diff --git a/lib/YaeAchievementLib.vcxproj b/lib/YaeAchievementLib.vcxproj
index c81ff62..6fbf0d6 100644
--- a/lib/YaeAchievementLib.vcxproj
+++ b/lib/YaeAchievementLib.vcxproj
@@ -60,7 +60,7 @@
       <SDLCheck>true</SDLCheck>
       <PreprocessorDefinitions>_DEBUG;YAEACHIEVEMENTLIB_EXPORTS;_WINDOWS;_USRDLL;WIN32_LEAN_AND_MEAN;ZYDIS_STATIC_BUILD;ZYCORE_STATIC_BUILD;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>false</ConformanceMode>
-      <LanguageStandard>stdcpp20</LanguageStandard>
+      <LanguageStandard>stdcpplatest</LanguageStandard>
       <MultiProcessorCompilation>true</MultiProcessorCompilation>
     </ClCompile>
     <Link>
@@ -78,7 +78,7 @@
       <IntrinsicFunctions>true</IntrinsicFunctions>
       <PreprocessorDefinitions>_AMD64_;NDEBUG;YAEACHIEVEMENTLIB_EXPORTS;_WINDOWS;_USRDLL;WIN32_LEAN_AND_MEAN;ZYDIS_STATIC_BUILD;ZYCORE_STATIC_BUILD;%(PreprocessorDefinitions)</PreprocessorDefinitions>
       <ConformanceMode>false</ConformanceMode>
-      <LanguageStandard>stdcpp20</LanguageStandard>
+      <LanguageStandard>stdcpplatest</LanguageStandard>
       <MultiProcessorCompilation>true</MultiProcessorCompilation>
       <FavorSizeOrSpeed>Speed</FavorSizeOrSpeed>
       <SDLCheck>true</SDLCheck>
diff --git a/lib/src/dllmain.cpp b/lib/src/dllmain.cpp
index 3f1928c..a916390 100644
--- a/lib/src/dllmain.cpp
+++ b/lib/src/dllmain.cpp
@@ -1,5 +1,6 @@
 // ReSharper disable CppClangTidyCertErr33C
 #include <Windows.h>
+#include <print>
 #include <string>
 #include <future>
 #include <TlHelp32.h>
@@ -49,11 +50,11 @@ namespace Hook {
 			const auto headLength = _byteswap_ushort(packet->HeaderLength);
 			const auto dataLength = _byteswap_ulong(packet->DataLength);
 
-			printf("CmdId: %d\n", _byteswap_ushort(packet->CmdId));
-			printf("DataLength: %d\n", dataLength);
+			std::println("CmdId: {}", _byteswap_ushort(packet->CmdId));
+			std::println("DataLength: {}", dataLength);
 
 			const auto base64 = Util::Base64Encode(packet->Data + headLength, dataLength) + "\n";
-			printf("Base64: %s\n", base64.c_str());
+			std::println("Base64: {}", base64);
 
 #ifdef _DEBUG
 			system("pause");
@@ -137,7 +138,7 @@ DWORD __stdcall ThreadProc(LPVOID hInstance)
 	if (MessagePipe == INVALID_HANDLE_VALUE)
 	{
 #ifdef _DEBUG
-		printf("CreateFile failed: %d\n", GetLastError());
+		std::println("CreateFile failed: {}", GetLastError());
 #else
 		Util::Win32ErrorDialog(1001, GetLastError());
 		ExitProcess(0);
diff --git a/lib/src/il2cpp-init.cpp b/lib/src/il2cpp-init.cpp
index a14b0c6..65596eb 100644
--- a/lib/src/il2cpp-init.cpp
+++ b/lib/src/il2cpp-init.cpp
@@ -1,4 +1,5 @@
 #include <Windows.h>
+#include <print>
 #include <string>
 #include <vector>
 #include <iterator>
@@ -40,11 +41,11 @@ namespace
 		std::vector<ZydisDecodedOperand> Operands;
 	};
 
