Thomas, These two examples work in our in-house systems with the current drop. Let me test in JLSE to see if I can find what is going on. Carlos From: "Peterka, Thomas" <[email protected]> Date: Friday, November 15, 2019 at 8:34 AM To: "Rosales-fernandez, Carlos" <[email protected]> Cc: Ecp-aurora-sdk-discuss <[email protected]> Subject: Re: [Ecp-aurora-sdk-discuss] New A21 SDK coming to JLSE later today Hi Carlos, I think there may be something wrong with this latest drop, because SYCL code that used to work now crashes, and reverting to the old version version of dpcpp/2019.9.30.013b continues to work. Specifically, I see two problems: 1. My test of USM generates the following run time error: symbol lookup error: ./fixed: undefined symbol: _ZN2cl4sycl6detail3usm12alignedAllocEmmRKNS0_7contextENS0_3usm5allocE The code is this: auto dev = Queue.get_device(); auto ctxt = Queue.get_context(); sycl::usm_allocator<int, sycl::usm::alloc::host> alloc(ctxt, dev); std::vector<int, decltype(alloc)> n(alloc); n.resize(1); The last line, resize, is where the error occurs. The same problem happens if I give the size in the constructor and don’t call the resize. 2. The following trivial example generates a segmentation fault: sycl::queue Queue; sycl::buffer<sycl::cl_int, 1> Buffer(4); sycl::range<1> NumOfWorkItems{Buffer.get_count()}; Queue.submit([&](sycl::handler &cgh) { auto Accessor = Buffer.get_access<sycl::access::mode::write>(cgh); cgh.parallel_for<class FillBuffer>(NumOfWorkItems, [=](sycl::id<1> WIid) { Accessor[WIid] = (cl::sycl::cl_int)WIid.get(0); }); }); The seg fault happens in the parallel_for loop. Tom ----------------- Tom Peterka Mathematics and Computer Science Division Argonne National Laboratory 9700 S. Cass Ave. Lemont, IL 60439 Bldg 240, Rm 2148 e-mail: [email protected]<mailto:[email protected]> web: www.mcs.anl.gov/~tpeterka phone: 630-252-7198 On Nov 11, 2019, at 3:19 PM, Rosales-fernandez, Carlos via Ecp-aurora-sdk-discuss <[email protected]<mailto:[email protected]>> wrote: Hi all, Just a heads up that we will be pushing a new SDK around 9pm Central Time to JLSE. At that point if you have scripts using module names only ,without an explicit version, your default loads will shift to the new SDK version. Older versions will remain in the system as usual. A notice will go out at that time with a link to the release notes. Regards, Carlos -- Ecp-aurora-sdk-discuss mailing list [email protected]<mailto:[email protected]> https://lists.jlse.anl.gov/mailman/listinfo/ecp-aurora-sdk-discuss