Comment by ckitching

I compiled your function with SCALE for gfx1030:

        .p2align        2                               ; -- Begin function _Z15ptx_thread_voteff
        .type   _Z15ptx_thread_voteff,@function
  _Z15ptx_thread_voteff:                  ; @_Z15ptx_thread_voteff
  ; %bb.0:                                ; %entry
        s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
        s_waitcnt_vscnt null, 0x0
        v_cmp_ge_f32_e32 vcc_lo, v0, v1
        s_cmp_eq_u32 vcc_lo, -1
        s_cselect_b32 s4, -1, 0
        v_cndmask_b32_e64 v0, 0, 1, s4
        s_setpc_b64 s[30:31]
  .Lfunc_end1:
        .size   _Z15ptx_thread_voteff, .Lfunc_end1-_Z15ptx_thread_voteff
                                        ; -- End function

What were the safety concerns you had? This code seems to be something like `return __all_sync(rSq >= rCritSq) ? 1 : 0`, right?