-	uintptr_t GetSection(LPCSTR name, size_t* sectionSize = nullptr)
+	std::span<uint8_t> GetSection(LPCSTR name)
 	{
 		using namespace Globals;
 		if (BaseAddress == 0)
-			return 0;
+			return {};
 
 		const auto dosHeader = (PIMAGE_DOS_HEADER)BaseAddress;
 		const auto ntHeader = (PIMAGE_NT_HEADERS)((uintptr_t)dosHeader + dosHeader->e_lfanew);
@@ -54,14 +55,13 @@ namespace
 		{
 			if (strcmp((char*)sectionHeader[i].Name, name) == 0)
 			{
-				if (sectionSize != nullptr) {
-					*sectionSize = sectionHeader[i].Misc.VirtualSize;
-				}
-				return BaseAddress + sectionHeader[i].VirtualAddress;
+				const auto sectionSize = sectionHeader[i].Misc.VirtualSize;
+				const auto virtualAddress = BaseAddress + sectionHeader[i].VirtualAddress;
+				return std::span(reinterpret_cast<uint8_t*>(virtualAddress), sectionSize);
 			}
 		}
 
-		return 0;
+		return {};
 	}
 
 	/// <summary>
@@ -148,7 +148,7 @@ namespace
 		for (const auto& instr : instructions)
 		{
 			if (instr.Instruction.mnemonic == ZYDIS_MNEMONIC_CALL) {
-				uint32_t destination = instr.RVA + instr.Instruction.length + instr.Operands[0].imm.value.s;
+				uint32_t destination = instr.Operands[0].imm.value.s + instr.RVA + instr.Instruction.length;
 				calls.insert(destination);
 			}
 		}
@@ -165,52 +165,50 @@ namespace
 
 	void ResolveCmdId()
 	{
-		size_t sectionSize;
-		const auto sectionAddress = GetSection("il2cpp", &sectionSize);
-		const auto sectionEnd = sectionAddress + sectionSize;
+		const auto il2cppSection = GetSection("il2cpp");
 
-		printf("Section Address: 0x%llX\n", sectionAddress);
-		printf("Section End: 0x%llX\n", sectionEnd);
+		std::println("Section Address: 0x{:X}", reinterpret_cast<uintptr_t>(il2cppSection.data()));
+		std::println("Section End: 0x{:X}", reinterpret_cast<uintptr_t>(il2cppSection.data() + il2cppSection.size()));
 
-		if (sectionAddress == 0)
+		if (il2cppSection.empty())
 			return; // message box?
 
-		const auto candidates = Util::PatternScanAll(sectionAddress, sectionEnd, "56 48 83 EC 20 48 89 D0 48 89 CE 80 3D ? ? ? ? 00");
-		printf("Candidates: %llu\n", candidates.size());
-
-		std::vector<std::vector<DecodedInstruction>> candidateInstructions;
-		std::ranges::transform(candidates, std::back_inserter(candidateInstructions), DecodeFunction);
+		const auto candidates = Util::PatternScanAll(il2cppSection, "56 48 83 EC 20 48 89 D0 48 89 CE 80 3D ? ? ? ? 00");
+		std::println("Candidates: {}", candidates.size());
 
 		std::vector<std::vector<DecodedInstruction>> filteredInstructions;
-		std::ranges::copy_if(candidateInstructions, std::back_inserter(filteredInstructions), [](const std::vector<DecodedInstruction>& instr) {
-			return GetDataReferenceCount(instr) == 5 && GetCallCount(instr) == 10 && GetUniqueCallCount(instr) == 6 && GetCmpImmCount(instr) == 5;
+		std::ranges::copy_if(
+			candidates | std::views::transform(DecodeFunction),
+			std::back_inserter(filteredInstructions),
+			[](const std::vector<DecodedInstruction>& instr) {
+			return GetDataReferenceCount(instr) == 5 && GetCallCount(instr) == 10 &&
+				GetUniqueCallCount(instr) == 6 && GetCmpImmCount(instr) == 5;
 		});
 
