================
@@ -29,17 +29,19 @@ static int is_uniform(uint64_t mask) {
// Wave-cooperative counter increment. The instrumentation pass emits calls to
// this in place of the default non-atomic load/add/store or atomicrmw
sequence.
-// The optional uniform counter allows calculating wave uniformity if present.
+// The uniform counter is optional; the wave counter records every wave visit.
COMPILER_RT_VISIBILITY void INSTR_PROF_INSTRUMENT_GPU_FUNC(uint64_t *counter,
uint64_t *uniform,
- uint64_t step) {
+ uint64_t step,
+ uint64_t *wave) {
uint64_t mask = __gpu_lane_mask();
if (__gpu_is_first_in_lane(mask)) {
__scoped_atomic_fetch_add(counter, step * __builtin_popcountg(mask),
__ATOMIC_RELAXED, __MEMORY_SCOPE_DEVICE);
if (uniform && is_uniform(mask))
__scoped_atomic_fetch_add(uniform, step * __builtin_popcountg(mask),
__ATOMIC_RELAXED, __MEMORY_SCOPE_DEVICE);
+ __scoped_atomic_fetch_add(wave, 1, __ATOMIC_RELAXED,
__MEMORY_SCOPE_DEVICE);
----------------
jhuber6 wrote:
Does this not need to use `step` at all? I'm a little hesitant to change the
format again for something that seems pretty minor. I've always wondered if we
could just change the uniformity to a count against full occupancy. I.e. we
know if we executed w/ full occupancy we'd have N, but we observed M. But I
don't r know what kind of optimizations PGO on HIP is enabling. What does this
extra information let us do?
https://github.com/llvm/llvm-project/pull/225589
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
