[PATCH] D52733: [OpenMP][NVPTX] Avoid data sharing if in parallel region

Hahnfeld added a comment. In https://reviews.llvm.org/D52733#1252966, @ABataev wrote: > In https://reviews.llvm.org/D52733#1252963, @Hahnfeld wrote: > > > In https://reviews.llvm.org/D52733#1251421, @ABataev wrote: > > > > > It might lead to increased register pressure, isn't it? Currently, I'm

[PATCH] D52733: [OpenMP][NVPTX] Avoid data sharing if in parallel region

ABataev added a comment. In https://reviews.llvm.org/D52733#1252963, @Hahnfeld wrote: > In https://reviews.llvm.org/D52733#1251421, @ABataev wrote: > > > It might lead to increased register pressure, isn't it? Currently, I'm > > trying to emit the code that can be optimized out and, thus, may de

[PATCH] D52733: [OpenMP][NVPTX] Avoid data sharing if in parallel region

Hahnfeld added a comment. In https://reviews.llvm.org/D52733#1251421, @ABataev wrote: > It might lead to increased register pressure, isn't it? Currently, I'm trying > to emit the code that can be optimized out and, thus, may decrease the > register pressure. That's why I tried to reduce the nu

[PATCH] D52733: [OpenMP][NVPTX] Avoid data sharing if in parallel region

ABataev added a comment. It might lead to increased register pressure, isn't it? Currently, I'm trying to emit the code that can be optimized out and, thus, may decrease the register pressure. That's why I tried to reduce the number of the runtime checks. Repository: rC Clang https://review

[PATCH] D52733: [OpenMP][NVPTX] Avoid data sharing if in parallel region

Hahnfeld created this revision. Hahnfeld added reviewers: gtbercea, ABataev. Herald added subscribers: cfe-commits, guansong, jholewinski. Previously the generated code only checked if the kernel is executing in SPMD mode. However a worker thread participating in a parallel region will never execu