[Clang] Pass correct lane mask for match helpers (#138693)

Summary:
We use the ballot to get the proper lane mask after we've masked off the
threads already done. This isn't an issue on AMDGPU but could cause
problems for post-Volta since it's saying that threads are active when
they aren't.

Author: jhuber6

clang/lib/Headers/gpuintrin.h

@@ -264,9 +264,10 @@ __gpu_match_any_u32_impl(uint64_t __lane_mask, uint32_t __x) {
   uint64_t __match_mask = 0;
 
   bool __done = 0;
-  while (__gpu_ballot(__lane_mask, !__done)) {
+  for (uint64_t __active_mask = __lane_mask; __active_mask;
+       __active_mask = __gpu_ballot(__lane_mask, !__done)) {
     if (!__done) {
-      uint32_t __first = __gpu_read_first_lane_u32(__lane_mask, __x);
+      uint32_t __first = __gpu_read_first_lane_u32(__active_mask, __x);
       if (__first == __x) {
         __match_mask = __gpu_lane_mask();
         __done = 1;
@@ -283,9 +284,10 @@ __gpu_match_any_u64_impl(uint64_t __lane_mask, uint64_t __x) {
   uint64_t __match_mask = 0;
 
   bool __done = 0;
-  while (__gpu_ballot(__lane_mask, !__done)) {
+  for (uint64_t __active_mask = __lane_mask; __active_mask;
+       __active_mask = __gpu_ballot(__lane_mask, !__done)) {
     if (!__done) {
-      uint64_t __first = __gpu_read_first_lane_u64(__lane_mask, __x);
+      uint64_t __first = __gpu_read_first_lane_u64(__active_mask, __x);
       if (__first == __x) {
         __match_mask = __gpu_lane_mask();
         __done = 1;