 LDj3SNuD
|
e674b37710
Fix Fcvtl_V and Fcvtn_V; fix half to float conv. and add float to half conv. (full FP emu.). Add 4 FP Tests. (#468)
|
7 лет назад |
|
LDj3SNuD
|
894459fcd7
Add Fmls_Se, Fmulx_Se/Ve, Smov_S Inst.; Opt. Clz/Clz_V, Cnt_V, Shl_V, S/Ushr_V, S/Usra_V Inst.; Add 11 Tests. Some fixes. (#449)
|
7 лет назад |
|
LDj3SNuD
|
bba9bf97d0
Add 9+7 fast/slow FP inst. impls.; add 14 FP Tests. (#437)
|
7 лет назад |
 gdkchan
|
3cf1b6cf77
Fix silly copy/paste error on float variant of the FMINNM instruction
|
7 лет назад |
|
gdkchan
|
221270db90
More accurate impl of FMINNM/FMAXNM, add vector variants (#296)
|
7 лет назад |
 Merry
|
b233ae964f
AInstEmitSimdCvt: Half-precision to single-precision conversion (#235)
|
7 лет назад |
|
Merry
|
0f8f40486d
ChocolArm64: More accurate implementation of Frecpe & Frecps (#228)
|
7 лет назад |
|
Merry
|
af1516a146
ASoftFloat: Fix InvSqrtEstimate for negative values (#233)
|
7 лет назад |
|
Merry
|
39f20d8d1a
Implement Frsqrte_S (#72)
|
8 лет назад |
