Skip to content

feat(JLL): cuda API to get reg spills from compiled bin #1837

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
avik-pal merged 1 commit into from
Nov 8, 2025
Merged

feat(JLL): cuda API to get reg spills from compiled bin #1837

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions deps/ReactantExtra/API.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -824,6 +824,26 @@ REACTANT_ABI void ReactantCudaDeviceGetProperties(DeviceProperties *jlprops,
jlprops->maxThreadsPerMultiProcessor = props.maxThreadsPerMultiProcessor;
}

REACTANT_ABI void ReactantCudaGetRegsSpillsMaxThreadsFromBinary(
const char *binary, const char *fnname, int32_t *regs, int32_t *spills,
int32_t *maxThreads) {
CUfunction fun;
CUmodule mod;

ReactantHandleCuResult(cuModuleLoadData(&mod, binary));
ReactantHandleCuResult(cuModuleGetFunction(&fun, mod, fnname));

ReactantHandleCuResult(
cuFuncGetAttribute(regs, CU_FUNC_ATTRIBUTE_NUM_REGS, fun));
ReactantHandleCuResult(
cuFuncGetAttribute(spills, CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES, fun));
*spills /= 4;
ReactantHandleCuResult(cuFuncGetAttribute(
maxThreads, CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK, fun));

return;
}

#else

REACTANT_ABI int32_t ReactantCudaDriverGetVersion() { return 0; }
Expand All @@ -839,6 +859,10 @@ REACTANT_ABI int32_t ReactantCudaDeviceGetWarpSizeInThreads() { return 0; }
REACTANT_ABI void ReactantCudaDeviceGetProperties(DeviceProperties *jlprops,
int32_t device_id) {}

REACTANT_ABI void ReactantCudaGetRegsSpillsMaxThreadsFromBinary(
const char *binary, const char *fnname, int32_t *regs, int32_t *spills,
int32_t *maxThreads) {}

#endif

REACTANT_ABI void *UnsafeBufferPointer(PjRtBuffer *buffer) {
Expand Down
1 change: 1 addition & 0 deletions deps/ReactantExtra/BUILD
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -994,6 +994,7 @@ cc_library(
"-Wl,-exported_symbol,_ReactantCudaDeviceGetComputeCapalilityMinor",
"-Wl,-exported_symbol,_ReactantCudaDeviceGetWarpSizeInThreads",
"-Wl,-exported_symbol,_ReactantCudaDeviceGetProperties",
"-Wl,-exported_symbol,_ReactantCudaGetRegsSpillsMaxThreadsFromBinary",
"-Wl,-exported_symbol,_PjRtDeviceGetLocalDeviceId",
"-Wl,-exported_symbol,_PjRtDeviceGetGlobalDeviceId",
"-Wl,-exported_symbol,_PjRtDeviceGetLocalHardwareId",
Expand Down
Loading