12 files changed, 17 insertions, 385 deletions

diff --git a/src/common/CMakeLists.txt b/src/common/CMakeLists.txt
index 5d781cd77..aeaf8e81f 100644
--- a/src/common/CMakeLists.txt
+++ b/src/common/CMakeLists.txt
@@ -108,7 +108,6 @@ add_library(common STATIC
     bit_util.h
     cityhash.cpp
     cityhash.h
-    color.h
     common_funcs.h
     common_paths.h
     common_types.h
diff --git a/src/common/bit_util.h b/src/common/bit_util.h
index 29f59a9a3..685e7fc9b 100644
--- a/src/common/bit_util.h
+++ b/src/common/bit_util.h
@@ -22,82 +22,6 @@ template <typename T>
 }
 
 #ifdef _MSC_VER
-[[nodiscard]] inline u32 CountLeadingZeroes32(u32 value) {
-    unsigned long leading_zero = 0;
-
-    if (_BitScanReverse(&leading_zero, value) != 0) {
-        return 31 - leading_zero;
-    }
-
-    return 32;
-}
-
-[[nodiscard]] inline u32 CountLeadingZeroes64(u64 value) {
-    unsigned long leading_zero = 0;
-
-    if (_BitScanReverse64(&leading_zero, value) != 0) {
-        return 63 - leading_zero;
-    }
-
-    return 64;
-}
-#else
-[[nodiscard]] inline u32 CountLeadingZeroes32(u32 value) {
-    if (value == 0) {
-        return 32;
-    }
-
-    return static_cast<u32>(__builtin_clz(value));
-}
-
-[[nodiscard]] inline u32 CountLeadingZeroes64(u64 value) {
-    if (value == 0) {
-        return 64;
-    }
-
-    return static_cast<u32>(__builtin_clzll(value));
-}
-#endif
-
-#ifdef _MSC_VER
-[[nodiscard]] inline u32 CountTrailingZeroes32(u32 value) {
-    unsigned long trailing_zero = 0;
-
-    if (_BitScanForward(&trailing_zero, value) != 0) {
-        return trailing_zero;
-    }
-
-    return 32;
-}
-
-[[nodiscard]] inline u32 CountTrailingZeroes64(u64 value) {
-    unsigned long trailing_zero = 0;
-
-    if (_BitScanForward64(&trailing_zero, value) != 0) {
-        return trailing_zero;
-    }
-
-    return 64;
-}
-#else
-[[nodiscard]] inline u32 CountTrailingZeroes32(u32 value) {
-    if (value == 0) {
-        return 32;
-    }
-
-    return static_cast<u32>(__builtin_ctz(value));
-}
-
-[[nodiscard]] inline u32 CountTrailingZeroes64(u64 value) {
-    if (value == 0) {
-        return 64;
-    }
-
-    return static_cast<u32>(__builtin_ctzll(value));
-}
-#endif
-
-#ifdef _MSC_VER
 
