On 7/31/24 02:03, Peter Maydell wrote:
> To implement the FEAT_EBF16 semantics, we are going to need
> the CPUARMState env pointer in every helper function which calls
> bfdotadd().
>
> Pass the env pointer through from generated code to the sme_bfmopa
> helper. (We'll add the code that uses it when we've adjusted
> all the helpers to have access to the env pointer.)
>
> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
> ---
> target/arm/tcg/helper-sme.h | 4 ++--
> target/arm/tcg/sme_helper.c | 4 ++--
> target/arm/tcg/translate-sme.c | 2 +-
> 3 files changed, 5 insertions(+), 5 deletions(-)
>
> diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h
> index 659867a1faf..f12d903aa44 100644
> --- a/target/arm/tcg/helper-sme.h
> +++ b/target/arm/tcg/helper-sme.h
> @@ -126,8 +126,8 @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG,
> void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG,
> void, ptr, ptr, ptr, ptr, ptr, ptr, i32)
> -DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG,
> - void, ptr, ptr, ptr, ptr, ptr, i32)
> +DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG,
> + void, env, ptr, ptr, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG,
> void, ptr, ptr, ptr, ptr, ptr, i32)
> DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG,
> diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
> index 2af2b957cb6..f172225b2f2 100644
> --- a/target/arm/tcg/sme_helper.c
> +++ b/target/arm/tcg/sme_helper.c
> @@ -1080,8 +1080,8 @@ void HELPER(sme_fmopa_h)(CPUARMState *env,
> }
> }
>
> -void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
> - void *vpm, uint32_t desc)
> +void HELPER(sme_bfmopa)(CPUARMState *env, void *vza, void *vzn, void *vzm,
> + void *vpn, void *vpm, uint32_t desc)
Per this morning's review of do_outprod_env, I think env should be penultimate, as for
other gen_helper_gvec_5_ptr functions.
Otherwise,
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
r~
> {
> intptr_t row, col, oprsz = simd_maxsz(desc);
> uint32_t neg = simd_data(desc) * 0x80008000u;
> diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
> index 8e9332f1898..bcb502feb05 100644
> --- a/target/arm/tcg/translate-sme.c
> +++ b/target/arm/tcg/translate-sme.c
> @@ -355,7 +355,7 @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a,
> MO_64, FPST_FPCR, gen_helper_sme_fmopa_d)
>
> /* TODO: FEAT_EBF16 */
> -TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa)
> +TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa)
>
> TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s)
> TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s)