Radeon vega vad är det
Radeon RX Vega series
Series of GPUs bygd AMD
This article fryst vatten about the GPU architecture bygd AMD. For the GPU architecture bygd Vivante, see Vivante Corporation.
The Radeon RX Vega series fryst vatten a series of graphics processors developed bygd AMD. These GPUs use the Graphics Core Next (GCN) 5th generation architecture, codenamed Vega, and are manufactured on 14 nmFinFET technology, developed bygd Samsung Electronics and licensed to GlobalFoundries.[5] The series consists of desktop graphics kort and APUs aimed at desktops, mobile devices, and embedded applications.
The lineup was released on 14 August 2017. It included the RX Vega 56 and the RX Vega 64, priced at $399 and $499 respectively.[6] These were followed bygd two mobile APUs, the Ryzen 2500U and Ryzen 2700U, in October 2017.[7] February 2018 saw the release of two desktop APUs, the Ryzen 3 2200G and the Ryzen 5 2400G, and the Ryzen Embedded V1000 line of APUs.[8][9] In September 2018 AMD announced several Vega APUs in their Athlon line of products.[10] Later in January 2019, the Radeon VII was announced based on the 7nm FinFET node manufactured bygd TSMC.[11][12]
History
[edit]The Vega microarchitecture was AMD's high-end graphics kort line,[13] and fryst vatten the successor to the R9 300 series enthusiast Fury products. Partial specifications of the architecture and Vega 10 GPU were announced with the Radeon Instinct MI25 in månad 2016.[14] AMD later released the details of the Vega architecture.
Announcement
[edit]Vega was originally announced at AMD's CES 2017 föredrag on 5 January 2017,[15] alongside the Zen line of CPUs.[16]
New features
[edit]Main article: Graphics Core Next § fifth
Vega targets increased instructions per clock, higher clock speeds, and support for HBM2.[17][18][19]
AMD's Vega has new memory hierarchy with high-bandwidth cache and its controller.[citation needed]
Support for HBM2 featuring double the bandwidth-per-pin over previous generation HBM. HBM2 allows for higher capacities with less than half the footprint of GDDR5 memory. Vega architecture fryst vatten optimized for streaming very large datasets and can work with a variety of memory types with up to 512TB of virtual address space.[citation needed]
Primitive shader for improved geometry processing. Replaces vertex and geometry shaders in geometry processing pipelines with a more programmable single scen. The primitive shader scen fryst vatten more efficient, introduces smart eller klok load balancing technologies and higher throughput.[20]
NCU: The Vega GPU introduces the Next-Gen Compute enhet. Versatile architecture featuring flexible compute units that can natively process 8-bit, 16-bit, 32-bit or 64-bit operations in each clock cycle. And run at higher frequencies. Vega brings support for Rapid packad Math, processing two half-precision (16-bit) in the same time as a single 32-bit floating-point operation. Up to 128 32-bit, 256 16-bit or 512 8-bit ops per clock are possible with the Vega architecture.[20]
Draw Stream Binning Rasterizer designed for higher performance and power efficiency. It allows for "fetch once, shade once" of pixels through the use of a smart on-chip insekter som pollinerar cache and early culling of pixels invisible in a sista scene.[citation needed]
Vega bumps Direct3D feature level support from 12_0 to 12_1.[citation needed]
Vega's rasteriser brings hardware-acceleration support for Rasterizer Ordered Views and Conservative Rasterisation Tier 3.[21]
Products
[edit]RX Vega branded discrete graphics
[edit]| Model (Code name) | Release Date & Price | Architecture & fab | Transistors & die storlek | Core | Fillrate[a][b][c] | Processing power[a][d] (GFLOPS) | Memory | TBP | Bus interface | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Config[e] | Clock[a] (MHz) | Texture (GT/s) | Pixel (GP/s) | Half | Single | Double | Size (GB) | Bandwidth (GB/s) | Bus type & width | Clock (MT/s) | ||||||
| Radeon RX Vega 56 (Vega 10)[22][23][24] | Aug 28, 2017 $399 USD | GCN 5 GloFo 14LPP[f][25][26] | 12.5×109 486 mm2 | 3584:224:64 56 CU | 1156 1471 | 258.9 329.5 | 73.98 94.14 | 16,572 21,088 | 8,286 10,544 | 517.9 659.0 | 8 | 409.6 | HBM2 2048-bit | 1600 | 210 W | PCIe 3.0 ×16 |
| Radeon RX Vega 64 (Vega 10)[27][23][24] | Aug 14, 2017 $499 USD | 4096:256:64 64 CU | 1247 1546 | 319.2 395.8 | 79.81 98.94 | 20,431 25,330 | 10,215 12,665 | 638.5 791.6 | 483.8 | 1890 | 295 W | |||||
| Radeon RX Vega 64 Liquid (Vega 10)[27][23][24] | Aug 14, 2017 $699 USD | 1406 1677 | 359.9 429.3 | 89.98 107.3 | 23,036 27,476 | 11,518 13,738 | 719.9 858.6 | 345 W | ||||||||
Radeon VII branded discrete graphics
[edit]- ^ abcBoost values (if available) are stated below the base value in italic.