 [[nodiscard]] inline u32 MostSignificantBit32(const u32 value) {
     unsigned long result;
diff --git a/src/common/color.h b/src/common/color.h
deleted file mode 100644
index bbcac858e..000000000
--- a/src/common/color.h
+++ /dev/null
@@ -1,271 +0,0 @@
-// Copyright 2014 Citra Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#pragma once
-
-#include <cstring>
-
-#include "common/common_types.h"
-#include "common/swap.h"
-#include "common/vector_math.h"
-
-namespace Common::Color {
-
-/// Convert a 1-bit color component to 8 bit
-[[nodiscard]] constexpr u8 Convert1To8(u8 value) {
-    return value * 255;
-}
-
-/// Convert a 4-bit color component to 8 bit
-[[nodiscard]] constexpr u8 Convert4To8(u8 value) {
-    return (value << 4) | value;
-}
-
-/// Convert a 5-bit color component to 8 bit
-[[nodiscard]] constexpr u8 Convert5To8(u8 value) {
-    return (value << 3) | (value >> 2);
-}
-
-/// Convert a 6-bit color component to 8 bit
-[[nodiscard]] constexpr u8 Convert6To8(u8 value) {
-    return (value << 2) | (value >> 4);
-}
-
-/// Convert a 8-bit color component to 1 bit
-[[nodiscard]] constexpr u8 Convert8To1(u8 value) {
-    return value >> 7;
-}
-
-/// Convert a 8-bit color component to 4 bit
-[[nodiscard]] constexpr u8 Convert8To4(u8 value) {
-    return value >> 4;
-}
-
-/// Convert a 8-bit color component to 5 bit
-[[nodiscard]] constexpr u8 Convert8To5(u8 value) {
-    return value >> 3;
-}
-
-/// Convert a 8-bit color component to 6 bit
-[[nodiscard]] constexpr u8 Convert8To6(u8 value) {
-    return value >> 2;
-}
-
-/**
- * Decode a color stored in RGBA8 format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRGBA8(const u8* bytes) {
-    return {bytes[3], bytes[2], bytes[1], bytes[0]};
-}
-
-/**
- * Decode a color stored in RGB8 format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRGB8(const u8* bytes) {
-    return {bytes[2], bytes[1], bytes[0], 255};
-}
-
-/**
- * Decode a color stored in RG8 (aka HILO8) format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRG8(const u8* bytes) {
-    return {bytes[1], bytes[0], 0, 255};
-}
-
-/**
- * Decode a color stored in RGB565 format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRGB565(const u8* bytes) {
-    u16_le pixel;
-    std::memcpy(&pixel, bytes, sizeof(pixel));
-    return {Convert5To8((pixel >> 11) & 0x1F), Convert6To8((pixel >> 5) & 0x3F),
-            Convert5To8(pixel & 0x1F), 255};
-}
-
-/**
- * Decode a color stored in RGB5A1 format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRGB5A1(const u8* bytes) {
-    u16_le pixel;
-    std::memcpy(&pixel, bytes, sizeof(pixel));
-    return {Convert5To8((pixel >> 11) & 0x1F), Convert5To8((pixel >> 6) & 0x1F),
-            Convert5To8((pixel >> 1) & 0x1F), Convert1To8(pixel & 0x1)};
-}
-
-/**
- * Decode a color stored in RGBA4 format
- * @param bytes Pointer to encoded source color
- * @return Result color decoded as Common::Vec4<u8>
- */
-[[nodiscard]] inline Common::Vec4<u8> DecodeRGBA4(const u8* bytes) {
-    u16_le pixel;
-    std::memcpy(&pixel, bytes, sizeof(pixel));
-    return {Convert4To8((pixel >> 12) & 0xF), Convert4To8((pixel >> 8) & 0xF),
-            Convert4To8((pixel >> 4) & 0xF), Convert4To8(pixel & 0xF)};
-}
-
-/**
- * Decode a depth value stored in D16 format
- * @param bytes Pointer to encoded source value
- * @return Depth value as an u32
- */
-[[nodiscard]] inline u32 DecodeD16(const u8* bytes) {
-    u16_le data;
-    std::memcpy(&data, bytes, sizeof(data));
-    return data;
-}
-
-/**
- * Decode a depth value stored in D24 format
- * @param bytes Pointer to encoded source value
- * @return Depth value as an u32
- */
-[[nodiscard]] inline u32 DecodeD24(const u8* bytes) {
-    return (bytes[2] << 16) | (bytes[1] << 8) | bytes[0];
-}
-
-/**
- * Decode a depth value and a stencil value stored in D24S8 format
- * @param bytes Pointer to encoded source values
- * @return Resulting values stored as a Common::Vec2
- */
-[[nodiscard]] inline Common::Vec2<u32> DecodeD24S8(const u8* bytes) {
