[Mono-list] 32-bit vs 64-bit Performance Discrepency

[Justin Holewinski]

On Wed, Oct 26, 2011 at 6:15 PM, Rodrigo Kumpera <kumpera at gmail.com> wrote:

> The CLR demands that all floating point calculations to be conducted with
> double precision.


Where in the spec does it state this?  Everything I've read allows for both
32-bit and 64-bit representations, with the only restriction being that
arithmetic must be performed with enough precision for the expression type.

And if 64-bit arithmetic is required, why is 32-bit used in the 32-bit Mono
VM, and in the .NET VM?


>
>
>
> On Wed, Oct 26, 2011 at 4:00 PM, Justin Holewinski <
> justin.holewinski at gmail.com> wrote:
>
>> I'm currently testing Mono on some single-precision FP-heavy workloads,
>> and I'm a bit surprised to see that the performance of the 64-bit VM is
>> significantly slower than the 32-bit VM, over 2x in many cases.  As an
>> example, on Mac OS X 10.7, with Mono 2.10.6 compiled in both 32-bit and
>> 64-bit modes:
>>
>> Matrix Multiply Micro-Benchmark:
>>
>> jholewinski at aquila [tests]$ ~/projects/mono/install/x86/bin/mono -O=all
>> embed1-extract.exe
>> Scalar:    362.775 ms
>> Mono.Simd: 164.645 ms
>> jholewinski at aquila [tests]$ ~/projects/mono/install/x64/bin/mono -O=all
>> embed1-extract.exe
>> Scalar:    841.482 ms
>> Mono.Simd: 131.844 ms
>>
>> The Mono.Simd case is good, but for the scalar code that is a
>> large discrepancy.  Further, if I look at the disasembly from Mono, it looks
>> like the 64-bit VM is using double-precision arithmetic for single-precision
>> data types with the non-Mono.Simd version:
>>
>> 000000000000001b        movss   0x00(%r13),%xmm0
>> 0000000000000021        cvtss2sd        %xmm0,%xmm0
>> 0000000000000025        movss   (%r14),%xmm1
>> 000000000000002a        cvtss2sd        %xmm1,%xmm1
>> 000000000000002e        mulsd   %xmm1,%xmm0
>> 0000000000000032        movss   0x04(%r13),%xmm1
>> 0000000000000038        cvtss2sd        %xmm1,%xmm1
>> 000000000000003c        movss   0x10(%r14),%xmm2
>> 0000000000000042        cvtss2sd        %xmm2,%xmm2
>> 0000000000000046        mulsd   %xmm2,%xmm1
>> 000000000000004a        addsd   %xmm1,%xmm0
>> 000000000000004e        movss   0x08(%r13),%xmm1
>> 0000000000000054        cvtss2sd        %xmm1,%xmm1
>> 0000000000000058        movss   0x20(%r14),%xmm2
>> 000000000000005e        cvtss2sd        %xmm2,%xmm2
>> 0000000000000062        mulsd   %xmm2,%xmm1
>> 0000000000000066        addsd   %xmm1,%xmm0
>> 000000000000006a        movss   0x0c(%r13),%xmm1
>>
>> This could definitely account for the performance discrepancy.  Why is
>> Mono up-converting to doubles for single-precision expressions?
>>
>> The 32-bit VM appears to be using the x87 stack instead of SSE scalar
>> instructions, but at least its using single-precision.
>>
>> --
>>
>> Thanks,
>>
>> Justin Holewinski
>>
>>
>> _______________________________________________
>> Mono-list maillist  -  Mono-list at lists.ximian.com
>> http://lists.ximian.com/mailman/listinfo/mono-list
>>
>>
>


-- 

Thanks,

Justin Holewinski
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.ximian.com/pipermail/mono-list/attachments/20111026/a2e307d1/attachment.html