- ^Texture fillrate fryst vatten calculated as the number of Texture Mapping Units multiplied bygd the base (or boost) core clock speed.
- ^Pixel fillrate fryst vatten calculated as the number of Render Output Units multiplied bygd the base (or boost) core clock speed.
- ^Precision performance fryst vatten calculated from the base (or boost) core clock speed based on a FMA operation.
- ^Unified shaders : Texture mapping units : Render output units and Compute units (CU)
Workstation GPUs
[edit]- ^ abcBoost values (if available) are stated below the base value in italic.
- ^Texture fillrate fryst vatten calculated as the number of Texture Mapping Units multiplied bygd the base (or boost) core clock speed.
- ^Pixel fillrate fryst vatten calculated as the number of Render Output Units multiplied bygd the base (or boost) core clock speed.
- ^Precision performance fryst vatten calculated from the base (or boost) core clock speed based on a FMA operation.
- ^Unified shaders : Texture mapping units : Render output units and Compute units (CU)
- ^ abcBoost values (if available) are stated below the base value in italic.
- ^Texture fillrate fryst vatten calculated as the number of Texture Mapping Units multiplied bygd the base (or boost) core clock speed.
- ^Pixel fillrate fryst vatten calculated as the number of Render Output Units multiplied bygd the base (or boost) core clock speed.
- ^Precision performance fryst vatten calculated from the base (or boost) core clock speed based on a FMA operation.
- ^Unified shaders : Texture mapping units : Render output units and Compute units (CU)
Mobile en arbetsstationofta relaterad till datorer eller kontor GPUs
[edit]| Model (Code name) | Release date | Architecture & fab | Transistors & die storlek | Core | Fillrate[a][b][c] | Processing power[a][d] (GFLOPS) | Memory | TDP | Bus interface | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Config[e] | Clock[a] (MHz) | Texture (GT/s) | Pixel (GP/s) | Half | Single | Double | Size (GB) | Bandwidth (GB/s) | Bus type & width | Clock (MT/s) | ||||||
| Radeon Pro Vega 16 (Vega 12)[43][44][45] | Nov 14, 2018 | GCN 5 GloFo 14 nm | ? | 1024:64:32 16 CU | 815 1190 | 52.16 76.16 | 26.08 38.08 | 3,338 4,874 | 1,669 2,437 | 104.3 152.3 | 4 | 307.2 | HBM2 1024-bit | 2400 | 50 W | PCIe 3.0 ×16 |
| Radeon Pro Vega 20 (Vega 12)[43][44][46] | 1280:80:32 20 CU | 815 1283 | 65.20 102.6 | 26.08 41.06 | 4,173 6,569 | 2,086 3,285 | 130.4 205.3 | 189.4 | 1480 | 50 W | ||||||
| Radeon Pro Vega 48 (Vega 10)[47][48] | Mar 19, 2019 | 12.5×109 495 mm2 | 3072:192:64 48 CU | 1200 | 230.4 | 76.80 | 14,746 | 7,373 | 460.8 | 8 | 402.4 | HBM2 2048-bit | 1572 | ? | ||
| Radeon Pro Vega 56 (Vega 10)[49][50][51] | Aug 17, 2017 | 3584:224:64 56 CU | 1138 1250 | 254.9 280.0 | 72.83 80.00 | 16,314 17,920 | 8,157 8,960 | 509.8 560.0 | 120 W | |||||||
| Radeon Pro Vega 64 (Vega 10)[49][50][52] | Jun 17, 2017 | 4096:256:64 64 CU | 1250 1350 | 320.0 345.6 | 80.00 86.40 | 20,480 22,118 | 10,240 11,059 | 640.0 691.2 | 16 | ? | ||||||
| Radeon Pro Vega 64X (Vega 10)[49][53] | Mar 19, 2019 | 4096:256:64 64 CU | 1250 1468 | 320.0 375.8 | 80.00 93.95 | 20,480 24,051 | 10,240 12,026 | 640.0 751.6 | 512.0 | 2000 | ||||||
- ^ abcBoost values (if available) are stated below the base value in italic.
