use much faster exp2/cos approximations in ffmpeg, large decrease in cpu usage on my machine on decoder thread

properly byteswap r13 for spinlock
Add PPCOpcodeBits
stub out broken fpscr updating in ppc_hir_builder. it's just code that repeatedly does nothing right now.
add note about 0 opcode bytes being executed to ppc_frontend
Add assert to check that function end is greater than function start, can happen with malformed functions
Disable prefetch and cachecontrol by default, automatic hardware prefetchers already do the job for the most part
minor cleanup in simplification_pass, dont loop optimizations, let the pass manager do it for us
Add experimental "delay_via_maybeyield" cvar, which uses MaybeYield to "emulate" the db16cyc instruction
Add much faster/simpler way of directly calling guest functions, no longer have to do a byte by byte search through the generated code
Generate label string ids on the fly
Fix unused function warnings for prefetch on clang, fix many other clang warnings
Eliminated majority of CallNativeSafes by replacing them with naive generic code paths.
^ Vector rotate left, vector shift left, vector shift right, vector shift arithmetic right, and vector average are included
These naive paths are implemented small loops that stash the two inputs to the stack and load them in gprs from there, they are not particularly fast but should be an order of magnitude faster than callnativesafe
to a host function, which would involve a call, stashing all volatile registers, an indirect call, potentially setting up a stack frame for the arrays that the inputs get stashed to, the actual operations, a return, loading all volatile registers, a return, etc
Added the fast SHR_V128 path back in
Implement signed vector average byte, signed vector average word. previously we were emitting no code for them. signed vector average byte appears in many games
Fix bug with signed vector average 32, we were doing unsigned shift, turning negative values into big positive ones potentially

src/xenia/cpu/compiler/passes/finalization_pass.cc

@@ -41,18 +41,6 @@ bool FinalizationPass::Run(HIRBuilder* builder) {
     block->ordinal = block_ordinal++;
 
     // Ensure all labels have names.
-    auto label = block->label_head;
-    while (label) {
-      if (!label->name) {
-        const size_t label_len = 6 + 4;
-        char* name = reinterpret_cast<char*>(arena->Alloc(label_len + 1, 1));
-        assert_true(label->id <= 9999);
-        auto end = fmt::format_to_n(name, label_len, "_label{}", label->id);
-        name[end.size] = '\0';
-        label->name = name;
-      }
-      label = label->next;
-    }
 
     // Remove unneeded jumps.
     auto tail = block->instr_tail;

src/xenia/cpu/compiler/passes/simplification_pass.cc

@@ -23,52 +23,6 @@ using namespace xe::cpu::hir;
 using xe::cpu::hir::HIRBuilder;
 using xe::cpu::hir::Instr;
 using xe::cpu::hir::Value;
-using vmask_portion_t = uint64_t;
-template <uint32_t Ndwords>
-struct Valuemask_t {
-  vmask_portion_t bits[Ndwords];
-
-  static Valuemask_t create_empty(vmask_portion_t fill = 0) {
-    Valuemask_t result;
-    for (uint32_t i = 0; i < Ndwords; ++i) {
-      result.bits[i] = fill;
-    }
-    return result;
-  }
-  template <typename TCallable>
-  Valuemask_t operate(TCallable&& oper) const {
-    Valuemask_t result = create_empty();
-
-    for (uint32_t i = 0; i < Ndwords; ++i) {
-      result.bits[i] = oper(bits[i]);
-    }
-    return result;
-  }
-  template <typename TCallable>
-  Valuemask_t operate(TCallable&& oper, Valuemask_t other) const {
-    Valuemask_t result = create_empty();
-
-    for (uint32_t i = 0; i < Ndwords; ++i) {
-      result.bits[i] = oper(bits[i], other.bits[i]);
-    }
-    return result;
-  }
-  Valuemask_t operator&(ValueMask other) const {
-    return operate([](vmask_portion_t x, vmask_portion_t y) { return x & y; },
-                   other);
-  }
-  Valuemask_t operator|(ValueMask other) const {
-    return operate([](vmask_portion_t x, vmask_portion_t y) { return x | y; },
-                   other);
-  }
-  Valuemask_t operator^(ValueMask other) const {
-    return operate([](vmask_portion_t x, vmask_portion_t y) { return x ^ y; },
-                   other);
-  }
-  Valuemask_t operator~() const {
-    return operate([](vmask_portion_t x) { return ~x; }, other);
-  }
-};
 
 SimplificationPass::SimplificationPass() : ConditionalGroupSubpass() {}
 
@@ -76,17 +30,13 @@ SimplificationPass::~SimplificationPass() {}
 
 bool SimplificationPass::Run(HIRBuilder* builder, bool& result) {
   result = false;
-  bool iter_result = false;
 
-  do {
-    iter_result = false;
-    iter_result |= SimplifyBitArith(builder);
-    iter_result |= EliminateConversions(builder);
-    iter_result |= SimplifyAssignments(builder);
-    iter_result |= SimplifyBasicArith(builder);
-    iter_result |= SimplifyVectorOps(builder);
-    result |= iter_result;
-  } while (iter_result);
+  result |= SimplifyBitArith(builder);
+  result |= EliminateConversions(builder);
+  result |= SimplifyAssignments(builder);
+  result |= SimplifyBasicArith(builder);
+  result |= SimplifyVectorOps(builder);
+
   return true;
 }
 // simplifications that apply to both or and xor
@@ -735,7 +685,9 @@ bool SimplificationPass::CheckAdd(hir::Instr* i, hir::HIRBuilder* builder) {
     auto [added_constant_neg, added_var_neg] =
         i->BinaryValueArrangeAsConstAndVar();
 
-    if (!added_constant_neg) return false;
+    if (!added_constant_neg) {
+      return false;
+    }
     if (added_constant_neg->AsUint64() &
         GetScalarSignbitMask(added_constant_neg->type)) {
       // adding a value that has its signbit set!
@@ -882,11 +834,6 @@ bool SimplificationPass::CheckScalarConstCmp(hir::Instr* i,
 
     } else if (cmpop == OPCODE_COMPARE_UGT) {
       // impossible, cannot be greater than mask
-
-      /* i->Replace(&OPCODE_ASSIGN_info, 0);
-      i->set_src1(builder->LoadZeroInt8());
-      return true;
-      */
       constant_replacement = builder->LoadZeroInt8();
 
     } else if (cmpop == OPCODE_COMPARE_ULE) {  // less than or equal to mask =
@@ -914,9 +861,9 @@ bool SimplificationPass::CheckIsTrueIsFalse(hir::Instr* i,
   bool istrue = i->opcode == &OPCODE_COMPARE_NE_info;
   bool isfalse = i->opcode == &OPCODE_COMPARE_EQ_info;
 
-  auto [input_cosntant, input] = i->BinaryValueArrangeAsConstAndVar();
+  auto [input_constant, input] = i->BinaryValueArrangeAsConstAndVar();
 
-  if (!input_cosntant || input_cosntant->AsUint64() != 0) {
+  if (!input_constant || input_constant->AsUint64() != 0) {
     return false;
   }
 
@@ -957,12 +904,6 @@ bool SimplificationPass::CheckIsTrueIsFalse(hir::Instr* i,
     }
   }
 
-  /* Instr* input_def = input->def;
-   if (!input_def) {
-     return false;
-   }
-
-   input_def = input_def->GetDestDefSkipAssigns();*/
   return false;
 }
 bool SimplificationPass::CheckSHRByConst(hir::Instr* i,