-    return {static_cast<u32>((bytes[2] << 16) | (bytes[1] << 8) | bytes[0]), bytes[3]};
-}
-
-/**
- * Encode a color as RGBA8 format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRGBA8(const Common::Vec4<u8>& color, u8* bytes) {
-    bytes[3] = color.r();
-    bytes[2] = color.g();
-    bytes[1] = color.b();
-    bytes[0] = color.a();
-}
-
-/**
- * Encode a color as RGB8 format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRGB8(const Common::Vec4<u8>& color, u8* bytes) {
-    bytes[2] = color.r();
-    bytes[1] = color.g();
-    bytes[0] = color.b();
-}
-
-/**
- * Encode a color as RG8 (aka HILO8) format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRG8(const Common::Vec4<u8>& color, u8* bytes) {
-    bytes[1] = color.r();
-    bytes[0] = color.g();
-}
-/**
- * Encode a color as RGB565 format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRGB565(const Common::Vec4<u8>& color, u8* bytes) {
-    const u16_le data =
-        (Convert8To5(color.r()) << 11) | (Convert8To6(color.g()) << 5) | Convert8To5(color.b());
-
-    std::memcpy(bytes, &data, sizeof(data));
-}
-
-/**
- * Encode a color as RGB5A1 format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRGB5A1(const Common::Vec4<u8>& color, u8* bytes) {
-    const u16_le data = (Convert8To5(color.r()) << 11) | (Convert8To5(color.g()) << 6) |
-                        (Convert8To5(color.b()) << 1) | Convert8To1(color.a());
-
-    std::memcpy(bytes, &data, sizeof(data));
-}
-
-/**
- * Encode a color as RGBA4 format
- * @param color Source color to encode
- * @param bytes Destination pointer to store encoded color
- */
-inline void EncodeRGBA4(const Common::Vec4<u8>& color, u8* bytes) {
-    const u16 data = (Convert8To4(color.r()) << 12) | (Convert8To4(color.g()) << 8) |
-                     (Convert8To4(color.b()) << 4) | Convert8To4(color.a());
-
-    std::memcpy(bytes, &data, sizeof(data));
-}
-
-/**
- * Encode a 16 bit depth value as D16 format
- * @param value 16 bit source depth value to encode
- * @param bytes Pointer where to store the encoded value
- */
-inline void EncodeD16(u32 value, u8* bytes) {
-    const u16_le data = static_cast<u16>(value);
-    std::memcpy(bytes, &data, sizeof(data));
-}
-
-/**
- * Encode a 24 bit depth value as D24 format
- * @param value 24 bit source depth value to encode
- * @param bytes Pointer where to store the encoded value
- */
-inline void EncodeD24(u32 value, u8* bytes) {
-    bytes[0] = value & 0xFF;
-    bytes[1] = (value >> 8) & 0xFF;
-    bytes[2] = (value >> 16) & 0xFF;
-}
-
-/**
- * Encode a 24 bit depth and 8 bit stencil values as D24S8 format
- * @param depth 24 bit source depth value to encode
- * @param stencil 8 bit source stencil value to encode
- * @param bytes Pointer where to store the encoded value
- */
-inline void EncodeD24S8(u32 depth, u8 stencil, u8* bytes) {
-    bytes[0] = depth & 0xFF;
-    bytes[1] = (depth >> 8) & 0xFF;
-    bytes[2] = (depth >> 16) & 0xFF;
-    bytes[3] = stencil;
-}
-
-/**
- * Encode a 24 bit depth value as D24X8 format (32 bits per pixel with 8 bits unused)
- * @param depth 24 bit source depth value to encode
- * @param bytes Pointer where to store the encoded value
- * @note unused bits will not be modified
- */
-inline void EncodeD24X8(u32 depth, u8* bytes) {
-    bytes[0] = depth & 0xFF;
-    bytes[1] = (depth >> 8) & 0xFF;
-    bytes[2] = (depth >> 16) & 0xFF;
-}
-
-/**
- * Encode an 8 bit stencil value as X24S8 format (32 bits per pixel with 24 bits unused)
- * @param stencil 8 bit source stencil value to encode
- * @param bytes Pointer where to store the encoded value
- * @note unused bits will not be modified
- */
-inline void EncodeX24S8(u8 stencil, u8* bytes) {
-    bytes[3] = stencil;
-}
-
-} // namespace Common::Color
diff --git a/src/core/hle/kernel/k_priority_queue.h b/src/core/hle/kernel/k_priority_queue.h
index 99fb8fe93..0dc929040 100644
--- a/src/core/hle/kernel/k_priority_queue.h
+++ b/src/core/hle/kernel/k_priority_queue.h
@@ -8,11 +8,11 @@
 #pragma once
 
