Video Code Engine (VCE; earlier referred to as Video Coding Engine, Video Compression Engine or Video Codec Engine in official 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. VCE occupies a considerable amount of the die surface at the time of its introduction 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

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.

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 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).

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".

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.

VCE 3.0 removes support for H.264 B-frames.

VCE 4.0

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

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.

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).

  • view
  • talk
  • edit
PlatformHigh, standard and low powerLow and ultra-low power
CodenameServerBasicToronto
MicroKyoto
DesktopPerformanceRaphaelPhoenix
MainstreamLlanoTrinityRichlandKaveriKaveri Refresh (Godavari)CarrizoBristol RidgeRaven RidgePicassoRenoirCezanne
Entry
BasicKabiniDalí
MobilePerformanceRenoirCezanneRembrandtDragon Range
MainstreamLlanoTrinityRichlandKaveriCarrizoBristol RidgeRaven RidgePicassoRenoir LucienneCezanne BarcelóPhoenix
EntryDalíMendocino
BasicDesna, Ontario, ZacateKabini, TemashBeema, MullinsCarrizo-LStoney RidgePollock
EmbeddedTrinityBald EagleMerlin Falcon, Brown FalconGreat Horned OwlGrey HawkOntario, ZacateKabiniSteppe Eagle, Crowned Eagle, LX-FamilyPrairie FalconBanded KestrelRiver Hawk
ReleasedAug 2011Oct 2012Jun 2013Jan 20142015Jun 2015Jun 2016Oct 2017Jan 2019Mar 2020Jan 2021Jan 2022Sep 2022Jan 2023Jan 2011May 2013Apr 2014May 2015Feb 2016Apr 2019Jul 2020Jun 2022Nov 2022
CPU microarchitectureK10PiledriverSteamrollerExcavator"Excavator+"ZenZen+Zen 2Zen 3Zen 3+Zen 4BobcatJaguarPumaPuma+"Excavator+"ZenZen+"Zen 2+"
ISAx86-64 v1x86-64 v2x86-64 v3x86-64 v4x86-64 v1x86-64 v2x86-64 v3
SocketDesktopPerformance—N/aAM5—N/a—N/a
Mainstream—N/aAM4—N/a—N/a
EntryFM1FM2FM2+FM2+, AM4AM4—N/a
Basic—N/a—N/aAM1—N/aFP5—N/a
OtherFS1FS1+, FP2FP3FP4FP5FP6FP7FL1FP7 FP7r2 FP8FT1FT3FT3bFP4FP5FT5FP5FT6
PCI Express version2.03.04.05.04.02.03.0
CXL—N/a—N/a
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)228246245245250210156180210CCD: (2x) 70 cIOD: 12217875 (+ 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 node11
Max core dies per CPU1211
Max CCX per core die1211
Max cores per CCX482424
Max CPU 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/SAHF
IOMMU—N/av2v1v2
BMI1, AES-NI, CLMUL, and F16C—N/a
MOVBE—N/a
AVIC, BMI2, RDRAND, and MWAITX/MONITORX—N/a
SME, TSME, ADX, SHA, RDSEED, SMAP, SMEP, XSAVEC, XSAVES, XRSTORS, CLFLUSHOPT, CLZERO, and PTE Coalescing—N/a—N/a
GMET, WBNOINVD, CLWB, QOS, PQE-BW, RDPID, RDPRU, and MCOMMIT—N/a—N/a
MPK, VAES—N/a—N/a
SGX—N/a—N/a
FPUs per core10.5110.51
Pipes per FPU22
FPU pipe width128-bit256-bit80-bit128-bit256-bit
CPU instruction set SIMD levelSSE4aAVXAVX2AVX-512SSSE3AVXAVX2
3DNow!3DNow!+—N/a—N/a
PREFETCH/PREFETCHW
GFNI—N/a—N/a
AMX—N/a
FMA4, LWP, TBM, and XOP—N/a—N/a—N/a—N/a
FMA3
AMD XDNA—N/a—N/a
L1 data cache per core (KiB)64163232
L1 data cache associativity (ways)2488
L1 instruction caches per core10.5110.51
Max APU total L1 instruction cache (KiB)2561281922565122566412896128
L1 instruction cache associativity (ways)23482348
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)—N/a41632—N/a4
Max 3D V-Cache per CCD (MiB)—N/a64—N/a—N/a
Max total in-CCD L3 cache per APU (MiB)4816644
Max. total 3D V-Cache per APU (MiB)—N/a64—N/a—N/a
Max. board L3 cache per APU (MiB)—N/a—N/a
Max total L3 cache per APU (MiB)48161284
APU L3 cache associativity (ways)1616
L3 cache schemeVictimVictim
Max. L4 cache—N/a—N/a
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 APU29.86634.13238.40046.93268.256102.40083.200120.00010.66612.80014.93319.20038.40012.80051.20088.000
GPU microarchitectureTeraScale 2 (VLIW5)TeraScale 3 (VLIW4)GCN 2nd genGCN 3rd genGCN 5th genRDNA 2RDNA 3TeraScale 2 (VLIW5)GCN 2nd genGCN 3rd genGCN 5th genRDNA 2
GPU instruction setTeraScale instruction setGCN instruction setRDNA instruction setTeraScale instruction setGCN instruction setRDNA instruction set
Max stock GPU base clock (MHz)60080084486611081250140021002400400538600?847900120060013001900
Max stock GPU base GFLOPS480614.4648.1886.71134.517601971.22150.43686.4102.486???345.6460.8230.41331.2486.4
3D engineUp to 400:20:8Up to 384:24:6Up to 512:32:8Up to 704:44:16Up 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 1.0VCN 2.1VCN 2.2VCN 3.1?UVD 3.0UVD 4.0UVD 4.2UVD 6.2VCN 1.0VCN 3.1
Video encoder—N/aVCE 1.0VCE 2.0VCE 3.1—N/aVCE 2.0VCE 3.4
AMD Fluid Motion
GPU power savingPowerPlayPowerTunePowerPlayPowerTune
TrueAudio—N/a?—N/a
FreeSync1 21 2
HDCP?1.42.22.3?1.42.22.3
PlayReady—N/a3.0 not yet—N/a3.0 not yet
Supported displays2–32–433 (desktop) 4 (mobile, embedded)42344
/drm/radeon—N/a—N/a
/drm/amdgpu—N/a—N/a