 		// should have only one result
 		if (filteredInstructions.size() != 1)
 		{
-			printf("Filtered Instructions: %llu\n", filteredInstructions.size());
+			std::println("Filtered Instructions: {}", filteredInstructions.size());
 			return;
 		}
 
 		const auto& instructions = filteredInstructions[0];
-		printf("RVA: 0x%08X\n", instructions.front().RVA);
+		std::println("RVA: 0x{:08X}", instructions.front().RVA);
 
 		// extract all the non-zero immediate values from the cmp instructions
-		std::decay_t<decltype(instructions)> cmpInstructions;
-		std::ranges::copy_if(instructions, std::back_inserter(cmpInstructions), [](const DecodedInstruction& instr) {
-			return instr.Instruction.mnemonic == ZYDIS_MNEMONIC_CMP && instr.Operands[1].type == ZYDIS_OPERAND_TYPE_IMMEDIATE && instr.Operands[1].imm.value.u;
-		});
-
 		std::vector<uint32_t> cmdIds;
-		std::ranges::transform(cmpInstructions, std::back_inserter(cmdIds), [](const DecodedInstruction& instr) {
-			return instr.Operands[1].imm.value.u;
+		std::ranges::for_each(instructions, [&cmdIds](const DecodedInstruction& instr) {
+			if (instr.Instruction.mnemonic == ZYDIS_MNEMONIC_CMP &&
+				instr.Operands[1].type == ZYDIS_OPERAND_TYPE_IMMEDIATE &&
+				instr.Operands[1].imm.value.u != 0) {
+				cmdIds.push_back(static_cast<uint32_t>(instr.Operands[1].imm.value.u));
+			}
 		});
 
 		for (const auto& cmdId : cmdIds)
 		{
-			printf("CmdId: %u\n", cmdId);
-			Globals::DynamicCmdIds.insert(cmdId);
+			std::println("CmdId: {}", cmdId);
+			Globals::DynamicCmdIds.insert(static_cast<uint16_t>(cmdId));
 		}
 
 
@@ -218,9 +216,9 @@ namespace
 
 	int32_t GetCallCount(uint8_t* target)
 	{
-		size_t sectionSize;
-		const auto sectionAddress = GetSection("il2cpp", &sectionSize);
-		const auto sectionEnd = sectionAddress + sectionSize;
+		const auto il2cppSection = GetSection("il2cpp");
+		const auto sectionAddress = reinterpret_cast<uintptr_t>(il2cppSection.data());
+		const auto sectionSize = il2cppSection.size();
 
 		int32_t count = 0;
 		const __m128i callOpcode = _mm_set1_epi8(0xE8);
@@ -283,12 +281,10 @@ namespace
 
 	uintptr_t Resolve_BitConverter_ToUInt16()
 	{
-		size_t sectionSize;
-		const auto sectionAddress = GetSection("il2cpp", &sectionSize);
-		const auto sectionEnd = sectionAddress + sectionSize;
+		const auto il2cppSection = GetSection("il2cpp");
 
-		printf("Section Address: 0x%llX\n", sectionAddress);
-		printf("Section End: 0x%llX\n", sectionEnd);
+		std::print("Section Address: 0x{:X}", reinterpret_cast<uintptr_t>(il2cppSection.data()));
+		std::println("Section End: 0x{:X}", reinterpret_cast<uintptr_t>(il2cppSection.data() + il2cppSection.size()));
 
