Re: [RFC] risc-v vector (RVV) emulation performance issues

2023-07-25 Thread Richard Henderson
On 7/24/23 06:40, Daniel Henrique Barboza wrote: Hi, As some of you are already aware the current RVV emulation could be faster. We have at least one commit (bc0ec52eb2, "target/riscv/vector_helper.c: skip set tail when vta is zero") that tried to address at least part of the problem. Running a

Re: [RFC] risc-v vector (RVV) emulation performance issues

2023-07-24 Thread Philippe Mathieu-Daudé
On 24/7/23 15:40, Daniel Henrique Barboza wrote: Hi, As some of you are already aware the current RVV emulation could be faster. We have at least one commit (bc0ec52eb2, "target/riscv/vector_helper.c: skip set tail when vta is zero") that tried to address at least part of the problem. First t

[RFC] risc-v vector (RVV) emulation performance issues

2023-07-24 Thread Daniel Henrique Barboza
Hi, As some of you are already aware the current RVV emulation could be faster. We have at least one commit (bc0ec52eb2, "target/riscv/vector_helper.c: skip set tail when vta is zero") that tried to address at least part of the problem. Running a simple program like this: --- #define SZ 10