GPUs

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

  • view
  • talk
  • edit
Name of GPU seriesWonderMach3D RageRage ProRage 128R100R200R300R400R500R600RV670R700EvergreenNorthern IslandsSouthern IslandsSea IslandsVolcanic IslandsArctic Islands/PolarisVegaNavi 1xNavi 2xNavi 3xNavi 4x
Released19861991Apr 1996Mar 1997Aug 1998Apr 2000Aug 2001Sep 2002May 2004Oct 2005May 2007Nov 2007Jun 2008Sep 2009Oct 2010Dec 2010Jan 2012Sep 2013Jun 2015Jun 2016, Apr 2017, Aug 2019Jun 2017, Feb 2019Jul 2019Nov 2020Dec 2022Feb 2025
Marketing NameWonderMach3D RageRage ProRage 128Radeon 7000Radeon 8000Radeon 9000Radeon X700/X800Radeon X1000Radeon HD 2000Radeon HD 3000Radeon HD 4000Radeon HD 5000Radeon HD 6000Radeon HD 7000Radeon 200Radeon 300Radeon 400/500/600Radeon RX Vega, Radeon VIIRadeon RX 5000Radeon RX 6000Radeon RX 7000Radeon RX 9000
AMD support
Kind2D3D
Instruction set architectureNot publicly knownTeraScale instruction setGCN instruction setRDNA instruction set
MicroarchitectureNot publicly knownGFX1GFX2TeraScale 1 (VLIW5) (GFX3)TeraScale 2 (VLIW5) (GFX4)TeraScale 2 (VLIW5) up to 68xx (GFX4)TeraScale 3 (VLIW4) in 69xx (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)
TypeFixed pipelineProgrammable pixel & vertex pipelinesUnified shader model
Direct3D—N/a5.06.07.08.19.0 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—N/a1.42.0+2.0b3.04.04.15.05.15.1 6.56.76.8
OpenGL—N/a1.11.21.31.53.34.5 (Windows), 4.6 (Linux Mesa 25.2+)4.6
Vulkan—N/a1.11.31.4
OpenCL—N/aClose to Metal1.1 (not supported by Mesa)1.2+ (on Linux: 1.1+ (no Image support on Clover, with Rusticl) with Mesa, 1.2+ on GCN 1.Gen)2.0+ (Adrenalin driver on Win 7+) (on Linux ROCm, Mesa 1.2+ (no support in Clover, only Rusticl, 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+))
HSA / ROCm—N/a?
Video decoding ASIC—N/aAvivo/UVDUVD+UVD 2UVD 2.2UVD 3UVD 4UVD 4.2UVD 5.0 or 6.0UVD 6.3UVD 7VCN 2.0VCN 3.0VCN 4.0VCN 5.0
Video encoding ASIC—N/aVCE 1.0VCE 2.0VCE 3.0 or 3.1VCE 3.4VCE 4.0
Fluid Motion?
Power saving?PowerPlayPowerTunePowerTune & ZeroCore Power?
TrueAudio—N/aVia dedicated DSPVia shaders
FreeSync—N/a1 2
HDCP—N/a?1.42.22.3
PlayReady—N/a3.03.0
Supported displays1–222–6?4
Max. resolution?2–6 × 2560×16002–6 × 4096×2160 @ 30 Hz2–6 × 5120×2880 @ 60 Hz3 × 7680×4320 @ 60 Hz7680×4320 @ 60 Hz7680x4320 @165 Hz7680x4320
/drm/radeon—N/a
/drm/amdgpu—N/aOptional

Operating system support

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, but added it in December 2018), 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

Support for the VCE ASIC is contained in the Linux kernel device driver amdgpu.
  • Initial VCE support was added on 4 February 2014 by Christian König of AMD to the free radeon driver.
  • Gallium3D state tracker for OpenMAX was added 24 October 2013 to Mesa 3D.
  • The free and open-source Radeon driver was adapted to use OpenMAX with the GStreamer OpenMAX (gst-omx) support for exposing the VCE video encode engine.
  • AMD employee Leo Liu implemented h264 level support into the Mesa 3D state tracker.

Windows

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

XSplit Broadcaster supports VCE from version 1.3.

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.

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.

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

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).

See also

Video hardware technologies

AMD

Others