 		/*
 			mov ecx, 0Fh
@@ -299,8 +295,8 @@ namespace
 			mov ecx, 5
 			call ThrowHelper.ThrowArgumentException
 		*/
-		auto candidates = Util::PatternScanAll(sectionAddress, sectionEnd, "B9 0F 00 00 00 E8 ? ? ? ? B9 0E 00 00 00 BA 16 00 00 00 E8 ? ? ? ? B9 05 00 00 00 E8 ? ? ? ?");
-		printf("Candidates: %llu\n", candidates.size());
+		auto candidates = Util::PatternScanAll(il2cppSection, "B9 0F 00 00 00 E8 ? ? ? ? B9 0E 00 00 00 BA 16 00 00 00 E8 ? ? ? ? B9 05 00 00 00 E8 ? ? ? ?");
+		std::println("Candidates: {}", candidates.size());
 
 		std::vector<uintptr_t> filteredEntries;
 		std::ranges::copy_if(candidates, std::back_inserter(filteredEntries), [](uintptr_t& entry) {
@@ -310,10 +306,10 @@ namespace
 
 		for (const auto& entry : filteredEntries)
 		{
-			printf("Entry: 0x%llX\n", entry);
+			std::println("Entry: 0x{:X}", entry);
 		}
 
-		printf("Looking for call counts...\n");
+		std::println("Looking for call counts...");
 		std::mutex mutex;
 		std::unordered_map<uintptr_t, int32_t> callCounts;
 		// find the call counts to candidate functions
@@ -333,7 +329,7 @@ namespace
 		uintptr_t targetEntry = 0;
 		for (const auto& [entry, count] : callCounts)
 		{
-			printf("Entry: 0x%llX, RVA: 0x%08llX, Count: %d\n", entry, entry - Globals::BaseAddress, count);
+			std::println("Entry: 0x{:X}, RVA: 0x{:08X}, Count: {}", entry, entry - Globals::BaseAddress, count);
 			if (count == 5) {
 				targetEntry = entry;
 			}
@@ -380,7 +376,7 @@ void InitIL2CPP()
 	resolveFuncFuture.get();
 	resolveCmdIdFuture.get();
 
-	printf("BaseAddress: 0x%llX\n", BaseAddress);
-	printf("IsCNREL: %d\n", IsCNREL);
-	printf("BitConverter_ToUInt16: 0x%llX\n", Offset.BitConverter_ToUInt16);
+	std::println("BaseAddress: 0x{:X}", BaseAddress);
+	std::println("IsCNREL: {:d}", IsCNREL);
+	std::println("BitConverter_ToUInt16: 0x{:X}", Offset.BitConverter_ToUInt16);
 }
diff --git a/lib/src/il2cpp-types.h b/lib/src/il2cpp-types.h
index c043e00..c667da7 100644
--- a/lib/src/il2cpp-types.h
+++ b/lib/src/il2cpp-types.h
@@ -1,5 +1,6 @@
 #pragma once
 #include <cstdint>
+#include <span>
 
 template <typename T>
 class Array
@@ -16,6 +17,10 @@ public:
 	T* data() {
 		return vector;
 	}
+
+	std::span<T> AsSpan() {
+		return { vector, max_length };
+	}
 };
 
 static_assert(alignof(Array<uint8_t>) == 8, "Array alignment is incorrect");
@@ -29,6 +34,10 @@ struct PacketMeta
 	uint16_t HeaderLength;
 	uint32_t DataLength;
 	uint8_t Data[1];
+
+	std::span<uint8_t> AsSpan() {
+		return {Data, DataLength};
+	}
 };
 #pragma pack(pop)
 
diff --git a/lib/src/util.cpp b/lib/src/util.cpp
index f90a1ec..23b89d4 100644
--- a/lib/src/util.cpp
+++ b/lib/src/util.cpp
@@ -1,5 +1,9 @@
 #include <string>
+#include <array>
+#include <ranges>
+#include <intrin.h>
 #include "util.h"
+
 #include "globals.h"
 
