The ARM Neoverse is a group of 64-bit ARM processor cores licensed by Arm Holdings. The cores are intended for datacenter, edge computing, and high-performance computing use. The group consists of ARM Neoverse V-Series, ARM Neoverse N-Series, and ARM Neoverse E-Series. ^{[1] [2]}

Neoverse V-Series

The Neoverse V-Series processors are intended for high-performance computing.

Neoverse V1

Neoverse V1 (code named Zeus ^[3]) is derived from the Cortex-X1 ^[4] and implements the ARMv8.4-A instruction set and some part of ARMv8.6-A. ^[5] It was officially announced by Arm on September 22, 2020. ^[6] It is said to be initially realized with a 7 nm process from TSMC. One of the changes from the X1 is that it supports SVE 2x256-bit.

According to The Next Platform, the AWS Graviton3 is based on the Neoverse V1. ^{[7] [8]}

Neoverse V2

Neoverse V2 (code named Demeter) is derived from the ARM Cortex-X3 and implements the ARMv9.0-A instruction set. It was officially announced by Arm on September 14, 2022. ^{[9] [10]} NVIDIA Grace, ^[11] AWS Graviton4 ^[12] and Google Axion ^[13] are based on the Neoverse V2.

Notable changes from the Neoverse V1: ^[14]

• BTB capacity: 12K entries
• TAGE predictor: 8-table
• micro-op cache: 1536 entries (reduced for efficiency)
• Decode width: 6
• Rename / Dispatch width: 8
• ROB: 320 entry
• Execution ports: 15
• L2 cache: 1024-2048 kB per core
• CMN-700 mesh interconnect
  • Up to 256 cores per die
  • Up to 512 MB SLC
  • Up to 4 TB/s bandwidth

Neoverse V3

Neoverse V3, (code named Poseidon) was teased by Arm alongside the V2 and E2 announcements. ^[15] It is targeted for systems including DDR5, PCIe gen6, and CXL 3.0. The codename Poseidon was first used for the generation succeeding Zeus, now V1, and targeted for 2021 on a 5nm node. ^[16]

Neoverse N-Series

The Neoverse N-Series processors are intended for core datacenter usage.

Neoverse N1

On February 20, 2019, Arm announced the Neoverse N1 microarchitecture (code named Ares) derived from the Cortex-A76 redesigned for infrastructure/server applications. The reference design supports up to 64 or 128 Neoverse N1 cores. ^{[17] [18]}

Notable changes from the Cortex-A76:

• Coherent I-cache and D-cache with 4-cycle LD-use
• L2 cache: 512–1024 kB per core
• Mesh interconnect instead of 1–4 cores per cluster

Neoverse N1 implements the ARMv8.2-A instruction set.

The Ampere Altra (2-socket 80-core) and AWS Graviton2 (64-core) CPU platforms are based on Neoverse N1 cores and were released in 2020. ^[19]

Neoverse N2

The Neoverse N2 (code named Perseus) is derived from the Cortex-A710 and implements the ARMv9.0-A instruction set. ^[19] It was officially announced by Arm on September 22, 2020. ^[6] On August 28, 2023, Arm announced the Neoverse CSS N2 (Genesis), a customizable CPU subsystem implementation by Arm to reduce the time to market for customers. ^{[20] [21] [22] [23]} Microsoft Azure Cobalt 100 128 Core CPU uses Neoverse N2. ^[24]

Notable changes from the Neoverse N1: ^{[25] [26]}

• BTB capacity: 8K entries
• micro-op cache: 1536 entries
• Rename / Dispatch width: 5
• ROB: 160+ entry
• Pipeline depth: 10 cycles
• Execution ports: 13
• SVE2 support
• CMN-700 mesh interconnect

Neoverse N-Next

Neoverse N-Next, presumably N3, was teased by Arm alongside the V2 and E2 announcements. ^[15] It is targeted for systems including DDR5, PCIe gen6, and CXL 3.0.

Neoverse E-Series

The Neoverse E-Series processors are intended for edge computing. They are designed for increased data throughput at decreased power consumption.

Neoverse E1

Neoverse E1 is derived from the Cortex-A65AE ^[27] and implements the ARMv8.2-A instruction set. It support SMT.

Neoverse E2

Neoverse E2 is derived from the Cortex-A510 ^[15] and implements the ARMv9-A instruction set.

Neoverse E-Next

Neoverse E-Next, presumably E3, was teased by Arm alongside the V2 and E2 announcements. ^[15] It is targeted for systems including DDR5, PCIe gen6, and CXL 3.0.

Matrix multiplication theoretical performance

Successors

With code name Poseidon a successor for Neoverse V1 (aka Zeus) ^[30] was first publicly mentioned on TechCon 2018. Actual introduction (used by third party chip designers in their products) was given in form of a rough target date of 2021. Its initial realization process is said to be 5 nm by TSMC.

References