diff --git a/Makefile.in b/Makefile.in
index a8dd0a7fa..63d040be4 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -322,7 +322,7 @@ CPPCHECK_INC = -I$(srcdir)/include -I$(srcdir)/src/obj_dbg -I$(srcdir)/src
 
 cppcheck: $(CPPCHECK_DEP)
 %.cppcheck: %.cpp
-	$(CPPCHECK) $(CPPCHECK_FLAGS) -DVL_DEBUG=1 -DVL_CPPCHECK=1 -DVL_THREADED=1 $(CPPCHECK_INC) $<
+	$(CPPCHECK) $(CPPCHECK_FLAGS) -DVL_DEBUG=1 -DVL_CPPCHECK=1 $(CPPCHECK_INC) $<
 
 CLANGTIDY = clang-tidy
 CLANGTIDY_FLAGS = -config='' \
@@ -330,7 +330,7 @@ CLANGTIDY_FLAGS = -config='' \
 	-checks='-fuchsia-*,-cppcoreguidelines-avoid-c-arrays,-cppcoreguidelines-init-variables,-cppcoreguidelines-avoid-goto,-modernize-avoid-c-arrays,-readability-magic-numbers,-readability-simplify-boolean-expr,-cppcoreguidelines-macro-usage' \
 
 CLANGTIDY_DEP = $(subst .cpp,.cpp.tidy,$(CPPCHECK_CPP))
-CLANGTIDY_DEFS = -DVL_DEBUG=1 -DVL_THREADED=1 -DVL_CPPCHECK=1
+CLANGTIDY_DEFS = -DVL_DEBUG=1 -DVL_CPPCHECK=1
 
 clang-tidy: $(CLANGTIDY_DEP)
 %.cpp.tidy: %.cpp
diff --git a/docs/guide/exe_verilator.rst b/docs/guide/exe_verilator.rst
index bae014be9..35b589351 100644
--- a/docs/guide/exe_verilator.rst
+++ b/docs/guide/exe_verilator.rst
@@ -1213,15 +1213,18 @@ Summary:
 
 .. option:: --threads <threads>
 
-.. option:: --no-threads
-
-   With "--threads 0" or "--no-threads", the default, the generated model
-   is not thread safe. With "--threads 1", the generated model is single
-   threaded but may run in a multithreaded environment. With "--threads N",
+   With "--threads 1", the default, the generated model is single threaded
+   but may run in a multithreaded environment. With "--threads N",
    where N >= 2, the model is generated to run multithreaded on up to N
    threads. See :ref:`Multithreading`. This option also applies to
    :vlopt:`--trace` (but not :vlopt:`--trace-fst`).
 
+.. option:: --no-threads
+
+   Deprecated and has no effect (ignored).
+
+   In versions prior to 5.004, created a model which was not thread safe.
+
 .. option:: --threads-dpi all
 
 .. option:: --threads-dpi none
diff --git a/docs/guide/verilating.rst b/docs/guide/verilating.rst
index 3921a1964..f041097d2 100644
--- a/docs/guide/verilating.rst
+++ b/docs/guide/verilating.rst
@@ -183,11 +183,6 @@ Multithreading
 
 Verilator supports multithreaded simulation models.
 
-With :vlopt:`--no-threads`, the default, the model is not thread safe, and
-any use of more than one thread calling into one or even different
-Verilated models may result in unpredictable behavior. This gives the
-highest single thread performance.
-
 With :vlopt:`--threads 1 <--threads>`, the generated model is single
 threaded, however the support libraries are multithread safe. This allows
 different instantiations of model(s) to potentially each be run under a
@@ -203,13 +198,6 @@ oversubscription, the Verilated model should not livelock nor deadlock,
 however, you can expect performance to be far worse than it would be with
 proper ratio of threads and CPU cores.
 
-The remainder of this section describe behavior with :vlopt:`--threads 1
-<--threads>` or :vlopt:`--threads {N} <--threads>` (not
-:vlopt:`--no-threads`).
-
-:code:`VL_THREADED` is defined in the C++ code when compiling a threaded
-Verilated module, causing the Verilated support classes become threadsafe.
-
 The thread used for constructing a model must be the same thread that calls
 :code:`eval()` into the model, this is called the "eval thread". The thread
 used to perform certain global operations such as saving and tracing must
diff --git a/docs/verilated.dox b/docs/verilated.dox
index 5af927ba6..67841f4b1 100644
--- a/docs/verilated.dox
+++ b/docs/verilated.dox
@@ -37,5 +37,4 @@ PREDEFINED             = \
                          "VL_NOT_FINAL=" \
                          "VL_PURE=" \
                          "VL_REQUIRES()=" \
-                         "VL_THREAD_LOCAL=" \
                          "__restrict=" \
diff --git a/include/verilated.cpp b/include/verilated.cpp
index 0d0d1a5c8..148c5b459 100644
--- a/include/verilated.cpp
+++ b/include/verilated.cpp
@@ -27,7 +27,7 @@
 //
 // verilated.o may exist both in --lib-create (incrementally linked .a/.so)
 // and the main module.  Both refer the same instance of static
-// variables/VL_THREAD_LOCAL in verilated.o such as Verilated, or
+// variables/thread_local in verilated.o such as Verilated, or
 // VerilatedImpData.  This is important to share that state, but the
 // sharing may cause a double-free error when shutting down because the
 // loader will insert a constructor/destructor at each reference to
@@ -68,9 +68,7 @@
 # include <direct.h>  // mkdir
 #endif
 
-#ifdef VL_THREADED
-# include "verilated_threads.h"
-#endif
+#include "verilated_threads.h"
 // clang-format on
 
 #include "verilated_trace.h"
@@ -96,7 +94,7 @@ VerilatedContext* Verilated::s_lastContextp = nullptr;
 
 // Keep below together in one cache line
 // Internal note: Globals may multi-construct, see verilated.cpp top.
-VL_THREAD_LOCAL Verilated::ThreadLocal Verilated::t_s;
+thread_local Verilated::ThreadLocal Verilated::t_s;
 
 //===========================================================================
 // User definable functions
@@ -193,43 +191,27 @@ void vl_warn(const char* filename, int linenum, const char* hier, const char* ms
 // Wrapper to call certain functions via messages when multithreaded
 
 void VL_FINISH_MT(const char* filename, int linenum, const char* hier) VL_MT_SAFE {
-#ifdef VL_THREADED
     VerilatedThreadMsgQueue::post(VerilatedMsg{[=]() {  //
         vl_finish(filename, linenum, hier);
     }});
-#else
-    vl_finish(filename, linenum, hier);
-#endif
 }
 
 void VL_STOP_MT(const char* filename, int linenum, const char* hier, bool maybe) VL_MT_SAFE {
-#ifdef VL_THREADED
     VerilatedThreadMsgQueue::post(VerilatedMsg{[=]() {  //
         vl_stop_maybe(filename, linenum, hier, maybe);
     }});
-#else
-    vl_stop_maybe(filename, linenum, hier, maybe);
-#endif
 }
 
 void VL_FATAL_MT(const char* filename, int linenum, const char* hier, const char* msg) VL_MT_SAFE {
-#ifdef VL_THREADED
     VerilatedThreadMsgQueue::post(VerilatedMsg{[=]() {  //
         vl_fatal(filename, linenum, hier, msg);
     }});
-#else
-    vl_fatal(filename, linenum, hier, msg);
-#endif
 }
 
 void VL_WARN_MT(const char* filename, int linenum, const char* hier, const char* msg) VL_MT_SAFE {
-#ifdef VL_THREADED
     VerilatedThreadMsgQueue::post(VerilatedMsg{[=]() {  //
         vl_warn(filename, linenum, hier, msg);
     }});
-#else
-    vl_warn(filename, linenum, hier, msg);
-#endif
 }
 
 //===========================================================================
@@ -252,24 +234,16 @@ std::string _vl_string_vprintf(const char* formatp, va_list ap) VL_MT_SAFE {
 }
 
 uint64_t _vl_dbg_sequence_number() VL_MT_SAFE {
-#ifdef VL_THREADED
     static std::atomic<uint64_t> sequence;
-#else
-    static uint64_t sequence = 0;
-#endif
     return ++sequence;
 }
 
 uint32_t VL_THREAD_ID() VL_MT_SAFE {
-#ifdef VL_THREADED
     // Alternative is to use std::this_thread::get_id, but that returns a
     // hard-to-read number and is very slow
     static std::atomic<uint32_t> s_nextId(0);
-    static VL_THREAD_LOCAL uint32_t t_myId = ++s_nextId;
+    static thread_local uint32_t t_myId = ++s_nextId;
     return t_myId;
-#else
-    return 0;
-#endif
 }
 
 void VL_DBG_MSGF(const char* formatp, ...) VL_MT_SAFE {
@@ -288,7 +262,6 @@ void VL_DBG_MSGF(const char* formatp, ...) VL_MT_SAFE {
     VL_PRINTF("-V{t%u,%" PRIu64 "}%s", VL_THREAD_ID(), _vl_dbg_sequence_number(), out.c_str());
 }
 
-#ifdef VL_THREADED
 void VL_PRINTF_MT(const char* formatp, ...) VL_MT_SAFE {
     va_list ap;
     va_start(ap, formatp);
@@ -298,7 +271,6 @@ void VL_PRINTF_MT(const char* formatp, ...) VL_MT_SAFE {
         VL_PRINTF("%s", out.c_str());
     }});
 }
-#endif
 
 //===========================================================================
 // Random -- Mostly called at init time, so not inline.
@@ -317,8 +289,8 @@ static uint32_t vl_sys_rand32() VL_MT_UNSAFE {
 }
 
 uint64_t vl_rand64() VL_MT_SAFE {
-    static VL_THREAD_LOCAL uint64_t t_state[2];
-    static VL_THREAD_LOCAL uint32_t t_seedEpoch = 0;
+    static thread_local uint64_t t_state[2];
+    static thread_local uint32_t t_seedEpoch = 0;
     // For speed, we use a thread-local epoch number to know when to reseed
     // A thread always belongs to a single context, so this works out ok
     if (VL_UNLIKELY(t_seedEpoch != VerilatedContextImp::randSeedEpoch())) {
@@ -762,7 +734,7 @@ void _vl_vsformat(std::string& output, const char* formatp, va_list ap) VL_MT_SA
     // Note uses a single buffer internally; presumes only one usage per printf
     // Note also assumes variables < 64 are not wide, this assumption is
     // sometimes not true in low-level routines written here in verilated.cpp
-    static VL_THREAD_LOCAL char t_tmp[VL_VALUE_STRING_MAX_WIDTH];
+    static thread_local char t_tmp[VL_VALUE_STRING_MAX_WIDTH];
     const char* pctp = nullptr;  // Most recent %##.##g format
     bool inPct = false;
     bool widthSet = false;
@@ -1160,7 +1132,7 @@ IData _vl_vsscanf(FILE* fp,  // If a fscanf
     // Read a Verilog $sscanf/$fscanf style format into the output list
     // The format must be pre-processed (and lower cased) by Verilator
     // Arguments are in "width, arg-value (or WDataIn* if wide)" form
-    static VL_THREAD_LOCAL char t_tmp[VL_VALUE_STRING_MAX_WIDTH];
+    static thread_local char t_tmp[VL_VALUE_STRING_MAX_WIDTH];
     int floc = fbits - 1;
     IData got = 0;
     bool inPct = false;
@@ -1453,7 +1425,7 @@ void VL_FCLOSE_I(IData fdi) VL_MT_SAFE {
 }
 
 void VL_SFORMAT_X(int obits, CData& destr, const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1464,7 +1436,7 @@ void VL_SFORMAT_X(int obits, CData& destr, const char* formatp, ...) VL_MT_SAFE
 }
 
