Re: [PATCH] Disable slp in loop vectorizer when cost model is very-cheap.

2021-08-23 Thread Richard Sandiford via Gcc-patches
liuhongt writes: > Performance impact for the commit with option: > -march=x86-64 -O2 -ftree-vectorize -fvect-cost-model=very-cheap > > SPEC2017 fprate > 503.bwaves_rBuildSame > 507.cactuBSSN_r -0.04 > 508.namd_r 0.14 > 510.parest_r-0.54 > 511.povray_r

[PATCH] Disable slp in loop vectorizer when cost model is very-cheap.

2021-08-22 Thread liuhongt via Gcc-patches
Performance impact for the commit with option: -march=x86-64 -O2 -ftree-vectorize -fvect-cost-model=very-cheap SPEC2017 fprate 503.bwaves_rBuildSame 507.cactuBSSN_r -0.04 508.namd_r 0.14 510.parest_r-0.54 511.povray_r 0.10 519.lbm_r B