- ^Texture fillrate fryst vatten calculated as the number of Texture Mapping Units multiplied bygd the base (or boost) core clock speed.
- ^Pixel fillrate fryst vatten calculated as the number of Render Output Units multiplied bygd the base (or boost) core clock speed.
- ^Precision performance fryst vatten calculated from the base (or boost) core clock speed based on a FMA operation.
- ^Unified shaders : Texture mapping units : Render output units and Compute units (CU)
Desktop APUs
[edit]Raven Ridge (2018)
[edit]Common features of Zen based Raven Ridge desktop APUs:
| Model | CPU | GPU | TDP | Release date | Release price | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Cores (threads) | Clock rate (GHz) | L3 cache (total) | Model | Config[i] | Clock (MHz) | Processing power (GFLOPS)[ii] | |||||
| Athlon 200GE | 2 (4) | 3.2 | — | 4 MB | Vega 3 | 192:12:4 3 CU | 1000 | 384 | 35 W | Sep 6, 2018 | US $55[54] |
| Athlon Pro 200GE | OEM | ||||||||||
| Athlon 220GE | 3.4 | Dec 21, 2018 | US $65[55] | ||||||||
| Athlon 240GE | 3.5 | US $75[55] | |||||||||
| Athlon 300GE | 3.4 | 1100 | 424.4 | Jul 7, 2019 | OEM | ||||||
| Athlon Pro 300GE | Sep 30, 2019 | ||||||||||
| Athlon 320GE | 3.5 | Jul 7, 2019 | |||||||||
| Athlon 3000G | Nov 19, 2019 | US $49[56] | |||||||||
| Athlon Silver 3050GE | 3.4 | Jul 21, 2020 | OEM | ||||||||
| Ryzen 3 Pro 2100GE[57] | 3.2 | 1000 | 384 | 2019 | |||||||
| Ryzen 3 2200GE | 4 (4) | 3.6 | Vega 8 | 512:32:16 8 CU | 1100 | 1126 | Apr 19, 2018 | ||||
| Ryzen 3 Pro 2200GE | May 10, 2018 | ||||||||||
| Ryzen 3 2200G | 3.5 | 3.7 | 65 W | Feb 12, 2018 | US $99[58] | ||||||
| Ryzen 3 Pro 2200G | May 10, 2018 | OEM | |||||||||
| Ryzen 5 2400GE | 4 (8) | 3.2 | 3.8 | RX Vega 11 | 704:44:16 11 CU | 1250 | 1760 | 35 W | Apr 19, 2018 | ||
| Ryzen 5 Pro 2400GE | Vega 11 | May 10, 2018 | |||||||||
| Ryzen 5 2400G | 3.6 | 3.9 | RX Vega 11 | 65 W | Feb 12, 2018 | US $169[58] | |||||
| Ryzen 5 Pro 2400G | Vega 11 | May 10, 2018 | OEM | ||||||||
Picasso (2019)
[edit]Common features of Zen+ based desktop APUs:
- Socket: AM4.
- All the CPUs support DDR4-2933 in dual-channel mode, while Athlon Pro 300GE and Athlon Silver Pro 3125GE support only DDR4-2666.
- L1 cache: 96 KB (32 KB information + 64 KB instruction) per core.
- L2 cache: 512 KB per core.
- All the CPUs support 16 PCIe 3.0 lanes.
- Includes integrated GCN 5th generation GPU.
