sshyran/core-v-family-of-risc-v-cores

CORE-V Family of RISC-V Cores

CORE-V Family of Open-Source RISC-V Cores

CORE-V is a family of permisively licensed, open-source RISC-V cores currated by the OpenHW Group ecosystems. Below is the CORE-V Roadmap of Application class and Embedded class cores followed by a short description of each of the cores and links to their respective GitHub repositories. The overall CORE-V Roadmap as well as core specific features and functionality are driven by members of the OpenHW Group. Details regarding OpenHW Group membership can be found here.

CORE-V Application Class, 5/6-Stage Cores

CVA6 Originally known as the PULP Ariane core, the CORE-V CVA6 6-stage, single issue, in-order core implementing RV32GC or RV64GC extensions with three privilege levels M, S, U to fully support a Unix-like (Linux, BSD, etc.) operating system. It has configurable size, separate TLBs, a hardware PTW and branch-prediction (branch target buffer, branch history table and a return address stack).

CVA5 The CVA5 is a 32-bit RISC-V processor designed for FPGAs supporting the Multiply/Divide and Atomic extensions (RV32IMA). The processor is written in SystemVerilog and has been designed to be both highly extensible and highly configurable. The CVA5 is derived from the Taiga Project from Simon Fraser University. The pipeline has been designed to support parallel, variable-latency execution units and to readily support the inclusion of new execution units.

CORE-V Embedded Class, 4-Stage Cores

CVE4 is a family of cores for embedded platforms that started from the PULP RI5CY core. These cores are 32bit, 4-stage in-order cores. Single configurations of these cores are maintained on different repositories and specialize in different embedded applications. Please find below the members of the CVE4 family.

• CV32E40P Originally known as the PULP RI5CY core, the CORE-V CV32E40P is a 32bit, 4-stage core that implements, RV32IMFC[Xpulp], has an optional 32-bit FPU supporting the F extension and instruction set extensions for DSP operations, including hardware loops, SIMD extensions, bit manipulation and post-increment instructions. This repository is has been moved (not forked) from the original PULP Platform github repository to its new home at the OpenHW Group github repository.

• CV32E40X The CORE-V CV32E40X is a small and efficient, 32-bit, in-order RISC-V core with a 4-stage pipeline that implements the RV32[I,E][M|Zmmul][A]Zca_Zcb_Zcmb_Zcmp_Zcmt[Zba_Zbb_Zbs|Zba_Zbb_Zbc_Zbs]ZicntrZihpmZicsrZifencei[X] instruction set architecture. The CV32E40X core is aimed at compute intensive applications and offers a general purpose extension interface by which custom instructions can be added external to the core.

• CV32E40S The CORE-V CV32E40S is a small and efficient, 32-bit, in-order RISC-V core with a 4-stage pipeline that implements the RV32[I|E][M|Zmmul]Zca_Zcb_Zcmb_Zcmp_Zcmt[Zba_Zbb_Zbs|Zba_Zbb_Zbc_Zbs]ZicsrZifenceiXsecure instruction set architecture. The CV32E40S core is aimed at security applications and offers both Machine mode and User mode, an enhanced PMP, as well as various anti-tampering features.

• CV32E41P is a small and efficient, 32-bit, in-order RISC-V core with a 4-stage pipeline that implements the RV32IM[F,Zfinx]C[Zce] instruction set architecture, and the Xpulp custom extensions for achieving higher code density, performance, and energy efficiency. It started its life as a fork of the CV32E40P core to implement the official RISC-V Zfinx and Zce ISA extensions.

CORE-V Embedded Class, 2-Stage Core

CVE2 is a low-cost, low-power, 32-bit, in-order RISC-V core with a 2-stage pipeline that implements RV32{E, I}[M]C instruction set architecture for achieving high-energy efficiency on control-oriented, computationally limited applications. It started its life as a fork of the lowRISC Ibex core and it will be shirked down to its essential components.