 #include <array>
+#include <bit>
 #include <concepts>
 
 #include "common/assert.h"
 #include "common/bit_set.h"
-#include "common/bit_util.h"
 #include "common/common_types.h"
 #include "common/concepts.h"
 
@@ -268,7 +268,7 @@ private:
     }
 
     constexpr s32 GetNextCore(u64& affinity) {
-        const s32 core = Common::CountTrailingZeroes64(affinity);
+        const s32 core = std::countr_zero(affinity);
         ClearAffinityBit(affinity, core);
         return core;
     }
diff --git a/src/core/hle/kernel/k_scheduler.cpp b/src/core/hle/kernel/k_scheduler.cpp
index 42f0ea483..12b5619fb 100644
--- a/src/core/hle/kernel/k_scheduler.cpp
+++ b/src/core/hle/kernel/k_scheduler.cpp
@@ -5,6 +5,8 @@
 // This file references various implementation details from Atmosphere, an open-source firmware for
 // the Nintendo Switch. Copyright 2018-2020 Atmosphere-NX.
 
+#include <bit>
+
 #include "common/assert.h"
 #include "common/bit_util.h"
 #include "common/fiber.h"
@@ -31,12 +33,12 @@ static void IncrementScheduledCount(Kernel::Thread* thread) {
 
 void KScheduler::RescheduleCores(KernelCore& kernel, u64 cores_pending_reschedule,
                                  Core::EmuThreadHandle global_thread) {
-    u32 current_core = global_thread.host_handle;
+    const u32 current_core = global_thread.host_handle;
     bool must_context_switch = global_thread.guest_handle != InvalidHandle &&
                                (current_core < Core::Hardware::NUM_CPU_CORES);
 
     while (cores_pending_reschedule != 0) {
-        u32 core = Common::CountTrailingZeroes64(cores_pending_reschedule);
+        const auto core = static_cast<u32>(std::countr_zero(cores_pending_reschedule));
         ASSERT(core < Core::Hardware::NUM_CPU_CORES);
         if (!must_context_switch || core != current_core) {
             auto& phys_core = kernel.PhysicalCore(core);
@@ -109,7 +111,7 @@ u64 KScheduler::UpdateHighestPriorityThreadsImpl(KernelCore& kernel) {
 
     // Idle cores are bad. We're going to try to migrate threads to each idle core in turn.
     while (idle_cores != 0) {
-        u32 core_id = Common::CountTrailingZeroes64(idle_cores);
+        const auto core_id = static_cast<u32>(std::countr_zero(idle_cores));
         if (Thread* suggested = priority_queue.GetSuggestedFront(core_id); suggested != nullptr) {
             s32 migration_candidates[Core::Hardware::NUM_CPU_CORES];
             size_t num_candidates = 0;
diff --git a/src/core/hle/kernel/memory/page_heap.h b/src/core/hle/kernel/memory/page_heap.h
index 22b0de860..131093284 100644
--- a/src/core/hle/kernel/memory/page_heap.h
+++ b/src/core/hle/kernel/memory/page_heap.h
@@ -8,11 +8,11 @@
 #pragma once
 
 #include <array>
+#include <bit>
 #include <vector>
 
 #include "common/alignment.h"
 #include "common/assert.h"
-#include "common/bit_util.h"
 #include "common/common_funcs.h"
 #include "common/common_types.h"
 #include "core/hle/kernel/memory/memory_types.h"
@@ -105,7 +105,7 @@ private:
                         ASSERT(depth == 0);
                         return -1;
                     }
-                    offset = offset * 64 + Common::CountTrailingZeroes64(v);
+                    offset = offset * 64 + static_cast<u32>(std::countr_zero(v));
                     ++depth;
                 } while (depth < static_cast<s32>(used_depths));
 
diff --git a/src/core/hle/kernel/process_capability.cpp b/src/core/hle/kernel/process_capability.cpp
index 0f128c586..0566311b6 100644
--- a/src/core/hle/kernel/process_capability.cpp
+++ b/src/core/hle/kernel/process_capability.cpp
@@ -2,6 +2,8 @@
 // Licensed under GPLv2 or any later version
 // Refer to the license.txt file included.
 
+#include <bit>
+
 #include "common/bit_util.h"
 #include "common/logging/log.h"
 #include "core/hle/kernel/errors.h"
@@ -60,7 +62,7 @@ constexpr CapabilityType GetCapabilityType(u32 value) {
 
 u32 GetFlagBitOffset(CapabilityType type) {
     const auto value = static_cast<u32>(type);
-    return static_cast<u32>(Common::BitSize<u32>() - Common::CountLeadingZeroes32(value));
+    return static_cast<u32>(Common::BitSize<u32>() - static_cast<u32>(std::countl_zero(value)));
 }
 
