Zen 2

2019 AMD 7-nanometer processor microarchitecture From Wikipedia, the free encyclopedia

Zen 2 is a computer processor microarchitecture by AMD. It is the successor of AMD's Zen and Zen+ microarchitectures, and is fabricated on the 7 nm MOSFET node from TSMC. The microarchitecture powers the third generation of Ryzen processors, known as Ryzen 3000 for the mainstream desktop chips (codename "Matisse"), Ryzen 4000U/H (codename "Renoir") and Ryzen 5000U (codename "Lucienne") for mobile applications, as Threadripper 3000 for high-end desktop systems,[6][7] and as Ryzen 4000G for accelerated processing units (APUs). The Ryzen 3000 series CPUs were released on 7 July 2019,[8][9] while the Zen 2-based Epyc server CPUs (codename "Rome") were released on 7 August 2019.[10] An additional chip, the Ryzen 9 3950X, was released in November 2019.[8]

Launched7 July 2019; 6 years ago (7 July 2019)[1]
Designed byAMD
Common manufacturers
CPUID codeFamily 17h
Quick facts General information, Launched ...
AMD Zen 2
General information
Launched7 July 2019; 6 years ago (7 July 2019)[1]
Designed byAMD
Common manufacturers
CPUID codeFamily 17h
Physical specifications
Transistors
  • 5.89 billion (1× CCD) or
    9.69 billion (2× CCD)
    (3.8 billion per 7 nm 8-core "CCD" & 2.09 billion for the 12 nm "I/O die")[2]
Cores
    • 4–16 (desktop)
    • 24–64 (HEDT)
    • 12–64 (workstation)
    • Up to 64 (server)
    • 2–8 (mobile)
Sockets
Cache
L1 cache64 KB per core:
  • 32 KB instructions
  • 32 KB data
L2 cache512 KB per core
L3 cache16 MB per CCX (APU: 8 MB)
Architecture and classification
Technology nodeTSMC N7[3][4]
TSMC N6[5]
MicroarchitectureZen
Instruction setAMD64 (x86-64)
Products, models, variants
Product code names
  • Matisse (desktop)
  • Rome (server)[4]
  • Castle Peak (HEDT/workstation)
  • Renoir (Desktop APU, mobile and embedded)
  • Mendocino (mobile and embedded refresh)
Brand names
History
PredecessorZen+
SuccessorZen 3
Support status
Supported
Close

At CES 2019, AMD showed a Ryzen third-generation engineering sample that contained one chiplet with eight cores and 16 threads.[6] AMD CEO Lisa Su also said to expect more than eight cores in the final lineup.[11] At Computex 2019, AMD revealed that the Zen 2 "Matisse" processors would feature up to 12 cores, and a few weeks later a 16 core processor was also revealed at E3 2019, being the aforementioned Ryzen 9 3950X.[12][13]

Zen 2 includes hardware mitigations to the Spectre security vulnerability.[14] Zen 2-based EPYC server CPUs use a design in which multiple CPU dies (up to eight in total) manufactured on a 7 nm process ("chiplets") are combined with a 14nm I/O die (as opposed to the 12nm IOD on Matisse variants) on each multi-chip module (MCM) package. Using this, up to 64 physical cores and 128 total compute threads (with simultaneous multithreading) are supported per socket. This architecture is nearly identical to the layout of the "pro-consumer" flagship processor Threadripper 3990X.[15] Zen 2 delivers about 15% more instructions per clock than Zen and Zen+,[16][17] the 14- and 12-nm microarchitectures utilized on first and second generation Ryzen, respectively.

The Steam Deck,[18][19] PlayStation 5, Xbox Series X and Series S all use chips based on the Zen 2 microarchitecture, with proprietary tweaks and different configurations in each system's implementation than AMD sells in its own commercially available APUs.[20][21]

Design

Two delidded Zen 2 processors designed with the multi-chip module approach. The Ryzen 5 3600 CPU on the left/top (used for mainstream Ryzen CPUs) uses a smaller, less capable I/O die and one CCD (the space for an additional CCD is used on the Ryzen 9), while the Epyc 7702 on the right/bottom (used for high-end desktop, HEDT, Ryzen Threadripper and server Epyc CPUs) uses a larger, more capable I/O die and up to eight CCDs.

