diff --git a/GPU/D3D11/GPU_D3D11.cpp b/GPU/D3D11/GPU_D3D11.cpp
index e14b1b1499..5dbe449087 100644
--- a/GPU/D3D11/GPU_D3D11.cpp
+++ b/GPU/D3D11/GPU_D3D11.cpp
@@ -289,44 +289,6 @@ void GPU_D3D11::CopyDisplayToOutput() {
 	gstate_c.Dirty(DIRTY_TEXTURE_IMAGE);
 }
 
-// Maybe should write this in ASM...
-void GPU_D3D11::FastRunLoop(DisplayList &list) {
-	PROFILE_THIS_SCOPE("gpuloop");
-	const CommandInfo *cmdInfo = cmdInfo_;
-	int dc = downcount;
-	for (; dc > 0; --dc) {
-		// We know that display list PCs have the upper nibble == 0 - no need to mask the pointer
-		const u32 op = *(const u32 *)(Memory::base + list.pc);
-		const u32 cmd = op >> 24;
-		const CommandInfo &info = cmdInfo[cmd];
-		const u32 diff = op ^ gstate.cmdmem[cmd];
-		if (diff == 0) {
-			if (info.flags & FLAG_EXECUTE) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			}
-		} else {
-			uint64_t flags = info.flags;
-			if (flags & FLAG_FLUSHBEFOREONCHANGE) {
-				drawEngine_.Flush();
-			}
-			gstate.cmdmem[cmd] = op;
-			if (flags & (FLAG_EXECUTE | FLAG_EXECUTEONCHANGE)) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			} else {
-				uint64_t dirty = flags >> 8;
-				if (dirty)
-					gstate_c.Dirty(dirty);
-			}
-		}
-		list.pc += 4;
-	}
-	downcount = 0;
-}
-
 void GPU_D3D11::FinishDeferred() {
 	// This finishes reading any vertex data that is pending.
 	drawEngine_.FinishDeferred();
diff --git a/GPU/D3D11/GPU_D3D11.h b/GPU/D3D11/GPU_D3D11.h
index 23d5582759..aadaef4556 100644
--- a/GPU/D3D11/GPU_D3D11.h
+++ b/GPU/D3D11/GPU_D3D11.h
@@ -66,7 +66,6 @@ public:
 	void EndHostFrame() override;
 
 protected:
-	void FastRunLoop(DisplayList &list) override;
 	void FinishDeferred() override;
 
 private:
diff --git a/GPU/Directx9/GPU_DX9.cpp b/GPU/Directx9/GPU_DX9.cpp
index 173f7dc004..32c03fd030 100644
--- a/GPU/Directx9/GPU_DX9.cpp
+++ b/GPU/Directx9/GPU_DX9.cpp
@@ -265,44 +265,6 @@ void GPU_DX9::CopyDisplayToOutput() {
 	gstate_c.Dirty(DIRTY_TEXTURE_IMAGE);
 }
 
-// Maybe should write this in ASM...
-void GPU_DX9::FastRunLoop(DisplayList &list) {
-	PROFILE_THIS_SCOPE("gpuloop");
-	const CommandInfo *cmdInfo = cmdInfo_;
-	int dc = downcount;
-	for (; dc > 0; --dc) {
-		// We know that display list PCs have the upper nibble == 0 - no need to mask the pointer
-		const u32 op = *(const u32 *)(Memory::base + list.pc);
-		const u32 cmd = op >> 24;
-		const CommandInfo &info = cmdInfo[cmd];
-		const u32 diff = op ^ gstate.cmdmem[cmd];
-		if (diff == 0) {
-			if (info.flags & FLAG_EXECUTE) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			}
-		} else {
-			uint64_t flags = info.flags;
-			if (flags & FLAG_FLUSHBEFOREONCHANGE) {
-				drawEngine_.Flush();
-			}
-			gstate.cmdmem[cmd] = op;
-			if (flags & (FLAG_EXECUTE | FLAG_EXECUTEONCHANGE)) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			} else {
-				uint64_t dirty = flags >> 8;
-				if (dirty)
-					gstate_c.Dirty(dirty);
-			}
-		}
-		list.pc += 4;
-	}
-	downcount = 0;
-}
-
 void GPU_DX9::FinishDeferred() {
 	// This finishes reading any vertex data that is pending.
 	drawEngine_.FinishDeferred();
diff --git a/GPU/Directx9/GPU_DX9.h b/GPU/Directx9/GPU_DX9.h
index 45cc632c63..2681bd4c79 100644
--- a/GPU/Directx9/GPU_DX9.h
+++ b/GPU/Directx9/GPU_DX9.h
@@ -66,7 +66,6 @@ public:
 	void BeginHostFrame() override;
 