 } // Anonymous namespace
diff --git a/src/tests/CMakeLists.txt b/src/tests/CMakeLists.txt
index 8a606b448..33fa89583 100644
--- a/src/tests/CMakeLists.txt
+++ b/src/tests/CMakeLists.txt
@@ -1,6 +1,5 @@
 add_executable(tests
     common/bit_field.cpp
-    common/bit_utils.cpp
     common/fibers.cpp
     common/param_package.cpp
     common/ring_buffer.cpp
diff --git a/src/tests/common/bit_utils.cpp b/src/tests/common/bit_utils.cpp
deleted file mode 100644
index 479b5995a..000000000
--- a/src/tests/common/bit_utils.cpp
+++ /dev/null
@@ -1,23 +0,0 @@
-// Copyright 2017 Citra Emulator Project
-// Licensed under GPLv2 or any later version
-// Refer to the license.txt file included.
-
-#include <catch2/catch.hpp>
-#include <math.h>
-#include "common/bit_util.h"
-
-namespace Common {
-
-TEST_CASE("BitUtils::CountTrailingZeroes", "[common]") {
-    REQUIRE(Common::CountTrailingZeroes32(0) == 32);
-    REQUIRE(Common::CountTrailingZeroes64(0) == 64);
-    REQUIRE(Common::CountTrailingZeroes32(9) == 0);
-    REQUIRE(Common::CountTrailingZeroes32(8) == 3);
-    REQUIRE(Common::CountTrailingZeroes32(0x801000) == 12);
-    REQUIRE(Common::CountTrailingZeroes64(9) == 0);
-    REQUIRE(Common::CountTrailingZeroes64(8) == 3);
-    REQUIRE(Common::CountTrailingZeroes64(0x801000) == 12);
-    REQUIRE(Common::CountTrailingZeroes64(0x801000000000UL) == 36);
-}
-
-} // namespace Common
diff --git a/src/video_core/cdma_pusher.cpp b/src/video_core/cdma_pusher.cpp
index 94679d5d1..33b3c060b 100644
--- a/src/video_core/cdma_pusher.cpp
+++ b/src/video_core/cdma_pusher.cpp
@@ -18,10 +18,10 @@
 // OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 //
 
+#include <bit>
 #include "command_classes/host1x.h"
 #include "command_classes/nvdec.h"
 #include "command_classes/vic.h"
-#include "common/bit_util.h"
 #include "video_core/cdma_pusher.h"
 #include "video_core/command_classes/nvdec_common.h"
 #include "video_core/engines/maxwell_3d.h"
@@ -56,7 +56,7 @@ void CDmaPusher::Step() {
 
     for (const u32 value : values) {
         if (mask != 0) {
-            const u32 lbs = Common::CountTrailingZeroes32(mask);
+            const auto lbs = static_cast<u32>(std::countr_zero(mask));
             mask &= ~(1U << lbs);
             ExecuteCommand(static_cast<u32>(offset + lbs), value);
             continue;
diff --git a/src/video_core/cdma_pusher.h b/src/video_core/cdma_pusher.h
index 8ca70b6dd..e5f212c1a 100644
--- a/src/video_core/cdma_pusher.h
+++ b/src/video_core/cdma_pusher.h
@@ -126,7 +126,7 @@ private:
 
     s32 count{};
     s32 offset{};
-    s32 mask{};
+    u32 mask{};
     bool incrementing{};
 
     // Queue of command lists to be processed
diff --git a/src/video_core/command_classes/codecs/h264.cpp b/src/video_core/command_classes/codecs/h264.cpp
index 65bbeac78..fea6aed98 100644
--- a/src/video_core/command_classes/codecs/h264.cpp
+++ b/src/video_core/command_classes/codecs/h264.cpp
@@ -19,7 +19,7 @@
 //
 
 #include <array>
-#include "common/bit_util.h"
+#include <bit>
 #include "video_core/command_classes/codecs/h264.h"
 #include "video_core/gpu.h"
 #include "video_core/memory_manager.h"
@@ -266,7 +266,7 @@ void H264BitWriter::WriteExpGolombCodedInt(s32 value) {
 }
 
 void H264BitWriter::WriteExpGolombCodedUInt(u32 value) {
-    const s32 size = 32 - Common::CountLeadingZeroes32(static_cast<s32>(value + 1));
+    const s32 size = 32 - std::countl_zero(value + 1);
     WriteBits(1, size);
 
     value -= (1U << (size - 1)) - 1;