LLVM 18.0.0git
|
Analyzes if a function potentially memory bound and if a kernel kernel may benefit from limiting number of waves to reduce cache thrashing. More...
Go to the source code of this file.
Classes | |
struct | llvm::AMDGPUPerfHintAnalysis |
struct | llvm::AMDGPUPerfHintAnalysis::FuncInfo |
Namespaces | |
namespace | llvm |
This is an optimization pass for GlobalISel generic memory operations. | |
Analyzes if a function potentially memory bound and if a kernel kernel may benefit from limiting number of waves to reduce cache thrashing.
Definition in file AMDGPUPerfHintAnalysis.h.