On 9/29/23 05:14, Jeff Law wrote:


On 9/28/23 21:49, Vineet Gupta wrote:

On 9/28/23 20:17, Jeff Law wrote:
I can bootstrap & regression test alpha using QEMU user mode emulation. So we might be able to trigger something that way. It'll take some time, but might prove fruitful.

That would be awesome. It's not like this this is burning or anything and one of the things in the long tail of things we need to do in this area.
Absolutely true.  In fact, I doubt this particular quirk is all that important in the extension removal space.  But we've got enough data to do a bit of an experiment.  While it takes a long time to run, it doesn't require any kind of regular human intervention.  Better to fire it off now while it's still fresh in our minds.  If we wait a week or two I'll have forgotten everything.

Just as a data-point, the SPEC QEMU icount on RISC-V with this patch seems promising (+ve is better, lesser icount)

Baseline        subreg promoted
                                                note preserved   %
benchmark       workload #
500.perlbench_r 0               1222524143251   1222717055541 -0.02%
                1               741422677286    740573609468 0.11%
                2               694157786227    693787219643 0.05%
502.gcc_r       0               189519277112    188986824061 0.28%  <--
                1               224763075520    224225499491 0.24%
                2               216802546093    216426186662 0.17%
                3               179634122120    179165923074 0.26%  <--
                4               222757886491    222343753217 0.19%
503.bwaves_r    0               309660270217    309640234863 0.01%
                1               488871452301    488838894844 0.01%
                2               381243468081    381218065515 0.01%
                3               463786236849    463756755469 0.01%
505.mcf_r       0               675010417323    675014630665 0.00%
507.cactuBSSN_r 0               2856874668987   2856874679135 0.00%
508.namd_r      0               1877527849689   1877508676900 0.00%
510.parest_r    0               3479719575579   3479104891751 0.02%
511.povray_r    0               3028749801452   3030037805612 -0.04%
519.lbm_r       0               1172421269180   1172421185445 0.00%
520.omnetpp_r   0               1014838628822   1007680353306 0.71%  <--
521.wrf_r       0               3897783090826   3897162379983 0.02%
523.xalancbmk_r 0               1062577057227   1062508198843 0.01%
525.x264_r      0               451836043634    449289002218 0.56%  <--
                1               1761617424590   1758009904369 0.20%  <--
                2               1686037465791   1682815274048 0.19%  <--
526.blender_r   0               1660559350538   1660534452552 0.00%
527.cam4_r      0               2141572063843   2141254936488 0.01%
531.deepsjeng_r 0               1605692153702   1603021256993 0.17%
538.imagick_r   0               3401602661013   3401602660827 0.00%
541.leela_r     0               1989286081019   1987365526160 0.10%
544.nab_r       0               1537038165879   1528865609530 0.53%  <--
548.exchange2_r 0               2050220774922   2048840906692 0.07%
549.fotonik3d_r 0               2231807908394   2231807600916 0.00%
554.roms_r      0               2612969430882   2611529873683 0.06%
557.xz_r        0               367967125022    367760820700 0.06%
                1               961163448926    961025548415 0.01%
                2               522156857947    521939109911 0.04%
997.specrand_fr 0               413618578       413604068 0.00%
999.specrand_ir 0               413618578       413604068 0.00%

Reply via email to