motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-04 16:23:55 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Implement vector float32 to bfloat16 conversion

Browse source 
This is BFCVT{N,T} for both AArch64 AdvSIMD and SVE,
and VCVT.BF16.F32 for AArch32 NEON.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525225817.400336-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2021-05-25 15:58:09 -07:00 • committed by Peter Maydell
parent 3a98ac40fa
commit d29b17ca3e
9 changed files with 95 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

7
target/arm/vfp_helper.c
View file

@ -416,6 +416,13 @@ uint32_t HELPER(bfcvt)(float32 x, void *status)
return float32_to_bfloat16(x, status);
}
uint32_t HELPER(bfcvt_pair)(uint64_t pair, void *status)
{
bfloat16 lo = float32_to_bfloat16(extract64(pair, 0, 32), status);
bfloat16 hi = float32_to_bfloat16(extract64(pair, 32, 32), status);
return deposit32(lo, 16, 16, hi);
}
/*
* VFP3 fixed point conversion. The AArch32 versions of fix-to-float
* must always round-to-nearest; the AArch64 ones honour the FPSCR