 void VL_SFORMAT_X(int obits, SData& destr, const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1475,7 +1447,7 @@ void VL_SFORMAT_X(int obits, SData& destr, const char* formatp, ...) VL_MT_SAFE
 }
 
 void VL_SFORMAT_X(int obits, IData& destr, const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1486,7 +1458,7 @@ void VL_SFORMAT_X(int obits, IData& destr, const char* formatp, ...) VL_MT_SAFE
 }
 
 void VL_SFORMAT_X(int obits, QData& destr, const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1497,7 +1469,7 @@ void VL_SFORMAT_X(int obits, QData& destr, const char* formatp, ...) VL_MT_SAFE
 }
 
 void VL_SFORMAT_X(int obits, void* destp, const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1518,7 +1490,7 @@ void VL_SFORMAT_X(int obits_ignored, std::string& output, const char* formatp, .
 }
 
 std::string VL_SFORMATF_NX(const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1529,7 +1501,7 @@ std::string VL_SFORMATF_NX(const char* formatp, ...) VL_MT_SAFE {
 }
 
 void VL_WRITEF(const char* formatp, ...) VL_MT_SAFE {
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
     va_list ap;
     va_start(ap, formatp);
@@ -1541,7 +1513,7 @@ void VL_WRITEF(const char* formatp, ...) VL_MT_SAFE {
 
 void VL_FWRITEF(IData fpi, const char* formatp, ...) VL_MT_SAFE {
     // While threadsafe, each thread can only access different file handles
-    static VL_THREAD_LOCAL std::string t_output;  // static only for speed
+    static thread_local std::string t_output;  // static only for speed
     t_output = "";
 
     va_list ap;
@@ -1771,7 +1743,7 @@ IData VL_VALUEPLUSARGS_INN(int, const std::string& ld, std::string& rdr) VL_MT_S
 
 const char* vl_mc_scan_plusargs(const char* prefixp) VL_MT_SAFE {
     const std::string& match = Verilated::threadContextp()->impp()->argPlusMatch(prefixp);
-    static VL_THREAD_LOCAL char t_outstr[VL_VALUE_STRING_MAX_WIDTH];
+    static thread_local char t_outstr[VL_VALUE_STRING_MAX_WIDTH];
     if (match.empty()) return nullptr;
     char* dp = t_outstr;
     for (const char* sp = match.c_str() + std::strlen(prefixp) + 1;  // +1 to skip the "+"
@@ -1865,7 +1837,7 @@ IData VL_ATOI_N(const std::string& str, int base) VL_PURE {
 static const char* memhFormat(int nBits) {
     assert((nBits >= 1) && (nBits <= 32));
 
-    static VL_THREAD_LOCAL char t_buf[32];
+    static thread_local char t_buf[32];
     switch ((nBits - 1) / 4) {
     case 0: VL_SNPRINTF(t_buf, 32, "%%01x"); break;
     case 1: VL_SNPRINTF(t_buf, 32, "%%02x"); break;
@@ -1883,7 +1855,7 @@ static const char* memhFormat(int nBits) {
 static const char* formatBinary(int nBits, uint32_t bits) {
     assert((nBits >= 1) && (nBits <= 32));
 
-    static VL_THREAD_LOCAL char t_buf[64];
+    static thread_local char t_buf[64];
     for (int i = 0; i < nBits; i++) {
         const bool isOne = bits & (1 << (nBits - 1 - i));
         t_buf[i] = (isOne ? '1' : '0');
@@ -2474,7 +2446,6 @@ void VerilatedContext::threads(unsigned n) {
             "%Error: Cannot set simulation threads after the thread pool has been created.");
     }
 
-#if VL_THREADED
     if (m_threads == n) return;  // To avoid unnecessary warnings
     m_threads = n;
     const unsigned hardwareThreadsAvailable = std::thread::hardware_concurrency();
@@ -2483,13 +2454,6 @@ void VerilatedContext::threads(unsigned n) {
                      "to %u. This will likely cause significant slowdown.\n",
                      hardwareThreadsAvailable, m_threads);
     }
-#else
-    if (n > 1) {
-        VL_PRINTF_MT("%%Warning: Verilator run-time library built without VL_THREADS. Ignoring "
-                     "call to 'VerilatedContext::threads' with argument %u.\n",
-                     n);
-    }
-#endif
 }
 
 void VerilatedContext::commandArgs(int argc, const char** argv) VL_MT_SAFE_EXCLUDES(m_argMutex) {
@@ -2505,7 +2469,7 @@ void VerilatedContext::commandArgsAdd(int argc, const char** argv)
 const char* VerilatedContext::commandArgsPlusMatch(const char* prefixp)
     VL_MT_SAFE_EXCLUDES(m_argMutex) {
     const std::string& match = impp()->argPlusMatch(prefixp);
-    static VL_THREAD_LOCAL char t_outstr[VL_VALUE_STRING_MAX_WIDTH];
+    static thread_local char t_outstr[VL_VALUE_STRING_MAX_WIDTH];
     if (match.empty()) return "";
     char* dp = t_outstr;
     for (const char* sp = match.c_str(); *sp && (dp - t_outstr) < (VL_VALUE_STRING_MAX_WIDTH - 2);)
@@ -2537,9 +2501,7 @@ void VerilatedContext::addModel(VerilatedModel* modelp) {
 
 VerilatedVirtualBase* VerilatedContext::threadPoolp() {
     if (m_threads == 1) return nullptr;
-#if VL_THREADED
     if (!m_threadPool) m_threadPool.reset(new VlThreadPool{this, m_threads - 1});
-#endif
     return m_threadPool.get();
 }
 
@@ -2701,9 +2663,7 @@ void VerilatedContext::randSeed(int val) VL_MT_SAFE {
     m_s.m_randSeed = val;
     const uint64_t newEpoch = VerilatedContextImp::s().s_randSeedEpoch + 1;
     // Obververs must see new epoch AFTER seed updated
-#ifdef VL_THREADED
     std::atomic_signal_fence(std::memory_order_release);
-#endif
     VerilatedContextImp::s().s_randSeedEpoch = newEpoch;
 }
 uint64_t VerilatedContextImp::randSeedDefault64() const VL_MT_SAFE {
@@ -2760,16 +2720,12 @@ VerilatedSyms::VerilatedSyms(VerilatedContext* contextp)
     : _vm_contextp__(contextp ? contextp : Verilated::threadContextp()) {
     VerilatedContext::checkMagic(_vm_contextp__);
     Verilated::threadContextp(_vm_contextp__);
-#ifdef VL_THREADED
     __Vm_evalMsgQp = new VerilatedEvalMsgQueue;
-#endif
 }
 
 VerilatedSyms::~VerilatedSyms() {
     VerilatedContext::checkMagic(_vm_contextp__);
-#ifdef VL_THREADED
     delete __Vm_evalMsgQp;
-#endif
 }
 
 //===========================================================================
@@ -2791,8 +2747,8 @@ void Verilated::debug(int level) VL_MT_SAFE {
 
 const char* Verilated::catName(const char* n1, const char* n2, const char* delimiter) VL_MT_SAFE {
     // Used by symbol table creation to make module names
-    static VL_THREAD_LOCAL char* t_strp = nullptr;
-    static VL_THREAD_LOCAL size_t t_len = 0;
+    static thread_local char* t_strp = nullptr;
+    static thread_local size_t t_len = 0;
     const size_t newlen = std::strlen(n1) + std::strlen(n2) + std::strlen(delimiter) + 1;
     if (VL_UNLIKELY(!t_strp || newlen > t_len)) {
         if (t_strp) delete[] t_strp;
@@ -2843,11 +2799,7 @@ void Verilated::removeFlushCb(VoidPCb cb, void* datap) VL_MT_SAFE {
 }
 void Verilated::runFlushCallbacks() VL_MT_SAFE {
     // Flush routines may call flush, so avoid mutex deadlock
-#ifdef VL_THREADED
     static std::atomic<int> s_recursing;
-#else
-    static int s_recursing = 0;
-#endif
     if (!s_recursing++) {
         const VerilatedLockGuard lock{VlCbStatic.s_flushMutex};
         runCallbacks(VlCbStatic.s_flushCbs);
@@ -2870,11 +2822,7 @@ void Verilated::removeExitCb(VoidPCb cb, void* datap) VL_MT_SAFE {
     removeCb(cb, datap, VlCbStatic.s_exitCbs);
 }
 void Verilated::runExitCallbacks() VL_MT_SAFE {
-#ifdef VL_THREADED
     static std::atomic<int> s_recursing;
-#else
-    static int s_recursing = 0;
-#endif
     if (!s_recursing++) {
         const VerilatedLockGuard lock{VlCbStatic.s_exitMutex};
         runCallbacks(VlCbStatic.s_exitCbs);
@@ -2908,17 +2856,14 @@ void Verilated::mkdir(const char* dirname) VL_MT_UNSAFE {
 }
 
 void Verilated::quiesce() VL_MT_SAFE {
-#ifdef VL_THREADED
     // Wait until all threads under this evaluation are quiet
     // THREADED-TODO
-#endif
 }
 
 int Verilated::exportFuncNum(const char* namep) VL_MT_SAFE {
     return VerilatedImp::exportFind(namep);
 }
 
-#ifdef VL_THREADED
 void Verilated::endOfThreadMTaskGuts(VerilatedEvalMsgQueue* evalMsgQp) VL_MT_SAFE {
     VL_DEBUG_IF(VL_DBG_MSGF("End of thread mtask\n"););
     VerilatedThreadMsgQueue::flush(evalMsgQp);
@@ -2932,7 +2877,6 @@ void Verilated::endOfEval(VerilatedEvalMsgQueue* evalMsgQp) VL_MT_SAFE {
     VL_DEBUG_IF(VL_DBG_MSGF("End-of-eval cleanup\n"););
     evalMsgQp->process();
 }
-#endif
 
 //===========================================================================
 // VerilatedImp:: Methods
@@ -3138,7 +3082,7 @@ void VerilatedHierarchy::remove(VerilatedScope* fromp, VerilatedScope* top) {
 //===========================================================================
 // VerilatedOneThreaded:: Methods
 
-#if defined(VL_THREADED) && defined(VL_DEBUG)
+#ifdef VL_DEBUG
 void VerilatedAssertOneThread::fatal_different() VL_MT_SAFE {
     VL_FATAL_MT(__FILE__, __LINE__, "",
                 "Routine called that is single threaded, but called from"
diff --git a/include/verilated.h b/include/verilated.h
index 66ae6017b..e07c8f878 100644
--- a/include/verilated.h
+++ b/include/verilated.h
@@ -54,11 +54,9 @@
 #include <unordered_set>
 #include <vector>
 // <iostream> avoided to reduce compile time
-#ifdef VL_THREADED
-# include <atomic>
-# include <mutex>
-# include <thread>
-#endif
+#include <atomic>
+#include <mutex>
+#include <thread>
 
 // Allow user to specify their own include file
 #ifdef VL_VERILATED_INCLUDE
@@ -149,8 +147,6 @@ enum VerilatedVarFlags {
 // Return current thread ID (or 0), not super fast, cache if needed
 extern uint32_t VL_THREAD_ID() VL_MT_SAFE;
 
-#if VL_THREADED
-
 #define VL_LOCK_SPINS 50000  /// Number of times to spin for a mutex before yielding
 
 /// Mutex, wrapped to allow -fthread_safety checks
@@ -202,34 +198,12 @@ public:
     void unlock() VL_RELEASE() VL_MT_SAFE { m_mutexr.unlock(); }
 };
 