- Fabrication process: GlobalFoundries12LP.
| Model | CPU | GPU | TDP | Release date | Release price | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Cores (threads) | Clock rate (GHz) | L3 cache (total) | Model[i] | Config[ii] | Clock (MHz) | Processing power (GFLOPS)[iii] | |||||
| Athlon Pro 300GE | 2 (4) | 3.4 | — | 4 MB | Vega 3 | 192:12:4 3 CU | 1100 | 424.4 | 35 W | Sep 30, 2019 | OEM |
| Athlon Silver Pro 3125GE | Radeon Graphics | Jul 21, 2020 | |||||||||
| Athlon Gold 3150GE | 4 (4) | 3.3 | 3.8 | ||||||||
| Athlon Gold Pro 3150GE | |||||||||||
| Athlon Gold 3150G | 3.5 | 3.9 | 65 W | ||||||||
| Athlon Gold Pro 3150G | |||||||||||
| Ryzen 3 3200GE | 3.3 | 3.8 | Vega 8 | 512:32:16 8 CU | 1200 | 1228.8 | 35 W | Jul 7, 2019 | |||
| Ryzen 3 Pro 3200GE | Sep 30, 2019 | ||||||||||
| Ryzen 3 3200G | 3.6 | 4.0 | 1250 | 1280 | 65 W | Jul 7, 2019 | US $99[62] | ||||
| Ryzen 3 Pro 3200G | Sep 30, 2019 | OEM | |||||||||
| Ryzen 5 Pro 3350GE | 3.3 | 3.9 | Radeon Graphics | 640:40:16 10 CU | 1200 | 1536 | 35 W | Jul 21, 2020 | |||
| Ryzen 5 Pro 3350G | 4 (8) | 3.6 | 4.0 | 1300 | 1830.4 | 65 W | |||||
| Ryzen 5 3400GE | 3.3 | Vega 11 | 704:44:16 11 CU | 35 W | Jul 7, 2019 | ||||||
| Ryzen 5 Pro 3400GE | Sep 30, 2019 | ||||||||||
| Ryzen 5 3400G | 3.7 | 4.2 | RX Vega 11 | 1400 | 1971.2 | 65 W | Jul 7, 2019 | US $149[62] | |||
| Ryzen 5 Pro 3400G | Vega 11 | Sep 30, 2019 | OEM | ||||||||
Renoir (2020)
[edit]Common features of Ryzen 4000 desktop APUs:
- Socket: AM4.
- All the CPUs support DDR4-3200 in dual-channel mode.
- L1 cache: 64 KB (32 KB information + 32 KB instruction) per core.
- L2 cache: 512 KB per core.
- All the CPUs support 24 PCIe 3.0 lanes. 4 of the lanes are reserved as link to the chipset.
- Includes integrated GCN 5th generation GPU.
- Fabrication process: TSMC7FF.
Cezanne (2021)
[edit]Common features of Ryzen 5000 desktop APUs:
- Socket: AM4.
- All the CPUs support DDR4-3200 in dual-channel mode.
- L1 cache: 64 KB (32 KB information + 32 KB instruction) per core.
- L2 cache: 512 KB per core.
- All the CPUs support 24 PCIe 3.0 lanes. 4 of the lanes are reserved as link to the chipset.
- Includes integrated GCN 5th generation GPU.
- Fabrication process: TSMC7FF.
