On 9/28/23 17:41, Nick Bowler wrote:
On 2023-09-28, Richard Henderson wrote:
Belated follow-up suggestion:
- if ((tmp & 0xff) > 0x7f) {
- tmp += 0x100;
- }
+ tmp += 0x80;
7 occurrences throughout vis_helper.c.
I agree with making this particular change but I think since it doesn
On 2023-09-28, Richard Henderson wrote:
> Belated follow-up suggestion:
>
> - if ((tmp & 0xff) > 0x7f) {
> - tmp += 0x100;
> - }
> + tmp += 0x80;
>
> 7 occurrences throughout vis_helper.c.
I agree with making this particular change but I think since it doesn't
fix a bug, it should go
On 9/24/23 01:03, Nick Bowler wrote:
On a real UltraSparc II, the fmul8x16au instruction takes two single-
precision input operands and returns a double-precision result. For
the second operand, bits 31:16 are used, and bits 15:0 are ignored.
However, the emulation is taking two double-precisio
On a real UltraSparc II, the fmul8x16au instruction takes two single-
precision input operands and returns a double-precision result. For
the second operand, bits 31:16 are used, and bits 15:0 are ignored.
However, the emulation is taking two double-precision input operands,
and furthermore it is