[aarch64-port-dev ] RFR (S) 8131682: C1 should use multibyte nops everywhere
aph at redhat.com
Mon Jul 27 12:07:12 UTC 2015
On 07/27/2015 11:53 AM, Aleksey Shipilev wrote:
> On 07/27/2015 01:21 PM, Andrew Haley wrote:
>> On 27/07/15 10:13, Aleksey Shipilev wrote:
>>> Thanks Goetz! Fixed the assembler_ppc.inline.hpp.
>>> Andrew/Edward, are you OK with AArch64 part?
>> I agree that it looks good. Please have a look to see how many NOPs take the
>> same time as a branch.
> I don't quite believe we should spend time trying branches for nops, at
> least for x86. The change we are discussing follows the Intel
> Optimization Reference Manual 22.214.171.124 "Using NOPs", which
> Assembler::align for x86 seems to implement with some bells and
> whistles. Agner agrees on using multi-byte nops (0F 1F ...) on modern
> x86 chips as well; up to the point he claims 4 insn/clock throughput for
Sure. My apologies: I responded to the wrong person. My interest is
More information about the hotspot-compiler-dev