Messages in this thread | | | Subject | Re: [PATCH 0/2] add AES-NI/AVX2/x86_64 implementation | From | Tianjia Zhang <> | Date | Sun, 22 Aug 2021 13:20:06 +0800 |
| |
Hi David,
On 8/20/21 6:03 PM, David Laight wrote: > From: Tianjia Zhang >> Sent: 18 August 2021 04:31 >> >> This patchsets exported some of the common functions implemented by >> the SM4 AESNI/AVX algorithm, and reused these functions to achieve >> the acceleration of AESNI/AVX2 implementation. > > These functions need bracketing by kernel_fpu_enable() > (or whatever it is called.) > That will significantly affect the performance. > > Also the functions look pretty big (I don't know how big > the generic ones are) and will take time to load into the I$ > and will displace other code. > > So while a hot-cache benchmark might show improvements > for repeated calls is isn't obvious that any significant > gain will be made for real-life calls which could easily > be of single buffers. > > David > > - > Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK > Registration No: 1397386 (Wales) >
Yes, the functions bracketed by kernel_fpu_begin() do affect performance. It seems that the kernel can only do this, so by processing as much data as possible in a kernel_fpu_begin/end() operation to improve performance. actually do it now.
Best regards, Tianjia
| |