Re: [PATCH v2 3/6] target/riscv: add support for zfinx

2022-01-01 Thread Weiwei Li
在 2022/1/2 上午3:48, Richard Henderson 写道: ol is the operation length; xl is the register length. In this case, the operation length doesn't matter -- we're interested in distinguishing RV32 and RV64, because that's where the change in semantics comes from. So both read and write fpr should

Re: [PATCH v2 3/6] target/riscv: add support for zfinx

2022-01-01 Thread Richard Henderson
On 12/31/21 10:05 PM, Weiwei Li wrote: 在 2022/1/1 上午4:06, Richard Henderson 写道: On 12/30/21 7:23 PM, Weiwei Li wrote: +    if (reg_num != 0) { +    switch (get_ol(ctx)) { Oh, you should be using get_xl here and elsewhere in this patch, not get_ol. Sorry. I don't know the difference betw

Re: [PATCH v2 3/6] target/riscv: add support for zfinx

2021-12-31 Thread Weiwei Li
在 2022/1/1 上午4:06, Richard Henderson 写道: On 12/30/21 7:23 PM, Weiwei Li wrote: +    if (reg_num != 0) { +    switch (get_ol(ctx)) { Oh, you should be using get_xl here and elsewhere in this patch, not get_ol. Sorry. I don't know the difference between get_xl and  get_ol. From gpr regis

Re: [PATCH v2 3/6] target/riscv: add support for zfinx

2021-12-31 Thread Richard Henderson
On 12/30/21 7:23 PM, Weiwei Li wrote: +if (reg_num != 0) { +switch (get_ol(ctx)) { Oh, you should be using get_xl here and elsewhere in this patch, not get_ol. r~

Re: [PATCH v2 3/6] target/riscv: add support for zfinx

2021-12-31 Thread Richard Henderson
On 12/30/21 7:23 PM, Weiwei Li wrote: From: liweiwei - update extension check REQUIRE_ZFINX_OR_F - update single float point register read/write - disable nanbox_s check Co-authored-by: ardxwe Signed-off-by: Weiwei Li Signed-off-by: Junqiang Wang --- target/riscv/fpu_helper.c

[PATCH v2 3/6] target/riscv: add support for zfinx

2021-12-30 Thread Weiwei Li
From: liweiwei - update extension check REQUIRE_ZFINX_OR_F - update single float point register read/write - disable nanbox_s check Co-authored-by: ardxwe Signed-off-by: Weiwei Li Signed-off-by: Junqiang Wang --- target/riscv/fpu_helper.c | 89 +++ target/riscv/helpe