按年被提到
20162017 · 5 次2026
系统、数据库与网络›计算机体系结构与硬件·arXiv:1607.02318 · cs.AR

The Renewed Case for the Reduced Instruction Set Computer: Avoiding ISA Bloat with Macro-Op Fusion for RISC-V

精简指令集计算机的再论:用宏操作融合避免 RISC-V 的 ISA 膨胀
Christopher Celio, Palmer Dabbelt, David A. Patterson, Krste Asanović · 2016

论证 RISC-V 配合宏操作融合,可在性能和代码密度上追平 CISC

开始阅读 ↗PDFalphaXiv 讨论
被提及 · 9 人首次 2016-07-28 · 最近 2025-01-03
9不同的人
9活跃月份
10讨论串
15被引(OpenAlex)

报告在 SPEC CINT2006 上比较 ARMv7、ARMv8、IA-32、x86-64 与开放的 RISC-V RV64G、RV64GC 的动态指令数和取指字节数。RV64G 平均比 x86-64 多执行 16% 的指令,但与 x86-64 退休的微操作数相差在 2% 以内;压缩变体 RV64GC 是最密的 ISA,取指字节比 x86-64 少 8%。利用宏操作融合可再把有效指令数平均减少 5.4%,因此无需再往 ISA 里添加更多指令。

HN 为什么提它

HN 上的人反复引用它来论证 ISA 本身对性能影响很小、简单正交的 ISA 加上宏操作融合就能追平 x86 和 ARM。

实证研究难度 4 / 5约 45 分钟经得起时间
读之前最好知道
1计算机体系结构与指令集(ISA)
2RISC 与 CISC
3微操作(micro-ops)与流水线
4SPEC 基准测试

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
批评kragen · 2022-05

“they don't seem to have simulated macro-op fusion at RTL level, much less in an FPGA or a MOSIS run.”

India reveals RISC-V CPU roadmap, expects product by 2023原评论 ↗
引用cmrx64 · 2016-07

“I think RISC-V is showing that RISC ISAs can still compete in this space: The Renewed Case for the Reduced Instruction Set Computer.”

拿它说明 RISC 指令集借助宏操作融合仍有竞争力
Show HN: Accelerating SHA256 by 100x in Golang on ARM原评论 ↗
引用_chris_ · 2016-12

“Load/store multiple, for starters. Even just load-pair-increment-address is a pain as it requires 3 write ports.”

借它支持 ARM 指令集在超标量设计中有问题的观点
Ask HN: What's the value proposition of RISC-V?原评论 ↗
引用_chris_ · 2017-09

“I just so happen to have written a tech report on this very topic! The Renewed Case for the Reduced Instruction Set Computer”

贴出自己写的相关技术报告,论证指令集选择影响很小
BOOM v2: an open-source out-of-order RISC-V core原评论 ↗
引用_chris_ · 2017-09

“The ISA is going to have close to zero impact on a processor's performance.”

借它主张指令集对处理器性能几乎没有影响
BOOM v2: an open-source out-of-order RISC-V core原评论 ↗
引用microcolonel · 2017-09

“Yeah, I drew my conclusions from your papers.”

说明自己关于 ARMv8 与 RISC-V 因融合而性能相当的结论来自这些论文
BOOM v2: an open-source out-of-order RISC-V core原评论 ↗
看全部 11 条 →
引用jabl · 2017-12

“So with RISC-V GC + macro fusion of a few common idioms you get slightly less micro-ops than x86-64, armv7, or armv8.”

引用它说明 RISC-V 加宏融合后微操作比 x86 还少一点
Power9 to the People原评论 ↗
引用baobrien · 2017-12

“With a few simple macro-op fusion pairs, it also comes right up to x86_64 in dynamic uOp count.”

引用它说明简单融合后 RISC-V 动态微操作数追平 x86_64
Boom v2: Open-source out-of-order RISC-V core [video]原评论 ↗
引用paulmd · 2022-03

“Also, a huge amount of instructions end up being used very little, there are a few "hotspot" instructions that make up a huge percent of actual instructions executed.”

引用它说明少数热点指令占了绝大多数执行量
RISC-V is succeeding原评论 ↗
引用jabl · 2022-11

“is a widely cited paper that argues that simple and orthogonal ISA's are preferable, as fusion can fix up those common cases”

称它是被广泛引用的论文,主张简单正交的指令集更好
ARM: Pragmatism, Not Purity原评论 ↗
引用Arnavion · 2025-01

“The only other source I know of was this 2016 paper that suggested specific macro fusions.”

称这是自己所知唯一提出具体宏融合序列的 2016 年论文
XiangShan – Open-source high performance RISC-V processor原评论 ↗
被提交为 story · 1 次