|
flang链接上的信息大概是这些?
“configure:5802: *** Fortran compiler
configure:29064: checking for Fortran compiler version
configure:29073: flang --version >&5
AMD clang version 16.0.3 (CLANG: AOCC_4.2.0-Build#89 2023_12_13)”
“configure:29520: checking if Fortran compiler works
configure:29552: flang -o conftest conftest.f >&5
configure:29552: $? = 0
configure:29552: ./conftest
configure:29552: $? = 0
configure:29569: result: yes”
我这边测试的结果确实是oneAPI编译开启avx指令集后的vasp6.4.2速度远超aocc编译版本,郁闷中。。。现在怀疑我aocc编译漏了些参数,居然amd自己的U优化不过Intel、、、层主后续方便的话,可否提供测试算例的一些数据,我们也交流一下哪种编译速度更快的问题
|
|