 #ifdef _DEBUG
@@ -11,12 +15,12 @@
 namespace
 {
 	struct HandleData {
-		DWORD pid;
-		HWND hwnd;
+		DWORD Pid;
+		HWND Hwnd;
 	};
 
 	bool IsMainWindow(HWND handle) {
-		return GetWindow(handle, GW_OWNER) == (HWND)0 && IsWindowVisible(handle) == TRUE;
+		return GetWindow(handle, GW_OWNER) == nullptr && IsWindowVisible(handle) == TRUE;
 	}
 
 	bool IsUnityWindow(HWND handle) {
@@ -29,16 +33,16 @@ namespace
 		HandleData& data = *(HandleData*)lParam;
 		DWORD pid = 0;
 		GetWindowThreadProcessId(handle, &pid);
-		if (data.pid != pid || !IsMainWindow(handle) || !IsUnityWindow(handle))
+		if (data.Pid != pid || !IsMainWindow(handle) || !IsUnityWindow(handle))
 			return TRUE;
-		data.hwnd = handle;
+		data.Hwnd = handle;
 		return FALSE;
 	}
 
-	std::tuple<std::vector<uint8_t>, std::vector<bool>> PatternToBytes(const char* pattern)
+	std::tuple<std::vector<uint8_t>, std::string> PatternToBytes(const char* pattern)
 	{
 		std::vector<uint8_t> bytes;
-		std::vector<bool> maskBytes;
+		std::string mask;
 
 		const auto start = const_cast<char*>(pattern);
 		const auto end = const_cast<char*>(pattern) + strlen(pattern);
@@ -49,14 +53,14 @@ namespace
 				if (*current == '?')
 					++current;
 				bytes.push_back(-1);
-				maskBytes.push_back(false);
+				mask.push_back('?');
 			}
 			else {
 				bytes.push_back(strtoul(current, &current, 16));
-				maskBytes.push_back(true);
+				mask.push_back('x');
 			}
 		}
-		return { bytes, maskBytes };
+		return { bytes, mask };
 	}
 
 }
@@ -69,17 +73,25 @@ namespace Util
 {
 	HWND FindMainWindowByPID(DWORD pid)
 	{
-		HandleData data = { pid, 0 };
+		HandleData data = { 
+			.Pid = pid,
+			.Hwnd = nullptr
+		};
 		EnumWindows(EnumWindowsCallback, (LPARAM)&data);
-		return data.hwnd;
+		return data.Hwnd;
 	}
 
-	std::string Base64Encode(BYTE const* buf, unsigned int bufLen)
+	std::string Base64Encode(std::span<uint8_t> data)
+	{
+		return Base64Encode(data.data(), data.size());
+	}
+
+	std::string Base64Encode(uint8_t const* buf, size_t bufLen)
 	{
 		std::string ret;
 		int i = 0;
-		BYTE char_array_3[3];
-		BYTE char_array_4[4];
+		uint8_t char_array_3[3];
+		uint8_t char_array_4[4];
 		while (bufLen--) {
 			char_array_3[i++] = *buf++;
 			if (i == 3) {
@@ -126,51 +138,67 @@ namespace Util
 		ErrorDialog("YaeAchievement", msg.c_str());
 	}
 
-	uintptr_t PatternScan(uintptr_t start, uintptr_t end, const char* pattern)
-	{
-		const auto [patternBytes, patternMask] = PatternToBytes(pattern);
-		const auto scanBytes = reinterpret_cast<uint8_t*>(start);
-
-		const auto patternSize = patternBytes.size();
-		const auto pBytes = patternBytes.data();
-
-		for (auto i = 0ul; i < end - start - patternSize; ++i) {
-			bool found = true;
-			for (auto j = 0ul; j < patternSize; ++j) {
-				if (scanBytes[i + j] != pBytes[j] && patternMask[j]) {
-					found = false;
-					break;
-				}
-			}
-			if (found) {
-				return reinterpret_cast<uintptr_t>(&scanBytes[i]);
-			}
-		}
-
-		return 0;
-	}
-
-	std::vector<uintptr_t> PatternScanAll(uintptr_t start, uintptr_t end, const char* pattern)
+	std::vector<uintptr_t> PatternScanAll(std::span<uint8_t> bytes, const char* pattern)
 	{
 		std::vector<uintptr_t> results;
 		const auto [patternBytes, patternMask] = PatternToBytes(pattern);
-		const auto scanBytes = reinterpret_cast<uint8_t*>(start);
+		constexpr std::size_t chunkSize = 16;
 
