[Clang] Fix GPU intrinsic helpers incorrectly sign extending (#129560)

Summary:
These return values are actually signed, meaning that casting will
extend it and then all the bits will be one.

(cherry picked from commit 4ca8ea8)

Author: jhuber6

clang/lib/Headers/amdgpuintrin.h

@@ -121,7 +121,7 @@ __gpu_read_first_lane_u64(uint64_t __lane_mask, uint64_t __x) {
   uint32_t __hi = (uint32_t)(__x >> 32ull);
   uint32_t __lo = (uint32_t)(__x & 0xFFFFFFFF);
   return ((uint64_t)__builtin_amdgcn_readfirstlane(__hi) << 32ull) |
-         ((uint64_t)__builtin_amdgcn_readfirstlane(__lo));
+         ((uint64_t)__builtin_amdgcn_readfirstlane(__lo) & 0xFFFFFFFF);
 }
 
 // Returns a bitmask of threads in the current lane for which \p x is true.

clang/lib/Headers/nvptxintrin.h

@@ -127,7 +127,8 @@ __gpu_read_first_lane_u64(uint64_t __lane_mask, uint64_t __x) {
                                              __gpu_num_lanes() - 1)
           << 32ull) |
          ((uint64_t)__nvvm_shfl_sync_idx_i32(__mask, __lo, __id,
-                                             __gpu_num_lanes() - 1));
+                                             __gpu_num_lanes() - 1) &
+          0xFFFFFFFF);
 }
 
 // Returns a bitmask of threads in the current lane for which \p x is true.