On 1/16/24 04:57, Daniel Henrique Barboza wrote:
I am now wondering if this is worth the trouble, and we should instead do:
+ int vlmax = cpu->cfg.vlenb >> (s->sew - s->lmul);
Like we're already doing in patch 9. Patch 12 would be a similar case.
This is more like what I expected to see.
On 1/12/24 19:51, Richard Henderson wrote:
On 1/13/24 08:38, Daniel Henrique Barboza wrote:
Signed-off-by: Daniel Henrique Barboza
---
target/riscv/insn_trans/trans_rvv.c.inc | 26 +
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/target/riscv/insn_t
On 1/13/24 08:38, Daniel Henrique Barboza wrote:
Signed-off-by: Daniel Henrique Barboza
---
target/riscv/insn_trans/trans_rvv.c.inc | 26 +
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans
Signed-off-by: Daniel Henrique Barboza
---
target/riscv/insn_trans/trans_rvv.c.inc | 26 +
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans/trans_rvv.c.inc
index 804cfd6c7f..3782d0fa2f 100644