-		const auto patternSize = patternBytes.size();
-		const auto pBytes = patternBytes.data();
+		const auto maskCount = static_cast<std::size_t>(std::ceil(patternMask.size() / chunkSize));
+		std::array<int32_t, 32> masks{};
 
-		for (auto i = 0ul; i < end - start - patternSize; ++i) {
-			bool found = true;
-			for (auto j = 0ul; j < patternSize; ++j) {
-				if (scanBytes[i + j] != pBytes[j] && patternMask[j]) {
-					found = false;
-					break;
+		auto chunks = patternMask | std::views::chunk(chunkSize);
+		for (std::size_t i = 0; auto chunk : chunks) {
+			int32_t mask = 0;
+			for (std::size_t j = 0; j < chunk.size(); ++j) {
+				if (chunk[j] == 'x') {
+					mask |= 1 << j;
 				}
 			}
-			if (found) {
-				results.push_back(reinterpret_cast<uintptr_t>(&scanBytes[i]));
-				i += patternSize - 1;
+			masks[i++] = mask;
+		}
+
+		__m128i xmm1 = _mm_loadu_si128(reinterpret_cast<const __m128i*>(patternBytes.data()));
+		__m128i xmm2, xmm3, mask;
+
+		auto pData = bytes.data();
+		const auto end = pData + bytes.size() - patternMask.size();
+
+		while (pData < end)
+		{
+			_mm_prefetch(reinterpret_cast<const char*>(pData + 64), _MM_HINT_NTA);
+
+			if (patternBytes[0] == pData[0])
+			{
+				xmm2 = _mm_loadu_si128(reinterpret_cast<const __m128i*>(pData));
+				mask = _mm_cmpeq_epi8(xmm1, xmm2);
+
+				if ((_mm_movemask_epi8(mask) & masks[0]) == masks[0])
+				{
+					bool found = true;
+					for (int i = 1; i < maskCount; ++i)
+					{
+						xmm2 = _mm_loadu_si128(reinterpret_cast<const __m128i*>(pData + i * chunkSize));
+						xmm3 = _mm_loadu_si128(reinterpret_cast<const __m128i*>(patternBytes.data() + i * chunkSize));
+						mask = _mm_cmpeq_epi8(xmm2, xmm3);
+						if ((_mm_movemask_epi8(mask) & masks[i]) != masks[i])
+						{
+							found = false;
+							break;
+						}
+					}
+
+
+					if (found) {
+						results.push_back(reinterpret_cast<uintptr_t>(pData));
+					}
+
+				}
+
+
 			}
+
+			++pData;
 		}
 
 		return results;
diff --git a/lib/src/util.h b/lib/src/util.h
index 8346e1b..e60cf32 100644
--- a/lib/src/util.h
+++ b/lib/src/util.h
@@ -3,16 +3,17 @@
 #include <Windows.h>
 #include <type_traits>
 #include <vector>
+#include <span>
 
 namespace Util
 {
 	HWND FindMainWindowByPID(DWORD pid);
-	std::string Base64Encode(BYTE const* buf, unsigned int bufLen);
+	std::string Base64Encode(std::span<uint8_t> data);
+	std::string Base64Encode(uint8_t const* buf, size_t bufLen);
 
 	void ErrorDialog(LPCSTR title, LPCSTR msg);
 	void ErrorDialog(LPCSTR msg);
 	void Win32ErrorDialog(DWORD code, DWORD winerrcode);
 
-	uintptr_t PatternScan(uintptr_t start, uintptr_t end, const char* pattern);
-	std::vector<uintptr_t> PatternScanAll(uintptr_t start, uintptr_t end, const char* pattern);
+	std::vector<uintptr_t> PatternScanAll(std::span<uint8_t> bytes, const char* pattern);
 }
\ No newline at end of file