Zen 2 is a significant departure from the physical design paradigm of AMD's previous Zen architectures, Zen and Zen+. Zen 2 moves to a multi-chip module design where the I/O components of the CPU are laid out on its own die which is separate from the dies containing processor cores, which are also called chiplets in this context. This separation has benefits in scalability and manufacturability. As physical interfaces don't scale very well with shrinks in process technology, their separation into a different die allows these components to be manufactured using a larger, more mature process node than the CPU dies. The CPU dies (referred to by AMD as core complex dies or CCDs), now more compact due to the move of I/O components onto another die, can be manufactured using a smaller process with fewer manufacturing defects than a larger die would exhibit (since the chances of a die having a defect increases with device (die) size) while also allowing for more dies per wafer. In addition, the central I/O die can service multiple chiplets, making it easier to construct processors with a large number of cores.[15][22][23]

Simplified illustration of the Zen 2 microarchitecture
On the left (top on mobile): Die shot of a Zen 2 Core Complex Die. On the middle: Die shot of a Zen 2 EPYC/Threadripper I/O die, On the right (bottom): I/O die of a Zen 2 mainstream Ryzen I/O die.

With Zen 2, each CPU chiplet houses 8 CPU cores, arranged in 2 core complexes (CCXs), each of 4 CPU cores. These chiplets are manufactured using TSMC's 7 nanometer MOSFET node and are about 74 to 80 mm2 in size.[22] The chiplet has about 3.8 billion transistors, while the 12 nm I/O die (IOD) is ~125 mm2 and has 2.09 billion transistors.[24] The amount of L3 cache has been doubled to 32 MB, with each CCX in the chiplet now having access to 16 MB of L3 compared to the 8 MB of Zen and Zen+.[25] AVX2 performance is greatly improved by an increase in execution unit width from 128-bit to 256-bit.[26] There are multiple variants of the I/O die: one manufactured on GlobalFoundries 14 nanometer process, and another manufactured using the same company's 12 nanometer process. The 14 nanometer dies have more features and are used for the EPYC Rome processors, whereas the 12 nm versions are used for consumer processors.[22] Both processes have similar feature sizes, so their transistor density is also similar.[27]

AMD's Zen 2 architecture can deliver higher performance at a lower power consumption than Intel's Cascade Lake architecture, with an example being the AMD Ryzen Threadripper 3970X running with a TDP of 140 W in ECO mode delivering higher performance than the Intel Core i9-10980XE running with a TDP of 165 W.[28]

New features

  • Some new instruction set extensions: WBNOINVD, CLWB, RDPID, RDPRU, MCOMMIT. Each instruction uses its own CPUID bit.[29][30]
  • Hardware mitigations against the Spectre V4 speculative store bypass vulnerability.[31]
  • Zero-latency memory mirroring optimization (undocumented).[32]
  • Doubled width of the execution units and load store units (from 128-bit to 256-bit) in the floating point coprocessor and significant further throughput enhancements in the multiplication execution unit. This allows the FPU to perform single-cycle AVX2 calculations.[33]
  • Introduced CPPC power management.[34]

Feature tables

CPUs

APUs

APU features table

Products

On 26 May 2019, AMD announced six Zen 2-based desktop Ryzen processors (codenamed "Matisse"). These included 6-core and 8-core variants in the Ryzen 5 and Ryzen 7 product lines, as well as a new Ryzen 9 line that includes the company's first 12-core and 16-core mainstream desktop processors.[35]

The Matisse I/O die is also used as the X570 chipset.

AMD's second generation of Epyc processors, codenamed "Rome", feature up to 64 cores, and were launched on 7 August 2019.[10]

Desktop CPUs

Matisse (3000 series)

Common features of Ryzen 3000 desktop CPUs:

  • Socket: AM4.
  • All the CPUs support DDR4-3200 in dual-channel mode.
  • L1 cache: 64 KB (32 KB data + 32 KB instruction) per core.
  • L2 cache: 512 KB per core.
  • All the CPUs support 24 PCIe 4.0 lanes. 4 of which are reserved as link to the chipset.
  • No integrated graphics.
  • Fabrication process: TSMC 7FF.
More information Branding and Model, Cores (threads) ...
Branding and Model Cores
(threads)		 Clock rate (GHz) L3 cache
(total)		 TDP Chiplets[i] Core
config[ii]		 Thermal Solution Release
date		 MSRP
Base Boost
Ryzen 9 3950X 16 (32) 3.5 4.7 64 MB 105 W[iii] 2 × CCD
1 × I/OD		 4 × 4 N/a Nov 25, 2019 US $749
3900XT 12 (24) 3.8 4 × 3 Jul 7, 2020 US $499
3900X 4.6 Wraith Prism Jul 7, 2019
3900[a] 3.1 4.3 65 W N/a Oct 8, 2019 OEM
Ryzen 7 3800XT 8 (16) 3.9 4.7 32 MB 105 W 1 × CCD
1 × I/OD		 2 × 4 N/a Jul 7, 2020 US $399
3800X 4.5 Wraith Prism Jul 7, 2019
3700X[a] 3.6 4.4 65 W[iv] US $329
Ryzen 5 3600XT 6 (12) 3.8 4.5 95 W 2 × 3 N/a Jul 7, 2020 US $249
3600X 4.4 Wraith Spire (non-LED) Jul 7, 2019
3600[a] 3.6 4.2 65 W Wraith Stealth US $199
3500X[38] 6 (6) 4.1 Oct 8, 2019 CNY 1099
(Mainland China Only)
3500 16 MB N/a Nov 15, 2019 OEM (Worldwide)

JPY 16000
(Japan Only)[39]

Ryzen 3 3300X 4 (8) 3.8 4.3 1 × 4 Wraith Stealth Apr 21, 2020 US $119
3100 3.6 3.9 2 × 2 US $99
Close
  1. [i]
    A Core Complex Die contains 1-2 Core Complexes (CCXs).
  2. [ii]
    Core Complexes (CCXs) × cores per CCX
  3. [iii]
    Ryzen 9 3900X and Ryzen 9 3950X may consume over 145 W under load.[36]
  4. [iv]
    Ryzen 7 3700X may consume 90 W under load.[37]
  1. [a]
    Model also available as PRO 3600, PRO 3700, PRO 3900, released on September 30, 2019 for OEMs.

Castle Peak (3000 series)

Common features of Ryzen 3000 HEDT/workstation CPUs:

  • Socket: sTRX4 (Threadripper), sWRX8 (Threadripper PRO).
  • Threadripper CPUs support DDR4-3200 in quad-channel mode while Threadripper PRO CPUs support DDR4-3200 in octa-channel mode.
  • L1 cache: 64 KB (32 KB data + 32 KB instruction) per core.
  • L2 cache: 512 KB per core.
  • Threadripper CPUs support 64 PCIe 4.0 lanes while Threadripper PRO CPUs support 128 PCIe 4.0 lanes. 8 of the lanes are reserved as link to the chipset.
  • No integrated graphics.
  • Fabrication process: TSMC 7FF.
More information Branding and Model, Cores (threads) ...
Branding and Model Cores
(threads)		 Clock rate (GHz) L3 cache
(total)		 TDP Chiplets Core
config[i]		 Release
date		 MSRP
Base Boost
Ryzen
Threadripper
PRO		 3995WX 64 (128) 2.7 4.2 256 MB 280 W
[ii]		 8 × CCD
1 × I/OD		 16 × 4 Jul 14, 2020
3975WX 32 (64) 3.5 128 MB 4 × CCD
1 × I/OD		 8 × 4
3955WX 16 (32) 3.9 4.3 64 MB 2 × CCD
1 × I/OD		 4 × 4
3945WX 12 (24) 4.0 4 × 3
Ryzen
Threadripper		 3990X 64 (128) 2.9 256 MB 8 × CCD
1 × I/OD		 16 × 4 Feb 7, 2020 US $3990
3970X 32 (64) 3.7 4.5 128 MB 4 × CCD
1 × I/OD		 8 × 4 Nov 25, 2019 US $1999
3960X 24 (48) 3.8 8 × 3 US $1399
Close
  1. [i]
    Core Complexes (CCXs) × cores per CCX
  2. [ii]
    Ryzen Threadripper 3990X may consume over 490 W under load.[40]

Renoir (4000 series)

Based on the Ryzen 4000G series APUs but with the integrated graphics disabled. Common features of Ryzen 4000 desktop CPUs:

  • Socket: AM4.
    • The AMD 4700S uses the BGA 2197 socket and the 4800S uses BGA 2963.
  • All the CPUs support DDR4-3200 in dual-channel mode.
  • L1 cache: 64 KB (32 KB data + 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.
  • No integrated graphics.
  • Fabrication process: TSMC 7FF.
  • Bundled with AMD Wraith Stealth

