Re: [Qemu-devel] [PATCH v3 00/22] re-factor softfloat and add fp16 functions

[Richard Henderson]

On 01/28/2018 12:41 PM, Emilio G. Cota wrote:
> On Thu, Jan 25, 2018 at 12:59:56 +0000, Alex Bennée wrote:
>> Howard Spoelstra <address@hidden> writes:
> (snip)
>>> Recent tcg optimisations had improved processor and floating point
>>> performance considerably, but that gain seems to be more than lost for
>>> the floating point performance.
>>>
>>> Any idea what is causing this?
>>
>> Well we expected a little degradation but it's a bit more than I
>> expected.
> 
> It's pretty bad (almost a 2X mean slowdown) for the three FP workloads
> in dbt-bench:

I have not yet tried dbt-bench, but on another test case I was able to recover
all of the performance by marking all of the helpers inline.  I'm somewhat
disappointed by the compiler here.


r~