-#else  // !VL_THREADED
-
-// Empty non-threaded mutex to avoid #ifdefs in consuming code
-class VerilatedMutex final {
-public:
-    void lock() {}  // LCOV_EXCL_LINE
-    void unlock() {}  // LCOV_EXCL_LINE
-};
-
-// Empty non-threaded lock guard to avoid #ifdefs in consuming code
-class VerilatedLockGuard final {
-    VL_UNCOPYABLE(VerilatedLockGuard);
-
-public:
-    explicit VerilatedLockGuard(VerilatedMutex&) {}
-    ~VerilatedLockGuard() = default;
-    void lock() {}  // LCOV_EXCL_LINE
-    void unlock() {}  // LCOV_EXCL_LINE
-};
-
-#endif  // VL_THREADED
-
 // Internals: Remember the calling thread at construction time, and make
 // sure later calls use same thread
 
 class VerilatedAssertOneThread final {
     // MEMBERS
-#if defined(VL_THREADED) && defined(VL_DEBUG)
+#ifdef VL_DEBUG
     uint32_t m_threadid;  // Thread that is legal
 public:
     // CONSTRUCTORS
@@ -250,7 +224,7 @@ public:
         }
     }
     static void fatal_different() VL_MT_SAFE;
-#else  // !VL_THREADED || !VL_DEBUG
+#else  // !VL_DEBUG
 public:
     void check() {}
 #endif
@@ -343,7 +317,7 @@ class VerilatedContext VL_NOT_FINAL {
 protected:
     // MEMBERS
     // Slow path variables
-    mutable VerilatedMutex m_mutex;  // Mutex for most s_s/s_ns members, when VL_THREADED
+    mutable VerilatedMutex m_mutex;  // Mutex for most s_s/s_ns members
 
     struct Serialized {  // All these members serialized/deserialized
         // No std::strings or pointers or will serialize badly!
@@ -397,11 +371,7 @@ protected:
     // Implementation details
     const std::unique_ptr<VerilatedContextImpData> m_impdatap;
     // Number of threads to use for simulation (size of m_threadPool + 1 for main thread)
-#ifdef VL_THREADED
     unsigned m_threads = std::thread::hardware_concurrency();
-#else
-    const unsigned m_threads = 1;
-#endif
     // The thread pool shared by all models added to this context
     std::unique_ptr<VerilatedVirtualBase> m_threadPool;
     // The execution profiler shared by all models added to this context
@@ -611,9 +581,7 @@ public:  // But for internal use only
     // MEMBERS
     // Keep first so is at zero offset for fastest code
     VerilatedContext* const _vm_contextp__;  // Context for current model
-#ifdef VL_THREADED
     VerilatedEvalMsgQueue* __Vm_evalMsgQp;
-#endif
     explicit VerilatedSyms(VerilatedContext* contextp);  // Pass null for default context
     ~VerilatedSyms();
 };
@@ -694,17 +662,15 @@ class Verilated final {
     static VerilatedContext* s_lastContextp;  // Last context constructed/attached
 
     // Not covered by mutex, as per-thread
-    static VL_THREAD_LOCAL struct ThreadLocal {
+    static thread_local struct ThreadLocal {
         // No non-POD objects here due to this:
         // Internal note: Globals may multi-construct, see verilated.cpp top.
 
         // Fast path
         VerilatedContext* t_contextp = nullptr;  // Thread's context
-#ifdef VL_THREADED
         uint32_t t_mtaskId = 0;  // mtask# executing on this thread
         // Messages maybe pending on thread, needs end-of-eval calls
         uint32_t t_endOfEvalReqd = 0;
-#endif
         const VerilatedScope* t_dpiScopep = nullptr;  // DPI context scope
         const char* t_dpiFilename = nullptr;  // DPI context filename
         int t_dpiLineno = 0;  // DPI context line number
@@ -911,7 +877,6 @@ public:
     static int dpiLineno() VL_MT_SAFE { return t_s.t_dpiLineno; }
     static int exportFuncNum(const char* namep) VL_MT_SAFE;
 
-#ifdef VL_THREADED
     // Internal: Set the mtaskId, called when an mtask starts
     // Per thread, so no need to be in VerilatedContext
     static void mtaskId(uint32_t id) VL_MT_SAFE { t_s.t_mtaskId = id; }
@@ -925,12 +890,9 @@ public:
     }
     // Internal: Called at end of eval loop
     static void endOfEval(VerilatedEvalMsgQueue* evalMsgQp) VL_MT_SAFE;
-#endif
 
 private:
-#ifdef VL_THREADED
     static void endOfThreadMTaskGuts(VerilatedEvalMsgQueue* evalMsgQp) VL_MT_SAFE;
-#endif
 };
 
 void VerilatedContext::debug(int val) VL_MT_SAFE { Verilated::debug(val); }
diff --git a/include/verilated.mk.in b/include/verilated.mk.in
index b01799dfb..9dcff5121 100644
--- a/include/verilated.mk.in
+++ b/include/verilated.mk.in
@@ -130,19 +130,8 @@ endif
 #######################################################################
 ##### Threaded builds
 
-ifneq ($(VM_C11),0)
- ifneq ($(VM_C11),)
-  VK_C11=1
- endif
-endif
-
-ifneq ($(VM_THREADS),0)
- ifneq ($(VM_THREADS),)
-  CPPFLAGS += -DVL_THREADED
-  VK_C11=1
-  VK_LIBS_THREADED=1
- endif
-endif
+CPPFLAGS += $(CFG_CXXFLAGS_STD_NEWEST)
+LDLIBS += $(CFG_LDLIBS_THREADS)
 
 ifneq ($(VM_TIMING),0)
  ifneq ($(VM_TIMING),)
@@ -150,18 +139,6 @@ ifneq ($(VM_TIMING),0)
  endif
 endif
 
-ifneq ($(VK_C11),0)
- ifneq ($(VK_C11),)
-  # Need C++11 at least, so always default to newest
-  CPPFLAGS += $(CFG_CXXFLAGS_STD_NEWEST)
- endif
-endif
-
-ifneq ($(VK_LIBS_THREADED),0)
- ifneq ($(VK_LIBS_THREADED),)
-  LDLIBS += $(CFG_LDLIBS_THREADS)
- endif
-endif
 
 #######################################################################
 ### Aggregates
diff --git a/include/verilated_fst_c.cpp b/include/verilated_fst_c.cpp
index ad3de6c26..1247b46ed 100644
--- a/include/verilated_fst_c.cpp
+++ b/include/verilated_fst_c.cpp
@@ -28,10 +28,8 @@
 #include "verilated_fst_c.h"
 
 // GTKWave configuration
-#ifdef VL_THREADED
-# define HAVE_LIBPTHREAD
-# define FST_WRITER_PARALLEL
-#endif
+#define HAVE_LIBPTHREAD
+#define FST_WRITER_PARALLEL
 
 // Include the GTKWave implementation directly
 #define FST_CONFIG_INCLUDE "fst_config.h"
@@ -248,14 +246,11 @@ void VerilatedFst::declDouble(uint32_t code, const char* name, int dtypenum, fst
 // Get/commit trace buffer
 
 VerilatedFst::Buffer* VerilatedFst::getTraceBuffer() {
-#ifdef VL_THREADED
     if (offload()) return new OffloadBuffer{*this};
-#endif
     return new Buffer{*this};
 }
 
 void VerilatedFst::commitTraceBuffer(VerilatedFst::Buffer* bufp) {
-#ifdef VL_THREADED
     if (offload()) {
         OffloadBuffer* const offloadBufferp = static_cast<OffloadBuffer*>(bufp);
         if (offloadBufferp->m_offloadBufferWritep) {
@@ -263,7 +258,6 @@ void VerilatedFst::commitTraceBuffer(VerilatedFst::Buffer* bufp) {
             return;  // Buffer will be deleted by the offload thread
         }
     }
-#endif
     delete bufp;
 }
 
diff --git a/include/verilated_funcs.h b/include/verilated_funcs.h
index 1733d33d4..c226426d8 100644
--- a/include/verilated_funcs.h
+++ b/include/verilated_funcs.h
@@ -73,11 +73,7 @@ extern void VL_WARN_MT(const char* filename, int linenum, const char* hier,
 
 // clang-format off
 /// Print a string, multithread safe. Eventually VL_PRINTF will get called.
-#ifdef VL_THREADED
 extern void VL_PRINTF_MT(const char* formatp, ...) VL_ATTR_PRINTF(1) VL_MT_SAFE;
-#else
-# define VL_PRINTF_MT VL_PRINTF  // The following parens will take care of themselves
-#endif
 // clang-format on
 
 /// Print a debug message from internals with standard prefix, with printf style format
diff --git a/include/verilated_imp.h b/include/verilated_imp.h
index cc1971d04..afc3d01c8 100644
--- a/include/verilated_imp.h
+++ b/include/verilated_imp.h
@@ -41,10 +41,8 @@
 #include <string>
 #include <utility>
 #include <vector>
-#ifdef VL_THREADED
-# include <functional>
-# include <queue>
-#endif
+#include <functional>
+#include <queue>
 // clang-format on
 
 class VerilatedScope;
@@ -52,7 +50,6 @@ class VerilatedScope;
 //======================================================================
 // Threaded message passing
 
-#ifdef VL_THREADED
 // Message, enqueued on an mtask, and consumed on the main eval thread
 class VerilatedMsg final {
 public:
@@ -152,7 +149,7 @@ private:
     VL_UNCOPYABLE(VerilatedThreadMsgQueue);
     // METHODS
     static VerilatedThreadMsgQueue& threadton() {
-        static VL_THREAD_LOCAL VerilatedThreadMsgQueue t_s;
+        static thread_local VerilatedThreadMsgQueue t_s;
         return t_s;
     }
 
@@ -178,7 +175,6 @@ public:
         }
     }
 };
-#endif  // VL_THREADED
 
 // FILE* list constructed from a file-descriptor
 class VerilatedFpList final {
diff --git a/include/verilated_profiler.cpp b/include/verilated_profiler.cpp
index b04cc34e3..85d76352b 100644
--- a/include/verilated_profiler.cpp
+++ b/include/verilated_profiler.cpp
@@ -20,9 +20,7 @@
 
 #include "verilated_profiler.h"
 
-#if VL_THREADED
 #include "verilated_threads.h"
-#endif
 
 #include <fstream>
 #include <string>
@@ -32,7 +30,7 @@
 
 // Internal note: Globals may multi-construct, see verilated.cpp top.
 
