petrbalvin 2bd52eb7ad fix(asm): scale the FLDPQ and FSTPQ pair offsets by sixteen ...

The pair encoder derived the imm7 divisor from the width suffix alone, so
the 128-bit FP pairs divided their offsets by eight and encoded twice the
distance.  The Q spellings scale by sixteen like every other 128-bit
access; the differential kernel carries them now.

Assisted-by: GLM 5.3 Flash

2026-10-07 02:36:24 +02:00

..

verify

fix(asm): scale the FLDPQ and FSTPQ pair offsets by sixteen

2026-10-07 02:36:24 +02:00

add_riscv64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00

amo_fp_riscv64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00

csr_riscv64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00

fma_riscv64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00

lrsc_cvt_riscv64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00

sample_amd64.s

style: put the repository assembly in gasm fmt canonical form

2026-09-17 20:33:18 +02:00