[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

kovdan01 added a comment. In D120129#3410514 , @jdoerfert wrote: > Our internal build bots and CI for some projects are broken for 3 days. I > wish to unbreak them so we get actual meaningful results, e.g., see if > something else is breaking our build.

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. In D120129#3410512 , @kovdan01 wrote: > In D120129#3410510 , @jdoerfert > wrote: > >> The two assertions introduced here do not hold for the libdevice.bc above. >> So whenever we link

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

kovdan01 added a comment. In D120129#3410510 , @jdoerfert wrote: > The two assertions introduced here do not hold for the libdevice.bc above. So > whenever we link the above we will cause the assertions to fail. That's what > I mean with break. isKernel

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. In D120129#3410493 , @kovdan01 wrote: > In D120129#3410479 , @jdoerfert > wrote: > >> Please revert this commit. It breaks any code using the cuda.11.0.2 >> libdevice.bc file, the sour

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

kovdan01 added a comment. In D120129#3410479 , @jdoerfert wrote: > Please revert this commit. It breaks any code using the cuda.11.0.2 > libdevice.bc file, the source of the `null` `nvvm.annotations` and the > annotations with 5 arguments. See below. >

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert requested changes to this revision. jdoerfert added a comment. This revision now requires changes to proceed. Please revert this commit. It breaks any code using the cuda.11.0.2 libdevice.bc file, the source of the `null` `nvvm.annotations` and the annotations with 5 arguments. See bel

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. Here are the null pointers that cause the assertion: !nvvm.annotations = !{!8, !9, !8, !10, !10, !10, !10, !11, !11, !10} !8 = !{null, !"align", i32 8} !9 = !{null, !"align", i32 8, !"align", i32 65544, !"align", i32 131080} !10 = !{null, !"align", i32 16}

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. In D120129#3408174 , @kovdan01 wrote: > In D120129#3408168 , @jdoerfert > wrote: > >> You don't need to run it. If you use this command line it doesn't crash? > > Yes, I run the same co

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

kovdan01 added a comment. In D120129#3408168 , @jdoerfert wrote: > You don't need to run it. If you use this command line it doesn't crash? Yes, I run the same command (with sm_75 instead of sm_80 because I don't have libomptarget-nvptx-sm_80.bc), and i

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. In D120129#3408116 , @kovdan01 wrote: > In D120129#3408088 , @jdoerfert > wrote: > >> Godbold seems to not have included this: >> >> $ cat test.cpp >> int main(){return 0;} >> $ c

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

kovdan01 added a comment. In D120129#3408088 , @jdoerfert wrote: > Godbold seems to not have included this: > > $ cat test.cpp > int main(){return 0;} > $ clang++ -fopenmp -fopenmp-targets=nvptx64 -Xopenmp-target -march=sm_80 > test.cpp > ... sta

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert added a comment. Godbold seems to not have included this: $ cat test.cpp int main(){return 0;} $ clang++ -fopenmp -fopenmp-targets=nvptx64 -Xopenmp-target -march=sm_80 test.cpp ... static bool llvm::isa_impl_cl::doit(const From *) [To = llvm::ConstantAsMetadata, From = const l

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

jdoerfert reopened this revision. jdoerfert added a comment. This revision is now accepted and ready to land. Our internal CI flagged an assertion in `llvm::NVPTXTargetLowering::getFunctionParamOptimizedAlign(llvm::Function const*, llvm::Type*, llvm::DataLayout const&)` last night. Given the er

[PATCH] D120129: [NVPTX] Enhance vectorization of ld.param & st.param

This revision was landed with ongoing or failed builds. This revision was automatically updated to reflect the committed changes. kovdan01 marked 2 inline comments as done. Closed by commit rG828b63c30943: [NVPTX] Enhance vectorization of ld.param & st.param (authored by kovdan01). Herald added a