Work around a CUPTI bug in CUDA 12.4 Update 1. (#2330)

src/compiler/reflection.jl

@@ -51,6 +51,16 @@ function code_sass(io::IO, job::CompilerJob; raw::Bool=false)
  return
  end
 
+ # NVIDIA bug #4604961: CUPTI in CUDA 12.4 Update 1 does not capture profiled events
+ # unless the activity API is first activated
+ if runtime_version() == v"12.4"
+ cfg = CUPTI.ActivityConfig([CUPTI.CUPTI_ACTIVITY_KIND_CONCURRENT_KERNEL,
+ CUPTI.CUPTI_ACTIVITY_KIND_INTERNAL_LAUNCH_API])
+ CUPTI.enable!(cfg) do
+ # do nothing
+ end
+ end
+
  cfg = CUPTI.CallbackConfig([CUPTI.CUPTI_CB_DOMAIN_RESOURCE]) do domain, id, data
  # only process relevant callbacks
  id == CUPTI.CUPTI_CBID_RESOURCE_MODULE_LOADED || return

test/core/execution.jl

@@ -77,7 +77,7 @@ end
  CUDA.code_warntype(devnull, dummy, Tuple{})
  CUDA.code_llvm(devnull, dummy, Tuple{})
  CUDA.code_ptx(devnull, dummy, Tuple{})
- if can_use_cupti() && CUDA.runtime_version() != v"12.4"
+ if can_use_cupti()
  # functions defined in Julia
  sass = sprint(io->CUDA.code_sass(io, dummy, Tuple{}))
  @test occursin(".text._Z5dummy", sass)
@@ -96,7 +96,7 @@ end
  @device_code_warntype io=devnull @cuda dummy()
  @device_code_llvm io=devnull @cuda dummy()
  @device_code_ptx io=devnull @cuda dummy()
- if can_use_cupti() && CUDA.runtime_version() != v"12.4"
+ if can_use_cupti()
  # functions defined in Julia
  sass = sprint(io->@device_code_sass io=io @cuda dummy())
  @test occursin(".text._Z5dummy", sass)
@@ -120,7 +120,7 @@ end
  @test occursin("dummy", sprint(io->(@device_code_llvm io=io optimize=false @cuda dummy())))
  @test occursin("dummy", sprint(io->(@device_code_llvm io=io @cuda dummy())))
  @test occursin("dummy", sprint(io->(@device_code_ptx io=io @cuda dummy())))
- if can_use_cupti() && CUDA.runtime_version() != v"12.4"
+ if can_use_cupti()
  @test occursin("dummy", sprint(io->(@device_code_sass io=io @cuda dummy())))
  end