2 files changed, 27 insertions, 16 deletions

diff --git a/src/video_core/macro/macro_jit_x64.cpp b/src/video_core/macro/macro_jit_x64.cpp
index d4a97ec7b..79434a63c 100644
--- a/src/video_core/macro/macro_jit_x64.cpp
+++ b/src/video_core/macro/macro_jit_x64.cpp
@@ -56,11 +56,13 @@ void MacroJITx64Impl::Compile_ALU(Macro::Opcode opcode) {
     const bool valid_operation = !is_a_zero && !is_b_zero;
     const bool is_move_operation = !is_a_zero && is_b_zero;
     const bool has_zero_register = is_a_zero || is_b_zero;
+    const bool no_zero_reg_skip = opcode.alu_operation == Macro::ALUOperation::AddWithCarry ||
+                                  opcode.alu_operation == Macro::ALUOperation::SubtractWithBorrow;
 
     Xbyak::Reg32 src_a;
     Xbyak::Reg32 src_b;
 
-    if (!optimizer.zero_reg_skip) {
+    if (!optimizer.zero_reg_skip || no_zero_reg_skip) {
         src_a = Compile_GetRegister(opcode.src_a, RESULT);
         src_b = Compile_GetRegister(opcode.src_b, eax);
     } else {
@@ -183,7 +185,8 @@ void MacroJITx64Impl::Compile_AddImmediate(Macro::Opcode opcode) {
         opcode.result_operation == Macro::ResultOperation::MoveAndSetMethod) {
         if (next_opcode.has_value()) {
             const auto next = *next_opcode;
-            if (next.result_operation == Macro::ResultOperation::MoveAndSetMethod) {
+            if (next.result_operation == Macro::ResultOperation::MoveAndSetMethod &&
+                opcode.dst == next.dst) {
                 return;
             }
         }
@@ -270,14 +273,6 @@ void MacroJITx64Impl::Compile_ExtractShiftLeftRegister(Macro::Opcode opcode) {
     Compile_ProcessResult(opcode.result_operation, opcode.dst);
 }
 
-static u32 Read(Engines::Maxwell3D* maxwell3d, u32 method) {
-    return maxwell3d->GetRegisterValue(method);
-}
-
-static void Send(Engines::Maxwell3D* maxwell3d, Macro::MethodAddress method_address, u32 value) {
-    maxwell3d->CallMethodFromMME(method_address.address, value);
-}
-
 void MacroJITx64Impl::Compile_Read(Macro::Opcode opcode) {
     if (optimizer.zero_reg_skip && opcode.src_a == 0) {
         if (opcode.immediate == 0) {
@@ -295,15 +290,27 @@ void MacroJITx64Impl::Compile_Read(Macro::Opcode opcode) {
             sub(result, opcode.immediate * -1);
         }
     }
-    Common::X64::ABI_PushRegistersAndAdjustStack(*this, PersistentCallerSavedRegs(), 0);
-    mov(Common::X64::ABI_PARAM1, qword[STATE]);
-    mov(Common::X64::ABI_PARAM2, RESULT);
-    Common::X64::CallFarFunction(*this, &Read);
-    Common::X64::ABI_PopRegistersAndAdjustStack(*this, PersistentCallerSavedRegs(), 0);
-    mov(RESULT, Common::X64::ABI_RETURN.cvt32());
+
+    // Equivalent to Engines::Maxwell3D::GetRegisterValue:
+    if (optimizer.enable_asserts) {
+        Xbyak::Label pass_range_check;
+        cmp(RESULT, static_cast<u32>(Engines::Maxwell3D::Regs::NUM_REGS));
+        jb(pass_range_check);
+        int3();
+        L(pass_range_check);
+    }
+    mov(rax, qword[STATE]);
+    mov(RESULT,
+        dword[rax + offsetof(Engines::Maxwell3D, regs) +
+              offsetof(Engines::Maxwell3D::Regs, reg_array) + RESULT.cvt64() * sizeof(u32)]);
+
     Compile_ProcessResult(opcode.result_operation, opcode.dst);
 }
 
+static void Send(Engines::Maxwell3D* maxwell3d, Macro::MethodAddress method_address, u32 value) {
+    maxwell3d->CallMethodFromMME(method_address.address, value);
+}
+
 void Tegra::MacroJITx64Impl::Compile_Send(Xbyak::Reg32 value) {
     Common::X64::ABI_PushRegistersAndAdjustStack(*this, PersistentCallerSavedRegs(), 0);
     mov(Common::X64::ABI_PARAM1, qword[STATE]);
@@ -435,6 +442,9 @@ void MacroJITx64Impl::Compile() {
     // one if our register isn't "dirty"
     optimizer.optimize_for_method_move = true;
 
+    // Enable run-time assertions in JITted code
+    optimizer.enable_asserts = false;
+
     // Check to see if we can skip emitting certain instructions
     Optimizer_ScanFlags();
 
diff --git a/src/video_core/macro/macro_jit_x64.h b/src/video_core/macro/macro_jit_x64.h
index 51ec090b8..a180e7428 100644
--- a/src/video_core/macro/macro_jit_x64.h
+++ b/src/video_core/macro/macro_jit_x64.h
@@ -76,6 +76,7 @@ private:
         bool zero_reg_skip{};
         bool skip_dummy_addimmediate{};
         bool optimize_for_method_move{};
+        bool enable_asserts{};
     };
     OptimizerState optimizer{};