Re: [PATCH RFC] target/arm: Implement SVE2 fp multiply-add long

2020-05-04 Thread Richard Henderson
On 5/4/20 8:43 AM, Stephen Long wrote: > +for (i = 0; i < opr_sz; i += sizeof(float32)) { > +float32 nn = *(float16 *)(vn + H1_2(i + sel1)); > +float32 mm = *(float16 *)(vm + H1_2(i + sel1)); For integers we could rely on C types for the extension. For floating point, you need

[PATCH RFC] target/arm: Implement SVE2 fp multiply-add long

2020-05-04 Thread Stephen Long
Implements FMLALB, FMLALT, FMLSLB, FMLSLT Signed-off-by: Stephen Long --- target/arm/helper-sve.h| 5 target/arm/sve.decode | 6 target/arm/sve_helper.c| 27 ++ target/arm/translate-sve.c | 58 ++ 4 files changed, 96 in