-VL_THREAD_LOCAL VlExecutionProfiler::ExecutionTrace VlExecutionProfiler::t_trace;
+thread_local VlExecutionProfiler::ExecutionTrace VlExecutionProfiler::t_trace;
 
 constexpr const char* const VlExecutionRecord::s_ascii[];
 
@@ -105,7 +103,6 @@ void VlExecutionProfiler::configure() {
 
 VerilatedVirtualBase* VlExecutionProfiler::construct(VerilatedContext& context) {
     VlExecutionProfiler* const selfp = new VlExecutionProfiler{context};
-#if VL_THREADED
     if (VlThreadPool* const threadPoolp = static_cast<VlThreadPool*>(context.threadPoolp())) {
         for (int i = 0; i < threadPoolp->numThreads(); ++i) {
             // Data to pass to worker thread initialization
@@ -126,7 +123,6 @@ VerilatedVirtualBase* VlExecutionProfiler::construct(VerilatedContext& context)
             threadPoolp->workerp(i)->wait();
         }
     }
-#endif
     return selfp;
 }
 
@@ -172,9 +168,7 @@ void VlExecutionProfiler::dump(const char* filenamep, uint64_t tickEnd)
             Verilated::threadContextp()->profExecWindow());
     const unsigned threads = static_cast<unsigned>(m_traceps.size());
     fprintf(fp, "VLPROF stat threads %u\n", threads);
-#ifdef VL_THREADED
     fprintf(fp, "VLPROF stat yields %" PRIu64 "\n", VlMTaskVertex::yields());
-#endif
 
     // Copy /proc/cpuinfo into this output so verilator_gantt can be run on
     // a different machine
diff --git a/include/verilated_profiler.h b/include/verilated_profiler.h
index 5ddf3b0d9..5ca1271ff 100644
--- a/include/verilated_profiler.h
+++ b/include/verilated_profiler.h
@@ -151,7 +151,7 @@ class VlExecutionProfiler final : public VerilatedVirtualBase {
 
     // STATE
     VerilatedContext& m_context;  // The context this profiler is under
-    static VL_THREAD_LOCAL ExecutionTrace t_trace;  // thread-local trace buffers
+    static thread_local ExecutionTrace t_trace;  // thread-local trace buffers
     mutable VerilatedMutex m_mutex;
     // Map from thread id to &t_trace of given thread
     std::map<uint32_t, ExecutionTrace*> m_traceps VL_GUARDED_BY(m_mutex);
diff --git a/include/verilated_threads.h b/include/verilated_threads.h
index b595c1bca..6100ac057 100644
--- a/include/verilated_threads.h
+++ b/include/verilated_threads.h
@@ -27,15 +27,6 @@
 
 #include "verilated.h"  // for VerilatedMutex and clang annotations
 
-#ifndef VL_THREADED
-// Hitting this likely means verilated_threads.cpp is being compiled when
-// 'verilator --threads' was not used.  'verilator --threads' sets
-// VL_THREADED.
-// Alternatively it is always safe but may harm performance to always
-// define VL_THREADED for all compiles.
-#error "verilated_threads.h/cpp expected VL_THREADED (from verilator --threads)"
-#endif
-
 #include <atomic>
 #include <condition_variable>
 #include <set>
diff --git a/include/verilated_trace.h b/include/verilated_trace.h
index 151d2c9f2..2d75ea0ab 100644
--- a/include/verilated_trace.h
+++ b/include/verilated_trace.h
@@ -35,10 +35,8 @@
 #include <unordered_set>
 #include <vector>
 
-#ifdef VL_THREADED
-# include <deque>
-# include <thread>
-#endif
+#include <deque>
+#include <thread>
 
 // clang-format on
 
@@ -48,7 +46,6 @@ class VerilatedTraceBuffer;
 template <class T_Buffer>
 class VerilatedTraceOffloadBuffer;
 
-#ifdef VL_THREADED
 //=============================================================================
 // Offloaded tracing
 
@@ -117,7 +114,6 @@ public:
         SHUTDOWN = 0xf  // Shutdown worker thread, also marks end of buffer
     };
 };
-#endif
 
 //=============================================================================
 // VerilatedTraceConfig
@@ -186,10 +182,9 @@ private:
             , m_userp{userp} {}
     };
 
-    bool m_offload = false;  // Use the offload thread (ignored if !VL_THREADED)
-    bool m_parallel = false;  // Use parallel tracing (ignored if !VL_THREADED)
+    bool m_offload = false;  // Use the offload thread
+    bool m_parallel = false;  // Use parallel tracing
 
-#ifdef VL_THREADED
     struct ParallelWorkerData {
         const dumpCb_t m_cb;  // The callback
         void* const m_userp;  // The use pointer to pass to the callback
@@ -209,7 +204,6 @@ private:
 
     // Passed a ParallelWorkerData*, second argument is ignored
     static void parallelWorkerTask(void*, bool);
-#endif
 
 protected:
     uint32_t* m_sigs_oldvalp = nullptr;  // Previous value store
@@ -251,7 +245,6 @@ private:
     // Close the file on termination
     static void onExit(void* selfp) VL_MT_UNSAFE_ONE;
 
-#ifdef VL_THREADED
     // Number of total offload buffers that have been allocated
     uint32_t m_numOffloadBuffers = 0;
     // Size of offload buffers
@@ -282,7 +275,6 @@ private:
 
     // Shut down and join worker, if it's running, otherwise do nothing
     void shutdownOffloadWorker();
-#endif
 
     // CONSTRUCTORS
     VL_UNCOPYABLE(VerilatedTrace);
@@ -317,13 +309,8 @@ protected:
     void closeBase();
     void flushBase();
 
-#ifdef VL_THREADED
     bool offload() const { return m_offload; }
     bool parallel() const { return m_parallel; }
-#else
-    static constexpr bool offload() { return false; }
-    static constexpr bool parallel() { return false; }
-#endif
 
     //=========================================================================
     // Virtual functions to be provided by the format specific implementation
@@ -475,7 +462,6 @@ public:
     }
 };
 
-#ifdef VL_THREADED
 //=============================================================================
 // VerilatedTraceOffloadBuffer
 
@@ -548,6 +534,5 @@ public:
         VL_DEBUG_IF(assert(m_offloadBufferWritep <= m_offloadBufferEndp););
     }
 };
-#endif
 
 #endif  // guard
diff --git a/include/verilated_trace_imp.h b/include/verilated_trace_imp.h
index 21756dc77..7718ded13 100644
--- a/include/verilated_trace_imp.h
+++ b/include/verilated_trace_imp.h
@@ -26,10 +26,8 @@
 
 #include "verilated_intrinsics.h"
 #include "verilated_trace.h"
-#ifdef VL_THREADED
-# include "verilated_threads.h"
-# include <list>
-#endif
+#include "verilated_threads.h"
+#include <list>
 
 #if 0
 # include <iostream>
@@ -78,7 +76,6 @@ static std::string doubleToTimescale(double value) {
     return valuestr;  // Gets converted to string, so no ref to stack
 }
 
-#ifdef VL_THREADED
 //=========================================================================
 // Buffer management
 
@@ -250,14 +247,11 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::shutdownOffloadWorker() {
     m_workerThread.reset(nullptr);
 }
 
-#endif
-
 //=============================================================================
 // Life cycle
 
 template <>
 void VerilatedTrace<VL_SUB_T, VL_BUF_T>::closeBase() {
-#ifdef VL_THREADED
     if (offload()) {
         shutdownOffloadWorker();
         while (m_numOffloadBuffers) {
@@ -265,12 +259,10 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::closeBase() {
             --m_numOffloadBuffers;
         }
     }
-#endif
 }
 
 template <>
 void VerilatedTrace<VL_SUB_T, VL_BUF_T>::flushBase() {
-#ifdef VL_THREADED
     if (offload()) {
         // Hand an empty buffer to the worker thread
         uint32_t* const bufferp = getOffloadBuffer();
@@ -280,7 +272,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::flushBase() {
         // this ensures all previous buffers have been processed.
         waitForOffloadBuffer(bufferp);
     }
-#endif
 }
 
 //=============================================================================
@@ -368,7 +359,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::traceInit() VL_MT_UNSAFE {
     Verilated::addFlushCb(VerilatedTrace<VL_SUB_T, VL_BUF_T>::onFlush, this);
     Verilated::addExitCb(VerilatedTrace<VL_SUB_T, VL_BUF_T>::onExit, this);
 
-#ifdef VL_THREADED
     if (offload()) {
         // Compute offload buffer size. we need to be able to store a new value for
         // each signal, which is 'nextCode()' entries after the init callbacks
@@ -381,7 +371,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::traceInit() VL_MT_UNSAFE {
         m_workerThread.reset(
             new std::thread{&VerilatedTrace<VL_SUB_T, VL_BUF_T>::offloadWorkerThreadMain, this});
     }
-#endif
 }
 
 template <>
@@ -468,7 +457,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::dumpvars(int level, const std::string&
     }
 }
 
-#ifdef VL_THREADED
 template <>
 void VerilatedTrace<VL_SUB_T, VL_BUF_T>::parallelWorkerTask(void* datap, bool) {
     ParallelWorkerData* const wdp = reinterpret_cast<ParallelWorkerData*>(datap);
@@ -493,11 +481,9 @@ VL_ATTR_NOINLINE void VerilatedTrace<VL_SUB_T, VL_BUF_T>::ParallelWorkerData::wa
     m_cv.wait(lock, [this] { return m_ready.load(std::memory_order_relaxed); });
     m_waiting = false;
 }
-#endif
 
 template <>
 void VerilatedTrace<VL_SUB_T, VL_BUF_T>::runCallbacks(const std::vector<CallbackRecord>& cbVec) {
-#ifdef VL_THREADED
     if (parallel()) {
         // If tracing in parallel, dispatch to the thread pool
         VlThreadPool* threadPoolp = static_cast<VlThreadPool*>(m_contextp->threadPoolp());
@@ -538,7 +524,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::runCallbacks(const std::vector<Callback
         // Done
         return;
     }
-#endif
     // Fall back on sequential execution
     for (const CallbackRecord& cbr : cbVec) {
         Buffer* const traceBufferp = getTraceBuffer();
@@ -551,15 +536,11 @@ template <>
 void VerilatedTrace<VL_SUB_T, VL_BUF_T>::runOffloadedCallbacks(
     const std::vector<CallbackRecord>& cbVec) {
     // Fall back on sequential execution
-#ifdef VL_THREADED
     for (const CallbackRecord& cbr : cbVec) {
         Buffer* traceBufferp = getTraceBuffer();
         cbr.m_dumpOffloadCb(cbr.m_userp, static_cast<OffloadBuffer*>(traceBufferp));
         commitTraceBuffer(traceBufferp);
     }
-#else
-    if (!cbVec.empty()) VL_FATAL_MT(__FILE__, __LINE__, "", "Unreachable");
-#endif
 }
 
 template <>
@@ -586,11 +567,8 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::dump(uint64_t timeui) VL_MT_SAFE_EXCLUD
         if (!preChangeDump()) return;
     }
 
-#ifdef VL_THREADED
     uint32_t* bufferp = nullptr;
-#endif
     if (offload()) {
-#ifdef VL_THREADED
         // Currently only incremental dumps run on the worker thread
         if (VL_LIKELY(!m_fullDump)) {
             // Get the offload buffer we are about to fill
@@ -607,9 +585,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::dump(uint64_t timeui) VL_MT_SAFE_EXCLUD
             flushBase();
             emitTimeChange(timeui);
         }
-#else
-        VL_FATAL_MT(__FILE__, __LINE__, "", "Unreachable");
-#endif
     } else {
         // Update time point
         emitTimeChange(timeui);
@@ -636,7 +611,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::dump(uint64_t timeui) VL_MT_SAFE_EXCLUD
         cbr.m_cleanupCb(cbr.m_userp, self());
     }
 
-#ifdef VL_THREADED
     if (offload() && VL_LIKELY(bufferp)) {
         // Mark end of the offload buffer we just filled
         *m_offloadBufferWritep++ = VerilatedTraceOffloadCommand::END;
@@ -651,7 +625,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::dump(uint64_t timeui) VL_MT_SAFE_EXCLUD
         // Pass it to the worker thread
         m_offloadBuffersToWorker.put(bufferp);
     }
-#endif
 }
 
 //=============================================================================
@@ -685,11 +658,6 @@ void VerilatedTrace<VL_SUB_T, VL_BUF_T>::addModel(VerilatedModel* modelp)
 
     // Get the desired trace config from the model
     const std::unique_ptr<VerilatedTraceConfig> configp = modelp->traceConfig();
-#ifndef VL_THREADED
-    if (configp->m_useOffloading) {
-        VL_FATAL_MT(__FILE__, __LINE__, "", "Cannot use trace offloading without VL_THREADED");
-    }
-#endif
 
