Make use of FST writer thread switchable at run-time.

Always build the FST libray with -DFST_WRITER_PARALLEL, iff VL_THREADED.
This supports run-time enablement of the FST writer thread, and has no
measurable performance impact on single threaded tracing but simplifies
the library build.

Note: the actual choice of using the fst writer thread is still compile
time, but can now be made run-time easily.

include/verilated_fst_c.cpp

@@ -28,7 +28,7 @@
 #include "verilated_fst_c.h"
 
 // GTKWave configuration
-#ifdef VL_TRACE_FST_WRITER_THREAD
+#ifdef VL_THREADED
 # define HAVE_LIBPTHREAD
 # define FST_WRITER_PARALLEL
 #endif
@@ -116,9 +116,7 @@ void VerilatedFst::open(const char* filename) VL_MT_SAFE_EXCLUDES(m_mutex) {
     m_fst = fstWriterCreate(filename, 1);
     fstWriterSetPackType(m_fst, FST_WR_PT_LZ4);
     fstWriterSetTimescaleFromString(m_fst, timeResStr().c_str());  // lintok-begin-on-ref
-#ifdef VL_TRACE_FST_WRITER_THREAD
-    fstWriterSetParallelMode(m_fst, 1);
-#endif
+    if (useFstWriterThread()) fstWriterSetParallelMode(m_fst, 1);
     fullDump(true);  // First dump must be full for fst
 
     m_curScope.clear();

include/verilated_fst_c.h

@@ -60,6 +60,14 @@ private:
     void declare(uint32_t code, const char* name, int dtypenum, fstVarDir vardir,
                  fstVarType vartype, bool array, int arraynum, bool bussed, int msb, int lsb);
 
+    static constexpr bool useFstWriterThread() {
+#ifdef VL_TRACE_FST_WRITER_THREAD
+        return true;
+#else
+        return false;
+#endif
+    }
+
 protected:
     //=========================================================================
     // Implementation of VerilatedTrace interface