 protected:
-	void FastRunLoop(DisplayList &list) override;
 	void FinishDeferred() override;
 
 private:
diff --git a/GPU/GLES/GPU_GLES.cpp b/GPU/GLES/GPU_GLES.cpp
index d0290c5e5f..44962d935a 100644
--- a/GPU/GLES/GPU_GLES.cpp
+++ b/GPU/GLES/GPU_GLES.cpp
@@ -481,44 +481,6 @@ void GPU_GLES::CopyDisplayToOutput() {
 #endif
 }
 
-// Maybe should write this in ASM...
-void GPU_GLES::FastRunLoop(DisplayList &list) {
-	PROFILE_THIS_SCOPE("gpuloop");
-	const CommandInfo *cmdInfo = cmdInfo_;
-	int dc = downcount;
-	for (; dc > 0; --dc) {
-		// We know that display list PCs have the upper nibble == 0 - no need to mask the pointer
-		const u32 op = *(const u32 *)(Memory::base + list.pc);
-		const u32 cmd = op >> 24;
-		const CommandInfo &info = cmdInfo[cmd];
-		const u32 diff = op ^ gstate.cmdmem[cmd];
-		if (diff == 0) {
-			if (info.flags & FLAG_EXECUTE) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			}
-		} else {
-			uint64_t flags = info.flags;
-			if (flags & FLAG_FLUSHBEFOREONCHANGE) {
-				drawEngine_.Flush();
-			}
-			gstate.cmdmem[cmd] = op;
-			if (flags & (FLAG_EXECUTE | FLAG_EXECUTEONCHANGE)) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			} else {
-				uint64_t dirty = flags >> 8;
-				if (dirty)
-					gstate_c.Dirty(dirty);
-			}
-		}
-		list.pc += 4;
-	}
-	downcount = 0;
-}
-
 void GPU_GLES::FinishDeferred() {
 	// This finishes reading any vertex data that is pending.
 	drawEngine_.FinishDeferred();
diff --git a/GPU/GLES/GPU_GLES.h b/GPU/GLES/GPU_GLES.h
index 9c3a4ada43..b81f349dd5 100644
--- a/GPU/GLES/GPU_GLES.h
+++ b/GPU/GLES/GPU_GLES.h
@@ -71,7 +71,6 @@ public:
 	void EndHostFrame() override;
 
 protected:
-	void FastRunLoop(DisplayList &list) override;
 	void FinishDeferred() override;
 
 private:
diff --git a/GPU/GPUCommon.cpp b/GPU/GPUCommon.cpp
index cbf22a9c28..fc9bf6b62a 100644
--- a/GPU/GPUCommon.cpp
+++ b/GPU/GPUCommon.cpp
@@ -965,6 +965,44 @@ bool GPUCommon::InterpretList(DisplayList &list) {
 	return gpuState == GPUSTATE_DONE || gpuState == GPUSTATE_ERROR;
 }
 