     // Configure trace base class
     if (!firstModel) {
@@ -915,7 +883,6 @@ void VerilatedTraceBuffer<VL_BUF_T>::fullDouble(uint32_t* oldp, double newval) {
     emitDouble(code, newval);
 }
 
-#ifdef VL_THREADED
 //=========================================================================
 // VerilatedTraceOffloadBuffer
 
@@ -934,6 +901,5 @@ VerilatedTraceOffloadBuffer<VL_BUF_T>::VerilatedTraceOffloadBuffer(VL_SUB_T& own
         m_offloadBufferWritep += 2;
     }
 }
-#endif
 
 #endif  // VL_CPPCHECK
diff --git a/include/verilated_types.h b/include/verilated_types.h
index dba797b74..0aae11ea1 100644
--- a/include/verilated_types.h
+++ b/include/verilated_types.h
@@ -367,7 +367,7 @@ public:
     // Can't just overload operator[] or provide a "at" reference to set,
     // because we need to be able to insert only when the value is set
     T_Value& at(int32_t index) {
-        static VL_THREAD_LOCAL T_Value s_throwAway;
+        static thread_local T_Value s_throwAway;
         // Needs to work for dynamic arrays, so does not use T_MaxSize
         if (VL_UNLIKELY(index < 0 || index >= m_deque.size())) {
             s_throwAway = atDefault();
@@ -378,7 +378,7 @@ public:
     }
     // Accessing. Verilog: v = assoc[index]
     const T_Value& at(int32_t index) const {
-        static VL_THREAD_LOCAL T_Value s_throwAway;
+        static thread_local T_Value s_throwAway;
         // Needs to work for dynamic arrays, so does not use T_MaxSize
         if (VL_UNLIKELY(index < 0 || index >= m_deque.size())) {
             return atDefault();
diff --git a/include/verilated_vcd_c.cpp b/include/verilated_vcd_c.cpp
index 2d0cc57f0..a0145b2af 100644
--- a/include/verilated_vcd_c.cpp
+++ b/include/verilated_vcd_c.cpp
@@ -230,12 +230,10 @@ VerilatedVcd::~VerilatedVcd() {
     if (m_wrBufp) VL_DO_CLEAR(delete[] m_wrBufp, m_wrBufp = nullptr);
     deleteNameMap();
     if (m_filep && m_fileNewed) VL_DO_CLEAR(delete m_filep, m_filep = nullptr);
-#ifdef VL_THREADED
     if (parallel()) {
         assert(m_numBuffers == m_freeBuffers.size());
         for (auto& pair : m_freeBuffers) VL_DO_CLEAR(delete[] pair.first, pair.first = nullptr);
     }
-#endif
 }
 
 void VerilatedVcd::closePrev() {
@@ -574,7 +572,6 @@ void VerilatedVcd::declDouble(uint32_t code, const char* name, bool array, int a
 
 VerilatedVcd::Buffer* VerilatedVcd::getTraceBuffer() {
     VerilatedVcd::Buffer* const bufp = new Buffer{*this};
-#ifdef VL_THREADED
     if (parallel()) {
         // Note: This is called from VeriltedVcd::dump, which already holds the lock
         // If no buffer available, allocate a new one
@@ -593,14 +590,12 @@ VerilatedVcd::Buffer* VerilatedVcd::getTraceBuffer() {
         bufp->m_size = pair.second;
         bufp->adjustGrowp();
     }
-#endif
     // Return the buffer
     return bufp;
 }
 
 void VerilatedVcd::commitTraceBuffer(VerilatedVcd::Buffer* bufp) {
     if (parallel()) {
-#if VL_THREADED
         // Note: This is called from VeriltedVcd::dump, which already holds the lock
         // Resize output buffer. Note, we use the full size of the trace buffer, as
         // this is a lot more stable than the actual occupancy of the trace buffer.
@@ -616,9 +611,6 @@ void VerilatedVcd::commitTraceBuffer(VerilatedVcd::Buffer* bufp) {
         bufferCheck();
         // Put buffer back on free list
         m_freeBuffers.emplace_back(bufp->m_bufp, bufp->m_size);
-#else
-        VL_FATAL_MT(__FILE__, __LINE__, "", "Unreachable");
-#endif
     } else {
         // Needs adjusting for emitTimeChange
         m_writep = bufp->m_writep;
@@ -665,7 +657,6 @@ void VerilatedVcdBuffer::finishLine(uint32_t code, char* writep) {
     m_writep = writep + suffixp[VL_TRACE_SUFFIX_ENTRY_SIZE - 1];
 
     if (m_owner.parallel()) {
-#ifdef VL_THREADED
         // Double the size of the buffer if necessary
         if (VL_UNLIKELY(m_writep >= m_growp)) {
             // Compute occupied size of current buffer
@@ -685,9 +676,6 @@ void VerilatedVcdBuffer::finishLine(uint32_t code, char* writep) {
             // Adjust resize limit
             adjustGrowp();
         }
-#else
-        VL_FATAL_MT(__FILE__, __LINE__, "", "Unreachable");
-#endif
     } else {
         // Flush the write buffer if there's not enough space left for new information
         // We only call this once per vector, so we need enough slop for a very wide "b###" line
diff --git a/include/verilated_vcd_c.h b/include/verilated_vcd_c.h
index 2967225b1..166a48322 100644
--- a/include/verilated_vcd_c.h
+++ b/include/verilated_vcd_c.h
@@ -65,11 +65,9 @@ private:
     using NameMap = std::map<const std::string, const std::string>;
     NameMap* m_namemapp = nullptr;  // List of names for the header
 
-#ifdef VL_THREADED
     // Vector of free trace buffers as (pointer, size) pairs.
     std::vector<std::pair<char*, size_t>> m_freeBuffers;
     size_t m_numBuffers = 0;  // Number of trace buffers allocated
-#endif
 
     void bufferResize(size_t minsize);
     void bufferFlush() VL_MT_UNSAFE_ONE;
@@ -187,7 +185,6 @@ class VerilatedVcdBuffer VL_NOT_FINAL {
     // The maximum number of bytes a single signal can emit
     const size_t m_maxSignalBytes = m_owner.m_maxSignalBytes;
 
-#ifdef VL_THREADED
     // Additional data for parallel tracing only
     char* m_bufp = nullptr;  // The beginning of the trace buffer
     size_t m_size = 0;  // The size of the buffer at m_bufp
@@ -197,7 +194,6 @@ class VerilatedVcdBuffer VL_NOT_FINAL {
         m_growp = (m_bufp + m_size) - (2 * m_maxSignalBytes);
         assert(m_growp >= m_bufp + m_maxSignalBytes);
     }
-#endif
 
     void finishLine(uint32_t code, char* writep);
 
diff --git a/include/verilated_vpi.cpp b/include/verilated_vpi.cpp
index 56f7d5e42..023c6683d 100644
--- a/include/verilated_vpi.cpp
+++ b/include/verilated_vpi.cpp
@@ -71,7 +71,7 @@ class VerilatedVpio VL_NOT_FINAL {
 
     // MEM MANGLEMENT
     // Internal note: Globals may multi-construct, see verilated.cpp top.
-    static VL_THREAD_LOCAL uint8_t* t_freeHead;
+    static thread_local uint8_t* t_freeHead;
 
 public:
     // CONSTRUCTORS
@@ -205,7 +205,7 @@ public:
     const VerilatedRange* rangep() const override { return &get_range(); }
     const char* name() const override { return m_varp->name(); }
     const char* fullname() const override {
-        static VL_THREAD_LOCAL std::string t_out;
+        static thread_local std::string t_out;
         t_out = std::string{m_scopep->name()} + "." + name();
         return t_out.c_str();
     }
@@ -348,7 +348,7 @@ public:
     uint32_t size() const override { return varp()->packed().elements(); }
     const VerilatedRange* rangep() const override { return &(varp()->packed()); }
     const char* fullname() const override {
-        static VL_THREAD_LOCAL std::string t_out;
+        static thread_local std::string t_out;
         constexpr size_t LEN_MAX_INDEX = 25;
         char num[LEN_MAX_INDEX];
         VL_SNPRINTF(num, LEN_MAX_INDEX, "%d", m_index);
@@ -666,7 +666,7 @@ public:
 // Statics
 // Internal note: Globals may multi-construct, see verilated.cpp top.
 
-VL_THREAD_LOCAL uint8_t* VerilatedVpio::t_freeHead = nullptr;
+thread_local uint8_t* VerilatedVpio::t_freeHead = nullptr;
 
 //======================================================================
 // VerilatedVpiError
@@ -708,7 +708,7 @@ public:
     }
     void setMessage(const std::string& file, PLI_INT32 line, const char* message, ...) {
         // message cannot be a const string& as va_start cannot use a reference
-        static VL_THREAD_LOCAL std::string t_filehold;
+        static thread_local std::string t_filehold;
         va_list args;
         va_start(args, message);
         VL_VSNPRINTF(m_buff, sizeof(m_buff), message, args);
@@ -1701,15 +1701,15 @@ void vl_get_value(const VerilatedVar* varp, void* varDatap, p_vpi_value valuep,
                   const char* fullname) {
     if (!vl_check_format(varp, valuep, fullname, true)) return;
     // Maximum required size is for binary string, one byte per bit plus null termination
-    static VL_THREAD_LOCAL char t_outStr[VL_VALUE_STRING_MAX_WORDS * VL_EDATASIZE + 1];
+    static thread_local char t_outStr[VL_VALUE_STRING_MAX_WORDS * VL_EDATASIZE + 1];
     // cppcheck-suppress variableScope
-    static const VL_THREAD_LOCAL int t_outStrSz = sizeof(t_outStr) - 1;
+    static const thread_local int t_outStrSz = sizeof(t_outStr) - 1;
     // We used to presume vpiValue.format = vpiIntVal or if single bit vpiScalarVal
     // This may cause backward compatibility issues with older code.
     if (valuep->format == vpiVectorVal) {
         // Vector pointer must come from our memory pool
         // It only needs to persist until the next vpi_get_value
-        static VL_THREAD_LOCAL t_vpi_vecval t_out[VL_VALUE_STRING_MAX_WORDS * 2];
+        static thread_local t_vpi_vecval t_out[VL_VALUE_STRING_MAX_WORDS * 2];
         valuep->value.vector = t_out;
         if (varp->vltype() == VLVT_UINT8) {
             t_out[0].aval = *(reinterpret_cast<CData*>(varDatap));
diff --git a/include/verilatedos.h b/include/verilatedos.h
index de89e822e..41e74684a 100644
--- a/include/verilatedos.h
+++ b/include/verilatedos.h
@@ -56,7 +56,7 @@
 # if !defined(_WIN32) && !defined(__MINGW32__)
 #  define VL_ATTR_WEAK __attribute__((weak))
 # endif
-# if defined(__clang__) && defined(VL_THREADED)
+# if defined(__clang__)
 #  define VL_ACQUIRE(...) __attribute__((acquire_capability(__VA_ARGS__)))
 #  define VL_ACQUIRE_SHARED(...) __attribute__((acquire_shared_capability(__VA_ARGS__)))
 #  define VL_RELEASE(...) __attribute__((release_capability(__VA_ARGS__)))
@@ -139,47 +139,34 @@
 # define VL_PREFETCH_RW(p)  ///< Prefetch pointer argument with read/write intent
 #endif
 
-#if defined(VL_THREADED) && !defined(VL_CPPCHECK)
-# if defined(_MSC_VER) && _MSC_VER >= 1900
-#  define VL_THREAD_LOCAL thread_local
-# elif defined(__GNUC__)
-#  if (__cplusplus < 201103L)
-#   error "VL_THREADED/--threads support requires C++-11 or newer only; use newer compiler"
-#  endif
-# else
-#  error "Unsupported compiler for VL_THREADED: No thread-local declarator"
-# endif
-# define VL_THREAD_LOCAL thread_local  // "thread_local" when supported
-#else
-# define VL_THREAD_LOCAL  // "thread_local" when supported
-#endif
 