The AMD 4700S and 4800S desktop processors are part of a "desktop kit" that comes bundled with a motherboard and GDDR6 RAM. The CPU is soldered, and provides 4 PCIe 2.0 lanes. These are reportedly cut-down variants of the APUs found on the PlayStation 5 and Xbox Series X and S repurposed from defective chip stock.[41][42][43]

More information Branding and model, Cores (threads) ...
Branding and model Cores
(threads)		 Clock rate (GHz) L3 cache
(total)		 TDP Core
config[i]		 Release
date		 MSRP
Base Boost
AMD 4800S[41][42] 8 (16) 4.0 8 MB 2 × 4 2022 bundled with desktop kit
4700S[43] 3.6 75 W 2021
Ryzen 5 4500 6 (12) 4.1 65 W 2 × 3 Apr 4, 2022 US $129
Ryzen 3 4100 4 (8) 3.8 4.0 4 MB 1 × 4 US $99
Close
    1. [i]
      Core Complexes (CCX) × cores per CCX

    Desktop APUs

    Initially only provided to OEM; later, AMD released retail Zen 2 desktop APUs in April 2022.[44] 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 data + 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: TSMC 7FF.
    More information Branding and model, CPU ...
    Branding and model CPU GPU TDP Release
    date    		 Release
    price
    Cores
    (threads)    		 Clock rate (GHz) L3 cache
    (total)    		 Core
    Config[i]    		 Model Clock
    (GHz)    		 Config[ii] Processing
    power[iii]
    (GFLOPS)
    Base Boost
    Ryzen 7 4700G[a] 8 (16) 3.6 4.4 8 MB 2 × 4 Radeon
    Graphics[b]    		 2.1 512:32:16
    8 CU    		 2150.4 65 W Jul 21, 2020 OEM
    4700GE[a] 3.1 4.3 2.0 2048 35 W
    Ryzen 5 4600G[a][45] 6 (12) 3.7 4.2 2 × 3 1.9 448:28:14
    7 CU    		 1702.4 65 W Jul 21, 2020
    (OEM)
    Apr 4, 2022
    (retail)    		 US $154
    4600GE[a] 3.3 35 W Jul 21, 2020 OEM
    Ryzen 3 4300G[a] 4 (8) 3.8 4.0 4 MB 1 × 4 1.7 384:24:12
    6 CU    		 1305.6 65 W
    4300GE[a] 3.5 35 W
    Close
    1. [i]
      Core complexes (CCXs) × cores per CCX
    2. [ii]
      Unified shaders : Texture mapping units : Render output units and Compute units (CU)
    3. [iii]
      Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
    1. [a]
      Model also available as PRO version as 4350GE,[46] 4350G,[47] 4650GE,[48] 4650G,[49] 4750GE,[50] 4750G,[51] released on July 21, 2020 for OEM only. Refresh models 4355GE, 4355G, 4655GE, 4655G released November 11, 2022.[52]
    2. [b]
      All of the iGPUs are branded as AMD Radeon Graphics.

    Mobile APUs

    Renoir (4000 series)

    Common features of Ryzen 4000 notebook APUs:

    More information Branding and Model, CPU ...
    Branding and Model CPU GPU TDP Release
    date
    Cores
    (threads)    		 Clock rate (GHz) L3 cache
    (total)    		 Core
    config[i]    		 Model Clock
    (GHz)    		 Config[ii] Processing
    power
    (GFLOPS)[iii]
    Base Boost
    Ryzen 9 4900H 8 (16) 3.3 4.4 8 MB 2 × 4 Radeon
    Graphics
    [a]    		 1.75 512:32:8
    8 CU    		 1792 35–54 W Mar 16, 2020
    4900HS 3.0 4.3 35 W
    Ryzen 7 4800H[53] 2.9 4.2 1.6 448:28:8
    7 CU    		 1433.6 35–54 W
    4800HS 35 W
    4980U[b] 2.0 4.4 1.95 512:32:8
    8 CU    		 1996.8 10–25 W Apr 13, 2021
    4800U 1.8 4.2 1.75 1792 Mar 16, 2020
    4700U[c] 8 (8) 2.0 4.1 1.6 448:28:8
    7 CU    		 1433.6
    Ryzen 5 4600H[54] 6 (12) 3.0 4.0 2 × 3 1.5 384:24:8
    6 CU    		 1152 35–54 W
    4600HS[55] 35 W
    4680U[b] 2.1 448:28:8
    7 CU    		 1344 10–25 W Apr 13, 2021
    4600U[c] 384:24:8
    6 CU    		 1152 Mar 16, 2020
    4500U 6 (6) 2.3
    Ryzen 3 4300U[c] 4 (4) 2.7 3.7 4 MB 1 × 4 1.4 320:20:8
    5 CU    		 896
    Close
    1. [i]
      Core Complexes (CCX) × cores per CCX
    2. [ii]
      Unified shaders : texture mapping units : render output units and compute units (CU)
    3. [iii]
      Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
    1. [a]
      All of the iGPUs are branded as AMD Radeon Graphics.
    2. [b]
      Only found on the Microsoft Surface Laptop 4.
    3. [c]
      Model also available as PRO version as 4450U,[56] 4650U,[57] 4750U,[58] released May 7, 2020.