| Branding and model | CPU | GPU[a] | Thermal solution | TDP | Release date | MSRP | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cores (threads) | Clock rate (GHz) | L3 cache (total) | Core config[i] | Clock (MHz) | Config[ii] | Processing power[iii] (GFLOPS) | |||||||
| Ryzen 7 | 5700G[b] | 8 (16) | 3.8 | 4.6 | 16 MB | 1 × 8 | 2000 | 512:32:8 8 CU | 2048 | Wraith Stealth | 65 W | Apr 13, 2021 (OEM), Aug 5, 2021 (retail) | US $359 |
| 5700GE[b] | 3.2 | 35 W | Apr 13, 2021 | OEM | |||||||||
| Ryzen 5 | 5600GT | 6 (12) | 3.6 | 1 × 6 | 1900 | 448:28:8 7 CU | 1702.4 | 65 W | Jan 31, 2024[71] | US $140 | |||
| 5600G[b] | 3.9 | 4.4 | Apr 13, 2021 (OEM), Aug 5, 2021 (retail) | US $259 | |||||||||
| 5600GE[b] | 3.4 | 35 W | Apr 13, 2021 | OEM | |||||||||
| 5500GT | 3.6 | 65 W | Jan 31, 2024[71] | US $125 | |||||||||
| Ryzen 3 | 5300G[b] | 4 (8) | 4.0 | 4.2 | 8 MB | 1 × 4 | 1700 | 384:24:8 6 CU | 1305.6 | OEM | Apr 13, 2021 | OEM | |
| 5300GE[b] | 3.6 | 35 W | |||||||||||
Mobile APUs
[edit]Raven Ridge (2017)
[edit]| Model | Release date | Fab | CPU | GPU | Socket | PCIe lanes | Memory support | TDP | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cores (threads) | Clock rate (GHz) | Cache | Model | Config[i] | Clock (MHz) | Processing power (GFLOPS)[ii] | ||||||||||
| L1 | L2 | L3 | ||||||||||||||
| Athlon Pro 200U | 2019 | GloFo 14LP | 2 (4) | 2.3 | 3.2 | 64 KB inst. 32 KB data per core | 512 KB per core | 4 MB | Radeon Vega 3 | 192:12:4 3 CU | 1000 | 384 | FP5 | 12 (8+4) | DDR4-2400 dual-channel | 12–25 W |
| Athlon 300U | Jan 6, 2019 | 2.4 | 3.3 | |||||||||||||
| Ryzen 3 2200U | Jan 8, 2018 | 2.5 | 3.4 | 1100 | 422.4 | |||||||||||
| Ryzen 3 3200U | Jan 6, 2019 | 2.6 | 3.5 | 1200 | 460.8 | |||||||||||
| Ryzen 3 2300U | Jan 8, 2018 | 4 (4) | 2.0 | 3.4 | Radeon Vega 6 | 384:24:8 6 CU | 1100 | 844.8 | ||||||||
| Ryzen 3 Pro 2300U | May 15, 2018 | |||||||||||||||
| Ryzen 5 2500U | Oct 26, 2017 | 4 (8) | 3.6 | Radeon Vega 8 | 512:32:16 8 CU | 1126.4 | ||||||||||
| Ryzen 5 Pro 2500U | May 15, 2018 | |||||||||||||||
| Ryzen 5 2600H | Sep 10, 2018 | 3.2 | DDR4-3200 dual-channel | 35–54 W | ||||||||||||
| Ryzen 7 2700U | Oct 26, 2017 | 2.2 | 3.8 | Radeon RX Vega 10 | 640:40:16 10 CU | 1300 | 1664 | DDR4-2400 dual-channel | 12–25 W | |||||||
| Ryzen 7 Pro 2700U | May 15, 2018 | Radeon Vega 10 | ||||||||||||||
| Ryzen 7 2800H | Sep 10, 2018 | 3.3 | Radeon RX Vega 11 | 704:44:16 11 CU | 1830.4 | DDR4-3200 dual-channel | 35–54 W | |||||||||
Picasso (2019)
[edit]Common features of Ryzen 3000 notebook APUs:
Dalí (2020)
[edit]Renoir (2020)
[edit]Common features of Ryzen 4000 notebook APUs:
- Socket: FP6.
- All the CPUs support DDR4-3200 or LPDDR4-4266 in dual-channel mode.
- L1 cache: 64 KB (32 KB information + 32 KB instruction) per core.
- L2 cache: 512 KB per core.
- All the CPUs support 16 PCIe 3.0 lanes.
- Includes integrated GCN 5th generation GPU.
- Fabrication process: TSMC7FF.
Lucienne (2021)
[edit]Common features of Ryzen 5000 notebook APUs:
- Socket: FP6.
- All the CPUs support DDR4-3200 or LPDDR4-4266 in dual-channel mode.
- L1 cache: 64 KB (32 KB uppgifter + 32 KB instruction) per core.
- L2 cache: 512 KB per core.
- All the CPUs support 16 PCIe 3.0 lanes.
- Includes integrated GCN 5th generation GPU.
- Fabrication process: TSMC7FF.