 #ifndef VL_NO_LEGACY
 # define VL_FUNC __func__  // Deprecated
 # define VL_THREAD  // Deprecated
+# define VL_THREAD_LOCAL thread_local  // Deprecated
 # define VL_STATIC_OR_THREAD static  // Deprecated
 #endif
 
 // Comment tag that Function is pure (and thus also VL_MT_SAFE)
 #define VL_PURE
-// Comment tag that function is threadsafe when VL_THREADED
+// Comment tag that function is threadsafe
 #if defined(__clang__)
 # define VL_MT_SAFE __attribute__((annotate("MT_SAFE")))
 #else
 # define VL_MT_SAFE
 #endif
-// Comment tag that function is threadsafe when VL_THREADED, only
+// Comment tag that function is threadsafe, only
 // during normal operation (post-init)
 #define VL_MT_SAFE_POSTINIT
 // Attribute that function is clang threadsafe and uses given mutex
 #define VL_MT_SAFE_EXCLUDES(mutex) VL_EXCLUDES(mutex)
-// Comment tag that function is not threadsafe when VL_THREADED
+// Comment tag that function is not threadsafe
 #if defined(__clang__)
 # define VL_MT_UNSAFE __attribute__((annotate("MT_UNSAFE")))
 #else
 # define VL_MT_UNSAFE
 #endif
-// Comment tag that function is not threadsafe when VL_THREADED,
+// Comment tag that function is not threadsafe
 // protected to make sure single-caller
 #define VL_MT_UNSAFE_ONE
 
@@ -482,28 +469,26 @@ using ssize_t = uint32_t;  ///< signed size_t; returned from read()
 //=========================================================================
 // Threading related OS-specific functions
 
-#if VL_THREADED
-# ifdef _WIN32
-#  define WIN32_LEAN_AND_MEAN
-#  define NOMINMAX
-#  include "Windows.h"
-#  define VL_CPU_RELAX() YieldProcessor()
-# elif defined(__i386__) || defined(__x86_64__) || defined(VL_CPPCHECK)
+#ifdef _WIN32
+# define WIN32_LEAN_AND_MEAN
+# define NOMINMAX
+# include "Windows.h"
+# define VL_CPU_RELAX() YieldProcessor()
+#elif defined(__i386__) || defined(__x86_64__) || defined(VL_CPPCHECK)
 // For more efficient busy waiting on SMT CPUs, let the processor know
 // we're just waiting so it can let another thread run
-#  define VL_CPU_RELAX() asm volatile("rep; nop" ::: "memory")
-# elif defined(__ia64__)
-#  define VL_CPU_RELAX() asm volatile("hint @pause" ::: "memory")
-# elif defined(__aarch64__)
-#  define VL_CPU_RELAX() asm volatile("yield" ::: "memory")
-# elif defined(__powerpc64__)
-#  define VL_CPU_RELAX() asm volatile("or 1, 1, 1; or 2, 2, 2;" ::: "memory")
-# elif defined(__loongarch__)
-// LoongArch does not currently have a yield/pause instruction
-#  define VL_CPU_RELAX() asm volatile("nop" ::: "memory")
-# else
-#  error "Missing VL_CPU_RELAX() definition. Or, don't use VL_THREADED"
-# endif
+# define VL_CPU_RELAX() asm volatile("rep; nop" ::: "memory")
+#elif defined(__ia64__)
+# define VL_CPU_RELAX() asm volatile("hint @pause" ::: "memory")
+#elif defined(__aarch64__)
+# define VL_CPU_RELAX() asm volatile("yield" ::: "memory")
+#elif defined(__powerpc64__)
+# define VL_CPU_RELAX() asm volatile("or 1, 1, 1; or 2, 2, 2;" ::: "memory")
+#elif defined(__loongarch__)
+/ LoongArch does not currently have a yield/pause instruction
+# define VL_CPU_RELAX() asm volatile("nop" ::: "memory")
+#else
+# error "Missing VL_CPU_RELAX() definition."
 #endif
 
 //=========================================================================
diff --git a/src/V3EmitCBase.cpp b/src/V3EmitCBase.cpp
index 40198fa76..c481f5bba 100644
--- a/src/V3EmitCBase.cpp
+++ b/src/V3EmitCBase.cpp
@@ -210,7 +210,7 @@ void EmitCBaseVisitor::emitVarDecl(const AstVar* nodep, bool asRef) {
             // Issue 2622.
             const bool beStatic = name.size() >= suffix.size()
                                   && name.substr(name.size() - suffix.size()) == suffix;
-            if (beStatic) puts("static VL_THREAD_LOCAL ");
+            if (beStatic) puts("static thread_local ");
         }
         puts(nodep->vlArgType(true, false, false, "", asRef));
         puts(";\n");
diff --git a/src/V3EmitCMake.cpp b/src/V3EmitCMake.cpp
index cf7b17563..a2206af5e 100644
--- a/src/V3EmitCMake.cpp
+++ b/src/V3EmitCMake.cpp
@@ -116,7 +116,7 @@ class CMakeEmitter final {
         cmake_set_raw(*of, name + "_COVERAGE", v3Global.opt.coverage() ? "1" : "0");
         *of << "# Timing mode?  0/1\n";
         cmake_set_raw(*of, name + "_TIMING", v3Global.usesTiming() ? "1" : "0");
-        *of << "# Threaded output mode?  0/1/N threads (from --threads)\n";
+        *of << "# Threaded output mode?  1/N threads (from --threads)\n";
         cmake_set_raw(*of, name + "_THREADS", cvtToStr(v3Global.opt.threads()));
         *of << "# VCD Tracing output mode?  0/1 (from --trace)\n";
         cmake_set_raw(*of, name + "_TRACE_VCD",
diff --git a/src/V3EmitMk.cpp b/src/V3EmitMk.cpp
index 163e408ba..f51f0fe34 100644
--- a/src/V3EmitMk.cpp
+++ b/src/V3EmitMk.cpp
@@ -63,10 +63,6 @@ public:
         of.puts("VM_PARALLEL_BUILDS = ");
         of.puts(v3Global.useParallelBuild() ? "1" : "0");
         of.puts("\n");
-        of.puts("# Threaded output mode?  0/1/N threads (from --threads)\n");
-        of.puts("VM_THREADS = ");
-        of.puts(cvtToStr(v3Global.opt.threads()));
-        of.puts("\n");
         of.puts("# Tracing output mode?  0/1 (from --trace/--trace-fst)\n");
         of.puts("VM_TRACE = ");
         of.puts(v3Global.opt.trace() ? "1" : "0");
diff --git a/src/V3Options.cpp b/src/V3Options.cpp
index f009a5f2d..287cdd93e 100644
--- a/src/V3Options.cpp
+++ b/src/V3Options.cpp
@@ -1388,10 +1388,17 @@ void V3Options::parseOptsList(FileLine* fl, const string& optdir, int argc, char
     DECL_OPTION("-sv", CbCall, [this]() { m_defaultLanguage = V3LangCode::L1800_2017; });
 
     DECL_OPTION("-threads-coarsen", OnOff, &m_threadsCoarsen).undocumented();  // Debug
-    DECL_OPTION("-no-threads", CbCall, [this]() { m_threads = 0; });
+    DECL_OPTION("-no-threads", CbCall, [this, fl]() {
+        fl->v3warn(DEPRECATED, "Option --no-threads is deprecated, use '--threads 1' instead");
+        m_threads = 1;
+    });
     DECL_OPTION("-threads", CbVal, [this, fl](const char* valp) {
         m_threads = std::atoi(valp);
         if (m_threads < 0) fl->v3fatal("--threads must be >= 0: " << valp);
+        if (m_threads == 0) {
+            fl->v3warn(DEPRECATED, "Option --threads 0 is deprecated, use '--threads 1' instead");
+            m_threads = 1;
+        }
     });
     DECL_OPTION("-threads-dpi", CbVal, [this, fl](const char* valp) {
         if (!std::strcmp(valp, "all")) {
diff --git a/src/V3Options.h b/src/V3Options.h
index c2c3852fc..1dcb95edf 100644
--- a/src/V3Options.h
+++ b/src/V3Options.h
@@ -304,7 +304,7 @@ private:
     int         m_pinsBv = 65;       // main switch: --pins-bv
     int         m_reloopLimit = 40; // main switch: --reloop-limit
     VOptionBool m_skipIdentical;  // main switch: --skip-identical
-    int         m_threads = 0;      // main switch: --threads (0 == --no-threads)
+    int         m_threads = 1;      // main switch: --threads
     int         m_threadsMaxMTasks = 0;  // main switch: --threads-max-mtasks
     VTimescale  m_timeDefaultPrec;  // main switch: --timescale
     VTimescale  m_timeDefaultUnit;  // main switch: --timescale
diff --git a/test_regress/driver.pl b/test_regress/driver.pl
index 4bd739304..1f227d341 100755
--- a/test_regress/driver.pl
+++ b/test_regress/driver.pl
@@ -904,7 +904,7 @@ sub compile_vlt_flags {
                           @{$param{verilator_flags}},
                           @{$param{verilator_flags2}},
                           @{$param{verilator_flags3}});
-    die "%Error: specify threads via 'threads =>' argument, not as a command line option" unless ($checkflags !~ /(^|\s)-?-threads\s/ && $checkflags !~ /(^|\s)-?-no-threads($|\s)/);
+    die "%Error: specify threads via 'threads =>' argument, not as a command line option" unless ($checkflags !~ /(^|\s)-?-threads\s/);
     $self->{sc} = 1 if ($checkflags =~ /-sc\b/);
     $self->{trace} = ($opt_trace || $checkflags =~ /-trace\b/
                       || $checkflags =~ /-trace-fst\b/);
diff --git a/test_regress/t/t_embed1.pl b/test_regress/t/t_embed1.pl
index 2c5b8a918..85d36addd 100755
--- a/test_regress/t/t_embed1.pl
+++ b/test_regress/t/t_embed1.pl
@@ -23,7 +23,7 @@ mkdir $child_dir;
          top_filename => "$Self->{name}_child.v",
          verilator_flags => ["-cc", "-Mdir", "${child_dir}", "--debug-check"],
          # Can't use multi threading (like hier blocks), but needs to be thread safe
-         threads => $Self->{vltmt} ? 1 : 0,
+         threads => 1,
         );
 
     run(logfile => "${child_dir}/vlt_compile.log",
diff --git a/test_regress/t/t_flag_values_deprecated.out b/test_regress/t/t_flag_values_deprecated.out
new file mode 100644
index 000000000..5f5efc6a9
--- /dev/null
+++ b/test_regress/t/t_flag_values_deprecated.out
@@ -0,0 +1,5 @@
+%Warning-DEPRECATED: Option --threads 0 is deprecated, use '--threads 1' instead
+                     ... For warning description see https://verilator.org/warn/DEPRECATED?v=latest
+                     ... Use "/* verilator lint_off DEPRECATED */" and lint_on around source to disable this message.
+%Error-DEPRECATED: Option --no-threads is deprecated, use '--threads 1' instead
+%Error: Exiting due to
diff --git a/test_regress/t/t_flag_values_deprecated.pl b/test_regress/t/t_flag_values_deprecated.pl
new file mode 100755
index 000000000..a4d6ad3c2
--- /dev/null
+++ b/test_regress/t/t_flag_values_deprecated.pl
@@ -0,0 +1,21 @@
+#!/usr/bin/env perl
+if (!$::Driver) { use FindBin; exec("$FindBin::Bin/bootstrap.pl", @ARGV, $0); die; }
+# DESCRIPTION: Verilator: Verilog Test driver/expect definition
+#
+# Copyright 2022 by Antmicro. This program is free software; you
+# can redistribute it and/or modify it under the terms of either the GNU
+# Lesser General Public License Version 3 or the Perl Artistic License
+# Version 2.0.
+# SPDX-License-Identifier: LGPL-3.0-only OR Artistic-2.0
+
+scenarios(vlt => 1);
+
+lint(
+    verilator_flags2 => ["-Werror-DEPRECATED", "--no-threads"],
+    fails => 1,
+    threads => 0,
+    expect_filename => $Self->{golden_filename},
+    );
+
+ok(1);
+1;
diff --git a/test_regress/t/t_gantt.pl b/test_regress/t/t_gantt.pl
index 1f92de577..e1c1c93c3 100755
--- a/test_regress/t/t_gantt.pl
+++ b/test_regress/t/t_gantt.pl
@@ -20,7 +20,7 @@ top_filename("t/t_gen_alw.v");
 compile(
     v_flags2 => ["--prof-exec"],
     # Checks below care about thread count, so use 2 (minimum reasonable)
-    threads => $Self->{vltmt} ? 2 : 0
+    threads => $Self->{vltmt} ? 2 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_gantt_two.cpp b/test_regress/t/t_gantt_two.cpp
index ecd0be219..5754c91fe 100644
--- a/test_regress/t/t_gantt_two.cpp
+++ b/test_regress/t/t_gantt_two.cpp
@@ -16,9 +16,8 @@ int main(int argc, char** argv, char** env) {
     srand48(5);
 
     const std::unique_ptr<VerilatedContext> contextp{new VerilatedContext};
-#ifdef VL_THREADED
-    contextp->threads(2);
-#endif
+    // VL_USE_THREADS define is set in t_gantt_two.pl
+    contextp->threads(TEST_USE_THREADS);
     contextp->commandArgs(argc, argv);
     contextp->debug(0);
 
diff --git a/test_regress/t/t_gantt_two.pl b/test_regress/t/t_gantt_two.pl
index 768f55440..60d41117c 100755
--- a/test_regress/t/t_gantt_two.pl
+++ b/test_regress/t/t_gantt_two.pl
@@ -17,13 +17,15 @@ scenarios(vlt_all => 1);
 # enough for the profiling to happen:
 top_filename("t/t_gen_alw.v");
 
+my $threads_num = $Self->{vltmt} ? 2 : 1;
+
 compile(
     make_top_shell => 0,
     make_main => 0,
     v_flags2 => ["--prof-exec --exe $Self->{t_dir}/$Self->{name}.cpp"],
     # Checks below care about thread count, so use 2 (minimum reasonable)
-    threads => $Self->{vltmt} ? 2 : 0,
-    make_flags => 'CPPFLAGS_ADD=-DVL_NO_LEGACY',
+    threads => $threads_num,
+    make_flags => "CPPFLAGS_ADD=\"-DVL_NO_LEGACY -DTEST_USE_THREADS=$threads_num\"",
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block.pl b/test_regress/t/t_hier_block.pl
index e861c733e..64e8f45ed 100755
--- a/test_regress/t/t_hier_block.pl
+++ b/test_regress/t/t_hier_block.pl
@@ -23,7 +23,7 @@ compile(
                          '--Wno-TIMESCALEMOD',
                          '--CFLAGS', '"-pipe -DCPP_MACRO=cplusplus"'
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_cmake.pl b/test_regress/t/t_hier_block_cmake.pl
index a4d74b89b..5c03ac6eb 100755
--- a/test_regress/t/t_hier_block_cmake.pl
+++ b/test_regress/t/t_hier_block_cmake.pl
@@ -13,17 +13,19 @@ clean_objs();
 scenarios(simulator => 1);
 top_filename("t/t_hier_block.v");
 
+my $threads = ($Self->{vltmt} ? '-DTEST_THREADS=6' : '-DTEST_THREADS=1');
+
 if (!$Self->have_cmake) {
     $Self->skip("Test requires CMake; ignore error since not available or version too old\n");
 } else {
     run(logfile => "$Self->{obj_dir}/cmake.log",
         cmd => ['cd "' . $Self->{obj_dir} . '" && cmake ' . $Self->{t_dir} . '/t_hier_block_cmake',
             "-DCMAKE_PREFIX_PATH=$ENV{VERILATOR_ROOT}",
-            ($Self->{vltmt} ? '-DTEST_THREADS=6' : '')
+            $threads
         ]);
 
     run(logfile => "$Self->{obj_dir}/build.log",
-        cmd => ['cd "' . $Self->{obj_dir} . '" && cmake --build', '.']
+        cmd => ['cd "' . $Self->{obj_dir} . '" && cmake --build', '.', '--', "CXX_FLAGS=$threads"]
     );
 
     run(logfile => "$Self->{obj_dir}/run.log",
diff --git a/test_regress/t/t_hier_block_cmake/main.cpp b/test_regress/t/t_hier_block_cmake/main.cpp
index 58bc8d5ad..beebaabff 100644
--- a/test_regress/t/t_hier_block_cmake/main.cpp
+++ b/test_regress/t/t_hier_block_cmake/main.cpp
@@ -14,9 +14,8 @@
 
 int main(int argc, char *argv[]) {
     const std::unique_ptr<VerilatedContext> contextp{new VerilatedContext};
-#if VL_THREADED
-    contextp->threads(6);
-#endif
+    // TEST_THREADS is set in t_hier_block_cmake.pl
+    contextp->threads(TEST_THREADS);
     contextp->commandArgs(argc, argv);
     std::unique_ptr<Vt_hier_block> top{new Vt_hier_block{contextp.get(), "top"}};
     for (int i = 0; i < 100 && !contextp->gotFinish(); ++i) {
diff --git a/test_regress/t/t_hier_block_nohier.pl b/test_regress/t/t_hier_block_nohier.pl
index 8da19e163..97586ec08 100755
--- a/test_regress/t/t_hier_block_nohier.pl
+++ b/test_regress/t/t_hier_block_nohier.pl
@@ -24,7 +24,7 @@ compile(
     verilator_flags2 => ['--stats',
                          '+define+USE_VLT', 't/t_hier_block_vlt.vlt',
                          '--CFLAGS', '"-pipe -DCPP_MACRO=cplusplus"'],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_sc.pl b/test_regress/t/t_hier_block_sc.pl
index 8aff1358d..b2264712f 100755
--- a/test_regress/t/t_hier_block_sc.pl
+++ b/test_regress/t/t_hier_block_sc.pl
@@ -24,7 +24,7 @@ compile(
                          '--hierarchical',
                          '--CFLAGS', '"-pipe -DCPP_MACRO=cplusplus"'
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_sc_trace_fst.pl b/test_regress/t/t_hier_block_sc_trace_fst.pl
index b2497ad14..331f3fe87 100755
--- a/test_regress/t/t_hier_block_sc_trace_fst.pl
+++ b/test_regress/t/t_hier_block_sc_trace_fst.pl
@@ -26,7 +26,7 @@ compile(
                          "--CFLAGS", '"-O0 -ggdb"',
                          "--trace-fst"
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_sc_trace_vcd.pl b/test_regress/t/t_hier_block_sc_trace_vcd.pl
index 7239369c7..5f27738e6 100755
--- a/test_regress/t/t_hier_block_sc_trace_vcd.pl
+++ b/test_regress/t/t_hier_block_sc_trace_vcd.pl
@@ -26,7 +26,7 @@ compile(
                          "--CFLAGS", '"-O0 -ggdb"',
                          "--trace"
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_trace_fst.pl b/test_regress/t/t_hier_block_trace_fst.pl
index 753b9dda1..d05251cfd 100755
--- a/test_regress/t/t_hier_block_trace_fst.pl
+++ b/test_regress/t/t_hier_block_trace_fst.pl
@@ -22,7 +22,7 @@ compile(
                          '--trace-fst',
                          '--no-trace-underscore',  # To avoid handle mismatches
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_trace_vcd.pl b/test_regress/t/t_hier_block_trace_vcd.pl
index 4f3b80f09..b53533adf 100755
--- a/test_regress/t/t_hier_block_trace_vcd.pl
+++ b/test_regress/t/t_hier_block_trace_vcd.pl
@@ -22,7 +22,7 @@ compile(
                          '--trace',
                          '--no-trace-underscore',  # To avoid handle mismatches
     ],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_hier_block_vlt.pl b/test_regress/t/t_hier_block_vlt.pl
index ef467ede9..63e0d466d 100755
--- a/test_regress/t/t_hier_block_vlt.pl
+++ b/test_regress/t/t_hier_block_vlt.pl
@@ -23,7 +23,7 @@ compile(
                          '+define+SHOW_TIMESCALE',
                          '+define+USE_VLT', 't/t_hier_block_vlt.vlt',
                          '--CFLAGS', '"-pipe -DCPP_MACRO=cplusplus"'],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_inst_tree_inl0_pub1.pl b/test_regress/t/t_inst_tree_inl0_pub1.pl
index 107b1e56d..5979621aa 100755
--- a/test_regress/t/t_inst_tree_inl0_pub1.pl
+++ b/test_regress/t/t_inst_tree_inl0_pub1.pl
@@ -16,7 +16,7 @@ my $default_vltmt_threads = $Self->get_default_vltmt_threads();
 compile(
     verilator_flags2 => ['--stats', "$Self->{t_dir}/$Self->{name}.vlt"],
     # Force 3 threads even if we have fewer cores
-    threads => $Self->{vltmt} ? $default_vltmt_threads : 0
+    threads => $Self->{vltmt} ? $default_vltmt_threads : 1
     );
 
 sub checkRelativeRefs {
diff --git a/test_regress/t/t_lib_prot_shared.pl b/test_regress/t/t_lib_prot_shared.pl
index cd8b2a1c6..b7fab1e92 100755
--- a/test_regress/t/t_lib_prot_shared.pl
+++ b/test_regress/t/t_lib_prot_shared.pl
@@ -61,7 +61,7 @@ while (1) {
                              "-LDFLAGS",
                              "'-Wl,-rpath,$abs_secret_dir -L$abs_secret_dir -l$secret_prefix'"],
         xsim_flags2 => ["$secret_dir/secret.sv"],
-        threads => $Self->{vltmt} ? 1 : 0,
+        threads => 1,
         context_threads => $Self->{vltmt} ? 6 : 1
         );
 
diff --git a/test_regress/t/t_split_var_0.pl b/test_regress/t/t_split_var_0.pl
index 0441871e4..321950306 100755
--- a/test_regress/t/t_split_var_0.pl
+++ b/test_regress/t/t_split_var_0.pl
@@ -15,7 +15,7 @@ scenarios(simulator => 1);
 # So use 6 threads here though it's not optimal in performace wise, but ok.
 compile(
     verilator_flags2 => ['--stats', "$Self->{t_dir}/t_split_var_0.vlt"],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_split_var_2_trace.pl b/test_regress/t/t_split_var_2_trace.pl
index 35d20007a..9395d8cc5 100755
--- a/test_regress/t/t_split_var_2_trace.pl
+++ b/test_regress/t/t_split_var_2_trace.pl
@@ -16,7 +16,7 @@ top_filename("t/t_split_var_0.v");
 # So use 6 threads here though it's not optimal in performace wise, but ok.
 compile(
     verilator_flags2 => ['--cc --trace --stats +define+TEST_ATTRIBUTES'],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_threads_counter_0.pl b/test_regress/t/t_threads_counter_0.pl
index b93572929..6c3744eeb 100755
--- a/test_regress/t/t_threads_counter_0.pl
+++ b/test_regress/t/t_threads_counter_0.pl
@@ -14,7 +14,7 @@ top_filename("t/t_threads_counter.v");
 
 compile(
     verilator_flags2 => ['--cc'],
-    threads => 0,
+    threads => 1,
     );
 
 execute(
diff --git a/test_regress/t/t_threads_crazy_context.pl b/test_regress/t/t_threads_crazy_context.pl
index 8e28bb87a..6a3f1512e 100755
--- a/test_regress/t/t_threads_crazy_context.pl
+++ b/test_regress/t/t_threads_crazy_context.pl
@@ -18,7 +18,7 @@ top_filename("t/t_threads_crazy.v");
 
 compile(
     verilator_flags2 => ['--cc'],
-    threads => $Self->{vltmt} ? 2 : 0,
+    threads => $Self->{vltmt} ? 2 : 1,
     context_threads => 1024
     );
 