    Lucienne (5000 series)

    Common features of Ryzen 5000 notebook APUs:

    More information Branding and Model, CPU ...
    Branding and Model CPU GPU TDP Release
    date
    Cores
    (threads)    		 Clock rate (GHz) L3 cache
    (total)    		 Core
    config[i]    		 Model Clock
    (GHz)    		 Config[ii] Processing
    power
    (GFLOPS)[iii]
    Base Boost
    Ryzen 7 5700U 8 (16) 1.8 4.3 8 MB 2 × 4 Radeon
    Graphics
    [a]    		 1.9 512:32:8
    8 CU    		 1945.6 10–25 W Jan 12, 2021
    Ryzen 5 5500U[59] 6 (12) 2.1 4.0 2 × 3 1.8 448:28:8
    7 CU    		 1612.8
    Ryzen 3 5300U 4 (8) 2.6 3.8 4 MB 1 × 4 1.5 384:24:8
    6 CU    		 1152
    Close
    1. [i]
      Core Complexes (CCX) × cores per CCX
    2. [ii]
      Unified shaders : texture mapping units : render output units and compute units (CU)
    3. [iii]
      Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
    1. [a]
      All of the iGPUs are branded as AMD Radeon Graphics.

    Ultra-mobile APUs

    In 2022, AMD announced the Mendocino ultra-mobile APUs.[60]

    Common features of Ryzen 7020 notebook APUs:

    • Socket: FT6
    • All the CPUs support LPDDR5-5500 in dual-channel mode.
    • L1 cache: 64 KB (32 KB data + 32 KB instruction) per core.
    • L2 cache: 512 KB per core.
    • All the CPUs support 4 PCIe 3.0 lanes.
    • Native USB 4 (40Gbps) Ports: 0
    • Native USB 3.2 Gen 2 (10Gbps) Ports: 1
    • Includes integrated RDNA 2 GPU.
    • Fabrication process: TSMC N6 FinFET.
    More information Branding and Model, CPU ...
    Branding and Model CPU GPU TDP Release
    date
    Cores
    (threads)    		 Clock rate (GHz) L3 cache
    (total)    		 Core
    config[i]    		 Model Clock
    (GHz)    		 Processing
    power[ii]
    (GFLOPS)
    Base Boost
    Ryzen 5 7520U[iii] 4 (8) 2.8 4.3 4 MB 1 × 4 610M
    2 CU    		 1.9 486.4 15 W September 20, 2022[61]
    Ryzen 3 7320U[iii] 2.4 4.1
    Close
    1. [i]
      Core Complexes (CCX) × cores per CCX
    2. [ii]
      Single precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
    3. [iii]
      Model also available as Chromebook optimized version as 7520C[62] and 7320C[63] released on May 23, 2023

    Embedded APUs

    More information Model, Release date ...
    Model Release
    date    		 Fab CPU GPU Socket PCIe
    support    		 Memory
    support    		 TDP
    Cores
    (threads)    		 Clock rate (GHz) Cache Archi-
    tecture    		 Config[i] Clock
    (GHz)    		 Processing
    power[ii]
    (GFLOPS)
    Base Boost L1 L2 L3
    V2516[64] Nov 10, 2020[65] TSMC
    7FF    		 6 (12) 2.1 3.95 32 KB inst.
    32 KB data
    per core    		 512 KB
    per core    		 8 MB GCN 5 384:24:8
    6 CU    		 1.5 1152 FP6 20
    (8+4+4+4)
    PCIe 3.0    		 DDR4-3200
    dual-channel
    LPDDR4X-4266
    quad-channel    		 10–25 W
    V2546[64] 3.0 3.95 35–54 W
    V2A46[64] Jan 4, 2023[66] 3.2 448:28:8
    7 CU    		 1.6 1433.6
    V2718[64] Nov 10, 2020 8 (16) 1.7 4.15 10–25 W
    V2748[64] 2.9 4.25 35–54 W
    Close
    1. [i]
      Unified Shaders : Texture Mapping Units : Render Output Units and Compute Units (CU)
    2. [ii]
      Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

    Server CPUs

    Common features:

    • SP3 socket
    • Zen 2 microarchitecture
    • TSMC 7 nm process for the compute dies, GloFo 14 nm process for the I/O die
    • MCM with one I/O Die (IOD) and multiple Core Complex Dies (CCD) for compute, two core complexes (CCX) per CCD chiplet
    • Eight-channel DDR4-3200
    • 128 PCIe 4.0 lanes per socket, 64 of which are used for Infinity Fabric inter-processor links in 2P platforms
    • 7002P series models are limited to uniprocessor operation (1P, single-socket)
    More information Model, Cores (threads) ...
    Model Cores
    (threads)    		 Chiplets Core
    config[i]    		 Clock rate Cache Socket Scaling TDP Release
    date    		 Release
    price
    Base
    (GHz)    		 Boost
    (GHz)    		 L2
    per core    		 L3
    per CCX    		 Total
    7232P   8 (16)2 + IOD   4 × 23.13.2512 KB  8 MB36 MB  SP31P 120 WAug 7, 2019  $450
    7252   4 × 23.13.216 MB68 MB2P   $475
    7262 4 + IOD   8 × 13.23.4132 MB 155 W  $575
    7F32   8 × 13.73.9132 MB 180 WApr 14, 2020[67]$2100
    7272 12 (24)2 + IOD   4 × 32.93.216 MB70 MB2P 120 WAug 7, 2019  $625
    7282 16 (32)2 + IOD   4 × 42.83.216 MB72 MB2P 120 WAug 7, 2019  $650
    7302(P) 4 + IOD   8 × 23.03.3136 MB2P (1P) 155 W  $978 ($825)
    7F52 8 + IOD 16 × 13.53.9264 MB2P 240 WApr 14, 2020[67]$3100
    7352 24 (48)4 + IOD   8 × 32.33.216 MB140 MB2P 155 WAug 7, 2019$1350
    7402(P) 2.83.352P (1P) 180 W$1783 ($1250)
    7F72 6 + IOD 12 × 23.23.7204 MB2P 240 WApr 14, 2020[67]$2450
    7452 32 (64)4 + IOD   8 × 42.353.3516 MB144 MB2P 155 WAug 7, 2019$2025
    7502(P) 2.53.352P (1P) 180 W$2600 ($2300)
    7542 2.93.42P 225 W$3400
    7532 8 + IOD 16 × 22.43.3272 MB 200 W$3350
    7552 48 (96)6 + IOD 12 × 42.23.316 MB216 MB2P 200 WAug 7, 2019$4025
    7642 8 + IOD 16 × 32.33.3280 MB 225 W$4775
    7662 64 (128)8 + IOD 16 × 42.03.316 MB288 MB2P 225 WAug 7, 2019$6150
    7702(P) 2.03.352P (1P) 200 W$6450 ($4425)
    7742 2.253.4 2P 225 W$6950
    7H12 2.63.3 280 WSep 18, 2019---
    Close
    1. [i]
      Core Complexes (CCX) × cores per CCX

    Video game consoles and other embedded

    Gallery

    • AMD Ryzen 7 3700X
      AMD Ryzen 7 3700X
    • Zen 2 I/O Die
      Zen 2 I/O Die
    • Infrared die shot of the I/O Die
      Infrared die shot of the I/O Die
    • EPYC I/O Die
      EPYC I/O Die
    • Zen 2 Core Complex Die (CCD)
      Zen 2 Core Complex Die (CCD)
    • AMD EPYC 7702 server processor
      AMD EPYC 7702 server processor
    • A delidded AMD 7702 featuring 8 CCDs and 1 I/O die, with remains of the solder thermal interface material (TIM) on the chiplets
      A delidded AMD 7702 featuring 8 CCDs and 1 I/O die, with remains of the solder thermal interface material (TIM) on the chiplets

    See also

    Wikimedia Commons has media related to Zen 2 microarchitecture.

    References

    Related Articles

    Wikiwand AI