RISC-V 很慢

RISC-V 很慢
RISC-V Is Sloooow

原始链接: https://marcin.juszkiewicz.com.pl/2026/03/10/risc-v-is-sloooow/

过去三个月，作者一直致力于将 Fedora Linux 移植到 RISC-V 架构。这项工作包括处理错误报告（目前仅剩 17 个）以及提交 86 个软件包构建的补丁请求——其中许多已成功合并并构建为 Fedora 43。一个主要挑战是由于当前 RISC-V 硬件的限制，构建速度较慢。与其它架构相比（例如，binutils 在 RISC-V 上需要 143 分钟，而在 x86_64 上需要 29 分钟），构建时间显著更长，因此需要禁用链接时优化 (LTO) 以节省内存并缩短构建时间。作者使用 QEMU 和 80 个模拟核心来缓解这个问题，从而为 LLVM 等复杂软件包实现合理的构建时间。未来的计划包括构建 Fedora 44、标准化内核镜像以及获取更快的硬件——这对 RISC-V 成为 Fedora 的主要架构至关重要。需要更快的构建器来启用 LTO 并实现与其它平台相当的构建时间。

最近的Hacker News讨论集中在RISC-V处理器的 perceived 速度较慢的问题上。然而，评论者普遍认为问题不在于RISC-V指令集架构（ISA）本身，而在于当前的硅实现和缺乏特定于架构的软件优化。原始帖子链接到一篇基准测试RISC-V性能的文章，但一些人认为标题具有误导性，因为测试平台（Banana Pi）不能代表RISC-V的潜力。有一种观点认为，进展速度比预期慢，尤其是在David Keller的TensTorrent项目方面。一些评论员认为，更快的RISC-V实现更有可能出现在中国。有趣的是，讨论还强调了IBM的s390x架构出人意料的单核性能，但同时也幽默地警告说IBM对已发布的基准测试非常敏感。

原文

About 3 months ago I started working with RISC-V port of Fedora Linux. Many things happened during that time.

Triaging

I went through the Fedora RISC-V tracker entries, triaged most of them (at the moment 17 entries left in NEW) and tried to handle whatever possible.

Fedora packaging

My usual way of working involves fetching sources of a Fedora package (fedpkg clone -a) and then building it (fedpkg mockbuild -r fedora-43-riscv64). After some time, I check did it built and if not then I go through build logs to find out why.

Effect? At the moment, 86 pull requests sent for Fedora packages. From heavy packages like the “llvm15” to simple ones like the “iyfct” (some simple game). At the moment most of them were merged, and most of these got built for the Fedora 43. Then we can build them as well as we follow ‘f43-updates’ tag on the Fedora koji.

Slowness

Work on packages brings the hard, sometimes controversial, topic: speed. Or rather lack of it.

You see, the RISC-V hardware at the moment is slow. Which results in terrible build times — look at details of the binutils 2.45.1-4.fc43 package:

Architecture	Cores	Memory	Build time
aarch64	12	46 GB	36 minutes
i686	8	29 GB	25 minutes
ppc64le	10	37 GB	46 minutes
riscv64	8	16 GB	143 minutes
s390x	3	45 GB	37 minutes
x86_64	8	29 GB	29 minutes

Also worth mentioning is that the current build of RISC-V Fedora port is done with disabled LTO. To cut on memory usage and build times.

RISC-V builders have four or eight cores with 8, 16 or 32 GB of RAM (depending on a board). And those cores are usually compared to Arm Cortex-A55 ones. The lowest cpu cores in today’s Arm chips.

The UltraRISC UR-DP1000 SoC, present on the Milk-V Titan motherboard should improve situation a bit (and can have 64 GB ram). Similar with SpacemiT K3-based systems (but only 32 GB ram). Both will be an improvement, but not the final solution.

We need hardware capable of building above “binutils” package below one hour. With LTO enabled system-wide etc. And it needs to be rackable and manageable like any other boring server. Without it, we can not even plan for the RISC-V 64-bit architecture to became one of official, primary architectures in Fedora Linux.

I still use QEMU

Such long build times make my use of QEMU useful. You see, with 80 emulated cores, I can build the “llvm15” package in about 4 hours. Compare that to 10.5 hours on a Banana Pi BPI-F3 builder (it may be quicker on a P550 one).

busy btop — btop shows 80 cores being busy

And LLVM packages make real use of both available cores and memory. I am wondering how fast would it go on 192/384 cores of Ampere One-based system.

Future plans

We plan to start building Fedora Linux 44. If things go well, we will use the same kernel image on all of our builders (the current ones use a mix of kernel versions). LTO will still be disabled.

When it comes to lack of speed… There are plans to bring new, faster builders. And probably assign some heavier packages to them.