@@ -28,8 +28,6 @@ execute(
 
 if ($Self->{vltmt}) {
     file_grep($Self->{run_log_filename}, qr/System has \d+ hardware threads but simulation thread count set to 1024\. This will likely cause significant slowdown\./);
-} else {
-    file_grep($Self->{run_log_filename}, qr/Verilator run-time library built without VL_THREADS\. Ignoring call to 'VerilatedContext::threads' with argument 1024\./);
 }
 
 ok(1);
diff --git a/test_regress/t/t_timing_debug1.out b/test_regress/t/t_timing_debug1.out
index 792642e49..5775d0dde 100644
--- a/test_regress/t/t_timing_debug1.out
+++ b/test_regress/t/t_timing_debug1.out
@@ -32,6 +32,7 @@
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__stl
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__stl
 -V{t#,#}         No triggers active
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -61,8 +62,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -119,8 +122,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -156,8 +161,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -188,8 +195,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -238,8 +247,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -301,8 +312,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -342,8 +355,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -373,8 +388,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -428,8 +445,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -464,8 +483,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -495,8 +516,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -544,8 +567,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -580,8 +605,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -616,8 +643,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -647,8 +676,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -696,8 +727,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -732,8 +765,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -763,8 +798,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -834,8 +871,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -866,8 +905,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -902,8 +943,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -933,8 +976,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -988,8 +1033,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1024,8 +1071,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1055,8 +1104,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1090,8 +1141,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1139,8 +1192,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1175,8 +1230,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1206,8 +1263,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1255,8 +1314,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1291,8 +1352,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1356,8 +1419,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1387,8 +1452,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1442,8 +1509,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1478,8 +1547,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1509,8 +1580,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1558,8 +1631,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1598,8 +1673,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1629,8 +1706,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1678,8 +1757,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1714,8 +1795,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1745,8 +1828,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1794,8 +1879,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1855,8 +1942,10 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug1::eval_step
 -V{t#,#}+    Vt_timing_debug1___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval
 -V{t#,#}+    Vt_timing_debug1___024root___eval_triggers__act
@@ -1898,4 +1987,5 @@
 -V{t#,#}+    Vt_timing_debug1___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug1___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+    Vt_timing_debug1___024root___eval_final
diff --git a/test_regress/t/t_timing_debug2.out b/test_regress/t/t_timing_debug2.out
index 6243cc26c..bbb0b3fe2 100644
--- a/test_regress/t/t_timing_debug2.out
+++ b/test_regress/t/t_timing_debug2.out
@@ -60,6 +60,7 @@
 -V{t#,#}             Awaiting join of fork at: t/t_timing_class.v:209
 -V{t#,#}+      Vt_timing_debug2_t___eval_initial__TOP__t__7
 -V{t#,#}+    Vt_timing_debug2___024root___eval_settle
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -69,8 +70,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
 -V{t#,#}         Committing processes waiting for @([event] t.ec.e):
 -V{t#,#}           - Process waiting at t/t_timing_class.v:80
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -107,8 +110,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -174,8 +179,10 @@
 -V{t#,#}             Resuming: Process waiting at t/t_timing_class.v:29
 -V{t#,#}         Suspending process waiting for @([event] t::EventClass.e) at t/t_timing_class.v:29
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -230,8 +237,10 @@
 -V{t#,#}             Resuming: Process waiting at t/t_timing_class.v:29
 -V{t#,#}         Suspending process waiting for @([event] t::EventClass.e) at t/t_timing_class.v:29
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -305,8 +314,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -344,8 +355,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -401,8 +414,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -459,10 +474,12 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
 -V{t#,#}+        Vt_timing_debug2_t__03a__03aForkDelayClass::~
 -V{t#,#}+        Vt_timing_debug2_t__03a__03aForkClass::~
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -490,8 +507,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -521,8 +540,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -549,8 +570,10 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -577,9 +600,11 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_timing_debug2::eval_step
 -V{t#,#}+    Vt_timing_debug2___024root___eval_debug_assertions
 -V{t#,#}+        Vt_timing_debug2_t__03a__03aAssignDelayClass::~
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval
 -V{t#,#}+    Vt_timing_debug2___024root___eval_triggers__act
@@ -606,6 +631,7 @@
 -V{t#,#}+    Vt_timing_debug2___024root___dump_triggers__act
 -V{t#,#}         No triggers active
 -V{t#,#}+    Vt_timing_debug2___024root___timing_commit
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+    Vt_timing_debug2___024root___eval_final
 -V{t#,#}+        Vt_timing_debug2_t__03a__03aDelay40::~
 -V{t#,#}+        Vt_timing_debug2_t__03a__03aDelayClass::~
diff --git a/test_regress/t/t_trace_litendian.pl b/test_regress/t/t_trace_litendian.pl
index 5b7289295..3ecfa6bc6 100755
--- a/test_regress/t/t_trace_litendian.pl
+++ b/test_regress/t/t_trace_litendian.pl
@@ -15,7 +15,7 @@ scenarios(simulator => 1);
 # Strangely, asking for more threads makes it go away.
 compile(
     verilator_flags2 => ['--cc --trace --trace-params -Wno-LITENDIAN'],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_trace_litendian_fst.pl b/test_regress/t/t_trace_litendian_fst.pl
index 3e24bf901..754bea6fd 100755
--- a/test_regress/t/t_trace_litendian_fst.pl
+++ b/test_regress/t/t_trace_litendian_fst.pl
@@ -17,7 +17,7 @@ top_filename("t/t_trace_litendian.v");
 # Strangely, asking for more threads makes it go away.
 compile(
     verilator_flags2 => ['--cc --trace-fst --trace-params -Wno-LITENDIAN'],
-    threads => $Self->{vltmt} ? 6 : 0
+    threads => $Self->{vltmt} ? 6 : 1
     );
 
 execute(
diff --git a/test_regress/t/t_trace_litendian_fst_sc.pl b/test_regress/t/t_trace_litendian_fst_sc.pl
index b79e1e78f..40366a231 100755
--- a/test_regress/t/t_trace_litendian_fst_sc.pl
+++ b/test_regress/t/t_trace_litendian_fst_sc.pl
@@ -21,7 +21,7 @@ else {
     # Strangely, asking for more threads makes it go away.
     compile(
         verilator_flags2 => ['--sc --trace-fst --trace-params -Wno-LITENDIAN'],
-        threads => $Self->{vltmt} ? 6 : 0
+        threads => $Self->{vltmt} ? 6 : 1
         );
 
     execute(
diff --git a/test_regress/t/t_verilated_debug.out b/test_regress/t/t_verilated_debug.out
index 4227ea526..55cf9f490 100644
--- a/test_regress/t/t_verilated_debug.out
+++ b/test_regress/t/t_verilated_debug.out
@@ -13,13 +13,16 @@ internalsDump:
 -V{t#,#}+    Vt_verilated_debug___024root___eval_initial__TOP
   Data: w96: 000000aa 000000bb 000000cc 
 -V{t#,#}+    Vt_verilated_debug___024root___eval_settle
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_verilated_debug___024root___eval
 -V{t#,#}+    Vt_verilated_debug___024root___eval_triggers__act
 -V{t#,#}+    Vt_verilated_debug___024root___dump_triggers__act
 -V{t#,#}         No triggers active
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+++++TOP Evaluate Vt_verilated_debug::eval_step
 -V{t#,#}+    Vt_verilated_debug___024root___eval_debug_assertions
+-V{t#,#}MTask0 starting
 -V{t#,#}+ Eval
 -V{t#,#}+    Vt_verilated_debug___024root___eval
 -V{t#,#}+    Vt_verilated_debug___024root___eval_triggers__act
@@ -35,4 +38,5 @@ internalsDump:
 -V{t#,#}+    Vt_verilated_debug___024root___eval_triggers__act
 -V{t#,#}+    Vt_verilated_debug___024root___dump_triggers__act
 -V{t#,#}         No triggers active
+-V{t#,#}End-of-eval cleanup
 -V{t#,#}+    Vt_verilated_debug___024root___eval_final
diff --git a/verilator-config.cmake.in b/verilator-config.cmake.in
index 2210b3297..8c19a2711 100644
--- a/verilator-config.cmake.in
+++ b/verilator-config.cmake.in
@@ -79,8 +79,8 @@ endif()
 
 define_property(TARGET
   PROPERTY VERILATOR_THREADED
-  BRIEF_DOCS "Verilator multithreading enabled"
-  FULL_DOCS "Verilator multithreading enabled"
+  BRIEF_DOCS "Deprecated and has no effect (ignored)"
+  FULL_DOCS "Deprecated and has no effect (ignored)"
 )
 
 define_property(TARGET
@@ -262,11 +262,6 @@ function(verilate TARGET)
                      "${VCMAKE}" "${VCMAKE_COPY}"
                      DEPENDS "${VCMAKE}" VERBATIM)
 
-  if (${VERILATE_PREFIX}_THREADS)
-    # If any verilate() call specifies THREADS, define VL_THREADED in the final build
-    set_property(TARGET ${TARGET} PROPERTY VERILATOR_THREADED ON)
-  endif()
-
   if (${VERILATE_PREFIX}_COVERAGE)
     # If any verilate() call specifies COVERAGE, define VM_COVERAGE in the final build
     set_property(TARGET ${TARGET} PROPERTY VERILATOR_COVERAGE ON)
@@ -326,7 +321,6 @@ function(verilate TARGET)
   target_compile_definitions(${TARGET} PRIVATE
     VM_COVERAGE=$<BOOL:$<TARGET_PROPERTY:VERILATOR_COVERAGE>>
     VM_SC=$<BOOL:$<TARGET_PROPERTY:VERILATOR_SYSTEMC>>
-    $<$<BOOL:$<TARGET_PROPERTY:VERILATOR_THREADED>>:VL_THREADED>
     VM_TRACE=$<BOOL:$<TARGET_PROPERTY:VERILATOR_TRACE>>
     VM_TRACE_VCD=$<BOOL:$<TARGET_PROPERTY:VERILATOR_TRACE_VCD>>
     VM_TRACE_FST=$<BOOL:$<TARGET_PROPERTY:VERILATOR_TRACE_FST>>
@@ -336,11 +330,9 @@ function(verilate TARGET)
     ${${VERILATE_PREFIX}_USER_LDLIBS}
   )
 
-  if (${VERILATE_PREFIX}_THREADS OR ${VERILATE_PREFIX}_TRACE_THREADS)
-    target_link_libraries(${TARGET} PUBLIC
-      ${VERILATOR_MT_CFLAGS}
-    )
-  endif()
+  target_link_libraries(${TARGET} PUBLIC
+    ${VERILATOR_MT_CFLAGS}
+  )
 
   target_compile_features(${TARGET} PRIVATE cxx_std_11)