VII
Radeon
RX 5000
Radeon
RX 6000
Radeon
RX 7000
Radeon
RX 9000
AMD support Ended Current
Kind 2D 3D
Instruction set architecture Not publicly known TeraScale instruction set GCN instruction set RDNA instruction set
Microarchitecture Not publicly known GFX1 GFX2 TeraScale 1
(VLIW5)

(GFX3)
TeraScale 2
(VLIW5)

(GFX4)
TeraScale 2
(VLIW5)

up to 68xx
(GFX4)
TeraScale 3
(VLIW4)

in 69xx [33][34]
(GFX5)
GCN 1st
gen

(GFX6)
GCN 2nd
gen

(GFX7)
GCN 3rd
gen

(GFX8)
GCN 4th
gen

(GFX8)
GCN 5th
gen

(GFX9)
RDNA
(GFX10.1)
RDNA 2
(GFX10.3)
RDNA 3
(GFX11)
RDNA 4
(GFX12)
Type Fixed pipeline[a] Programmable pixel & vertex pipelines Unified shader model
Direct3D 5.0 6.0 7.0 8.1 9.0
11 (9_2)
9.0b
11 (9_2)
9.0c
11 (9_3)
10.0
11 (10_0)
10.1
11 (10_1)
11 (11_0) 11 (11_1)
12 (11_1)
11 (12_0)
12 (12_0)
11 (12_1)
12 (12_1)
11 (12_1)
12 (12_2)
Shader model 1.4 2.0+ 2.0b 3.0 4.0 4.1 5.0 5.1 5.1
6.5
6.7 6.8
OpenGL 1.1 1.2 1.3 2.1[b][35] 3.3 4.5[36][37][38][c] 4.6
Vulkan 1.1[c][d] 1.3[39] 1.4[40]
OpenCL Close to Metal 1.1 (not supported by Mesa) 1.2+ (on Linux: 1.1+ (no Image support on clover, with by rustiCL) with Mesa, 1.2+ on GCN 1.Gen) 2.0+ (Adrenalin driver on Win7+)
(on Linux ROCM, Mesa 1.2+ (no Image support in clover, but in rustiCL with Mesa, 2.0+ and 3.0 with AMD drivers or AMD ROCm), 5th gen: 2.2 win 10+ and Linux RocM 5.0+
2.2+ and 3.0 windows 8.1+ and Linux ROCM 5.0+ (Mesa rustiCL 1.2+ and 3.0 (2.1+ and 2.2+ wip))[41][42][43]
HSA / ROCm Yes  ?
Video decoding ASIC Avivo/UVD UVD+ UVD 2 UVD 2.2 UVD 3 UVD 4 UVD 4.2 UVD 5.0 or 6.0 UVD 6.3 UVD 7 [15][e] VCN 2.0 [15][e] VCN 3.0 [44] VCN 4.0 VCN 5.0
Video encoding ASIC VCE 1.0 VCE 2.0 VCE 3.0 or 3.1 VCE 3.4 VCE 4.0 [15][e]
Fluid Motion [f] No Yes No  ?
Power saving  ? PowerPlay PowerTune PowerTune & ZeroCore Power  ?
TrueAudio Via dedicated DSP Via shaders
FreeSync 1
2
HDCP[g]  ? 1.4 2.2 2.3 [45]
PlayReady[g] 3.0 No 3.0
Supported displays[h] 1–2 2 2–6  ? 4
Max. resolution  ? 2–6 ×
2560×1600
2–6 ×
4096×2160 @ 30 Hz
2–6 ×
5120×2880 @ 60 Hz
3 ×
7680×4320 @ 60 Hz [46]

7680×4320 @ 60 Hz PowerColor
7680x4320

@165 Hz

7680x4320
/drm/radeon[i] Yes
/drm/amdgpu[i] Optional [47] Yes
Close
  1. The Radeon 100 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
  2. R300, R400 and R500 based cards do not fully comply with OpenGL 2+ as the hardware does not support all types of non-power of two (NPOT) textures.
  3. OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.
  4. Vulkan support is theoretically possible but has not been implemented in a stable driver.
  5. The UVD and VCE were replaced by the Video Core Next (VCN) ASIC in the Raven Ridge APU implementation of Vega.
  6. Video processing for video frame rate interpolation technique. In Windows it works as a DirectShow filter in your player. In Linux, there is no support on the part of drivers and / or community.
  7. To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
  8. More displays may be supported with native DisplayPort connections, or splitting the maximum resolution between multiple monitors with active converters.
  9. DRM (Direct Rendering Manager) is a component of the Linux kernel. AMDgpu is the Linux kernel module. Support in this table refers to the most current version.

Operating system support

Summarize
Perspective

The VCE SIP core needs to be supported by the device driver. The device driver provides one or multiple interfaces, e. g. OpenMAX IL. One of these interfaces is then used by end-user software, like GStreamer or HandBrake (HandBrake rejected VCE support in December 2016,[48] but added it in December 2018[49]), to access the VCE hardware and make use of it.

AMD's proprietary device driver AMD Catalyst is available for multiple operating systems and support for VCE was added to it[citation needed]. Additionally, a free device driver is available. This driver also supports the VCE hardware.

Linux

Thumb
Support for the VCE ASIC is contained in the Linux kernel device driver amdgpu.

Windows

The software "MediaShow Espresso Video Transcoding" seems to utilize VCE and UVD to the fullest extent possible.[54]

XSplit Broadcaster supports VCE from version 1.3.[55]

Open Broadcaster Software (OBS Studio) supports VCE for recording and streaming. The original Open Broadcaster Software (OBS) requires a fork build in order to enable VCE.[56]

AMD Radeon Software supports VCE with built in game capture ("Radeon ReLive") and use AMD AMF/VCE on APU or Radeon Graphics card to reduce FPS drop when capturing game or video content.[57]

HandBrake added Video Coding Engine support in version 1.2.0 in December 2018.[49]

Successor

The VCE was succeeded by AMD Video Core Next in the Raven Ridge series of APUs released in October 2017. The VCN combines both encode (VCE) and decode (UVD).[58]

See also

Video hardware technologies

AMD

Others

References

Loading related searches...

Wikiwand - on

Seamless Wikipedia browsing. On steroids.