+// Maybe should write this in ASM...
+void GPUCommon::FastRunLoop(DisplayList &list) {
+	PROFILE_THIS_SCOPE("gpuloop");
+	const CommandInfo *cmdInfo = cmdInfo_;
+	int dc = downcount;
+	for (; dc > 0; --dc) {
+		// We know that display list PCs have the upper nibble == 0 - no need to mask the pointer
+		const u32 op = *(const u32 *)(Memory::base + list.pc);
+		const u32 cmd = op >> 24;
+		const CommandInfo &info = cmdInfo[cmd];
+		const u32 diff = op ^ gstate.cmdmem[cmd];
+		if (diff == 0) {
+			if (info.flags & FLAG_EXECUTE) {
+				downcount = dc;
+				(this->*info.func)(op, diff);
+				dc = downcount;
+			}
+		} else {
+			uint64_t flags = info.flags;
+			if (flags & FLAG_FLUSHBEFOREONCHANGE) {
+				drawEngineCommon_->DispatchFlush();
+			}
+			gstate.cmdmem[cmd] = op;
+			if (flags & (FLAG_EXECUTE | FLAG_EXECUTEONCHANGE)) {
+				downcount = dc;
+				(this->*info.func)(op, diff);
+				dc = downcount;
+			} else {
+				uint64_t dirty = flags >> 8;
+				if (dirty)
+					gstate_c.Dirty(dirty);
+			}
+		}
+		list.pc += 4;
+	}
+	downcount = 0;
+}
+
 void GPUCommon::BeginFrame() {
 	immCount_ = 0;
 	if (dumpNextFrame_) {
diff --git a/GPU/GPUCommon.h b/GPU/GPUCommon.h
index 2c99e2aaaf..e83c499d79 100644
--- a/GPU/GPUCommon.h
+++ b/GPU/GPUCommon.h
@@ -265,8 +265,8 @@ protected:
 
 	void BeginFrame() override;
 
-	// To avoid virtual calls to PreExecuteOp().
-	virtual void FastRunLoop(DisplayList &list) = 0;
+	virtual void FastRunLoop(DisplayList &list);
+
 	void SlowRunLoop(DisplayList &list);
 	void UpdatePC(u32 currentPC, u32 newPC);
 	void UpdateState(GPURunState state);
diff --git a/GPU/Vulkan/GPU_Vulkan.cpp b/GPU/Vulkan/GPU_Vulkan.cpp
index 1f8fa0bc57..a95e93d911 100644
--- a/GPU/Vulkan/GPU_Vulkan.cpp
+++ b/GPU/Vulkan/GPU_Vulkan.cpp
@@ -376,44 +376,6 @@ void GPU_Vulkan::CopyDisplayToOutput() {
 	gstate_c.Dirty(DIRTY_TEXTURE_IMAGE);
 }
 
-// Maybe should write this in ASM...
-void GPU_Vulkan::FastRunLoop(DisplayList &list) {
-	PROFILE_THIS_SCOPE("gpuloop");
-	const CommandInfo *cmdInfo = cmdInfo_;
-	int dc = downcount;
-	for (; dc > 0; --dc) {
-		// We know that display list PCs have the upper nibble == 0 - no need to mask the pointer
-		const u32 op = *(const u32 *)(Memory::base + list.pc);
-		const u32 cmd = op >> 24;
-		const CommandInfo &info = cmdInfo[cmd];
-		const u32 diff = op ^ gstate.cmdmem[cmd];
-		if (diff == 0) {
-			if (info.flags & FLAG_EXECUTE) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			}
-		} else {
-			uint64_t flags = info.flags;
-			if (flags & FLAG_FLUSHBEFOREONCHANGE) {
-				drawEngine_.Flush();
-			}
-			gstate.cmdmem[cmd] = op;
-			if (flags & (FLAG_EXECUTE | FLAG_EXECUTEONCHANGE)) {
-				downcount = dc;
-				(this->*info.func)(op, diff);
-				dc = downcount;
-			} else {
-				uint64_t dirty = flags >> 8;
-				if (dirty)
-					gstate_c.Dirty(dirty);
-			}
-		}
-		list.pc += 4;
-	}
-	downcount = 0;
-}
-
 void GPU_Vulkan::FinishDeferred() {
 	drawEngine_.FinishDeferred();
 }
diff --git a/GPU/Vulkan/GPU_Vulkan.h b/GPU/Vulkan/GPU_Vulkan.h
index 2bb8b3cf26..670ff9487b 100644
--- a/GPU/Vulkan/GPU_Vulkan.h
+++ b/GPU/Vulkan/GPU_Vulkan.h
@@ -71,7 +71,6 @@ public:
 	}
 
 protected:
-	void FastRunLoop(DisplayList &list) override;
 	void FinishDeferred() override;
 
 private: