RFR: 8293833: Error mixing types with -XX:+UseCMoveUnconditionally -XX:+UseVectorCmov [v4]
Fei Gao
fgao at openjdk.org
Mon Oct 17 06:47:21 UTC 2022
> After JDK-8139340, JDK-8192846 and JDK-8289422, we can vectorize
> the case below by enabling -XX:+UseCMoveUnconditionally and
> -XX:+UseVectorCmov:
>
> // double[] a, double[] b, double[] c;
> for (int i = 0; i < a.length; i++) {
> c[i] = (a[i] > b[i]) ? a[i] : b[i];
> }
>
>
> But we don't support the case like:
>
> // double[] a;
> // int seed;
> for (int i = 0; i < a.length; i++) {
> a[i] = (i % 2 == 0) ? seed + i : seed - i;
> }
>
> because the IR nodes for the CMoveD in the loop is:
>
> AddI AndI AddD SubD
> \ / / /
> CmpI / /
> \ / /
> Bool / /
> \ / /
> CMoveD
>
>
> and it is not our target pattern, which requires that the inputs
> of Cmp node must be the same as the inputs of CMove node
> as commented in CMoveKit::make_cmovevd_pack(). Because
> we can't vectorize the CMoveD pack, we shouldn't vectorize
> its inputs, AddD and SubD. But the current function
> CMoveKit::make_cmovevd_pack() doesn't clear the unqualified
> CMoveD pack from the packset. In this way, superword wrongly
> vectorizes AddD and SubD. Finally, we get a scalar CMoveD
> node with two vector inputs, AddVD and SubVD, which has
> wrong mixing types, then the assertion fails.
>
> To fix it, we need to remove the unvectorized CMoveD pack
> from the packset and clear related map info.
Fei Gao has updated the pull request incrementally with one additional commit since the last revision:
Update IR framework testcase
-------------
Changes:
- all: https://git.openjdk.org/jdk/pull/10627/files
- new: https://git.openjdk.org/jdk/pull/10627/files/47ca7341..f65118cc
Webrevs:
- full: https://webrevs.openjdk.org/?repo=jdk&pr=10627&range=03
- incr: https://webrevs.openjdk.org/?repo=jdk&pr=10627&range=02-03
Stats: 9 lines in 1 file changed: 9 ins; 0 del; 0 mod
Patch: https://git.openjdk.org/jdk/pull/10627.diff
Fetch: git fetch https://git.openjdk.org/jdk pull/10627/head:pull/10627
PR: https://git.openjdk.org/jdk/pull/10627
More information about the hotspot-compiler-dev
mailing list