optimizing acmp in L-World (original) (raw)

David Simms david.simms at oracle.com
Thu Feb 8 13:58:14 UTC 2018

Just a note that the "Universe::oop_metadata_odd_mask()" is the "encoded klass ptr form", therefore dependent on "UseCompressedClassPointers" feature, which when enabled I assume there is no space within the compressed ptr space (I could be wrong that). That is:

    "assert(Universe::oop_metadata_odd_mask() == 1, "should be");" ? "should be" == "if (UseCompressedClassPointers)"

/D

On 8/02/2018 8:03 a.m., John Rose wrote:

On Feb 7, 2018, at 5:27 PM, Tobias Hartmann <tobias.hartmann at oracle.com <mailto:tobias.hartmann at oracle.com>> wrote:

Knowing that ObjectAlignmentInBytes is guaranteed to be >= 2, we can do even better:

__ testptr(rdx, rdx);_ __ jcc(Assembler::zero, isnull);_ __ movl(rbx, Address(rdx, oopDesc::klassoffsetinbytes()));_ __ andptr(rbx, Universe::oopmetadataoddmask());_ __ orptr(rdx, rbx);_ Yep. And if metadataoddmask is some higher number like 0x10 or 0x20 (which I think it should be, in the long run*) then you just need to add a right-shift to pull it down into to the mask 0x07. In future systems if we use a color bit to mark the buffer pointer of the value type, we can just clear that single bit, in one of the operands, to force x != x. — John * P.S. So metadataoddmask is 0x01. I missed that detail the first time around. If we align klass metadata pointers a little more strongly we can make it a larger number like 0x10 or 0x20, with the effect that we don't need an extra instruction to remove that bit when using the klass pointer. We could just align value and object klasses a little differently, by allocating them (say) even mod 0x20 and then (say) bump each value klass upward by 0x10. The fragmentation overhead would be small relative to the (probable) speed improvement of omitting the detag operation.

More information about the valhalla-dev mailing list