14 files changed, 40 insertions, 141 deletions

diff --git a/src/common/alignment.h b/src/common/alignment.h
index 5040043de..fb81f10d8 100644
--- a/src/common/alignment.h
+++ b/src/common/alignment.h
@@ -9,50 +9,45 @@
 namespace Common {
 
 template <typename T>
-[[nodiscard]] constexpr T AlignUp(T value, std::size_t size) {
-    static_assert(std::is_unsigned_v<T>, "T must be an unsigned value.");
+requires std::is_unsigned_v<T>[[nodiscard]] constexpr T AlignUp(T value, size_t size) {
     auto mod{static_cast<T>(value % size)};
     value -= mod;
     return static_cast<T>(mod == T{0} ? value : value + size);
 }
 
 template <typename T>
-[[nodiscard]] constexpr T AlignDown(T value, std::size_t size) {
-    static_assert(std::is_unsigned_v<T>, "T must be an unsigned value.");
-    return static_cast<T>(value - value % size);
+requires std::is_unsigned_v<T>[[nodiscard]] constexpr T AlignUpLog2(T value, size_t align_log2) {
+    return static_cast<T>((value + ((1ULL << align_log2) - 1)) >> align_log2 << align_log2);
 }
 
 template <typename T>
-[[nodiscard]] constexpr T AlignBits(T value, std::size_t align) {
-    static_assert(std::is_unsigned_v<T>, "T must be an unsigned value.");
-    return static_cast<T>((value + ((1ULL << align) - 1)) >> align << align);
+requires std::is_unsigned_v<T>[[nodiscard]] constexpr T AlignDown(T value, size_t size) {
+    return static_cast<T>(value - value % size);
 }
 
 template <typename T>
-[[nodiscard]] constexpr bool Is4KBAligned(T value) {
-    static_assert(std::is_unsigned_v<T>, "T must be an unsigned value.");
+requires std::is_unsigned_v<T>[[nodiscard]] constexpr bool Is4KBAligned(T value) {
     return (value & 0xFFF) == 0;
 }
 
 template <typename T>
-[[nodiscard]] constexpr bool IsWordAligned(T value) {
-    static_assert(std::is_unsigned_v<T>, "T must be an unsigned value.");
+requires std::is_unsigned_v<T>[[nodiscard]] constexpr bool IsWordAligned(T value) {
     return (value & 0b11) == 0;
 }
 
 template <typename T>
-[[nodiscard]] constexpr bool IsAligned(T value, std::size_t alignment) {
-    using U = typename std::make_unsigned<T>::type;
+requires std::is_integral_v<T>[[nodiscard]] constexpr bool IsAligned(T value, size_t alignment) {
+    using U = typename std::make_unsigned_t<T>;
     const U mask = static_cast<U>(alignment - 1);
     return (value & mask) == 0;
 }
 
-template <typename T, std::size_t Align = 16>
+template <typename T, size_t Align = 16>
 class AlignmentAllocator {
 public:
     using value_type = T;
-    using size_type = std::size_t;
-    using difference_type = std::ptrdiff_t;
+    using size_type = size_t;
+    using difference_type = ptrdiff_t;
 
     using propagate_on_container_copy_assignment = std::true_type;
     using propagate_on_container_move_assignment = std::true_type;
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/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;
diff --git a/src/video_core/texture_cache/accelerated_swizzle.cpp b/src/video_core/texture_cache/accelerated_swizzle.cpp
index a4fc1184b..15585caeb 100644
--- a/src/video_core/texture_cache/accelerated_swizzle.cpp
+++ b/src/video_core/texture_cache/accelerated_swizzle.cpp
@@ -27,7 +27,7 @@ BlockLinearSwizzle2DParams MakeBlockLinearSwizzle2DParams(const SwizzleParameter
     const Extent3D num_tiles = swizzle.num_tiles;
     const u32 bytes_per_block = BytesPerBlock(info.format);
     const u32 stride_alignment = CalculateLevelStrideAlignment(info, swizzle.level);
-    const u32 stride = Common::AlignBits(num_tiles.width, stride_alignment) * bytes_per_block;
+    const u32 stride = Common::AlignUpLog2(num_tiles.width, stride_alignment) * bytes_per_block;
     const u32 gobs_in_x = Common::DivCeilLog2(stride, GOB_SIZE_X_SHIFT);
     return BlockLinearSwizzle2DParams{
         .origin{0, 0, 0},
@@ -47,7 +47,7 @@ BlockLinearSwizzle3DParams MakeBlockLinearSwizzle3DParams(const SwizzleParameter
     const Extent3D num_tiles = swizzle.num_tiles;
     const u32 bytes_per_block = BytesPerBlock(info.format);
     const u32 stride_alignment = CalculateLevelStrideAlignment(info, swizzle.level);
-    const u32 stride = Common::AlignBits(num_tiles.width, stride_alignment) * bytes_per_block;
+    const u32 stride = Common::AlignUpLog2(num_tiles.width, stride_alignment) * bytes_per_block;
 
     const u32 gobs_in_x = (stride + GOB_SIZE_X - 1) >> GOB_SIZE_X_SHIFT;
     const u32 block_size = gobs_in_x << (GOB_SIZE_SHIFT + block.height + block.depth);
diff --git a/src/video_core/texture_cache/util.cpp b/src/video_core/texture_cache/util.cpp
index 279932778..ce8fcfe0a 100644
--- a/src/video_core/texture_cache/util.cpp
+++ b/src/video_core/texture_cache/util.cpp
@@ -279,7 +279,7 @@ template <u32 GOB_EXTENT>
     const bool is_small = IsSmallerThanGobSize(blocks, gob, info.block.depth);
     const u32 alignment = is_small ? 0 : info.tile_width_spacing;
     return Extent2D{
-        .width = Common::AlignBits(gobs.width, alignment),
+        .width = Common::AlignUpLog2(gobs.width, alignment),
         .height = gobs.height,
     };
 }
@@ -352,7 +352,7 @@ template <u32 GOB_EXTENT>
     // https://github.com/Ryujinx/Ryujinx/blob/1c9aba6de1520aea5480c032e0ff5664ac1bb36f/Ryujinx.Graphics.Texture/SizeCalculator.cs#L134
     if (tile_width_spacing > 0) {
         const u32 alignment_log2 = GOB_SIZE_SHIFT + tile_width_spacing + block.height + block.depth;
-        return Common::AlignBits(size_bytes, alignment_log2);
+        return Common::AlignUpLog2(size_bytes, alignment_log2);
     }
     const u32 aligned_height = Common::AlignUp(size.height, tile_size_y);
     while (block.height != 0 && aligned_height <= (1U << (block.height - 1)) * GOB_SIZE_Y) {
@@ -528,9 +528,9 @@ template <u32 GOB_EXTENT>
     const u32 alignment = StrideAlignment(num_tiles, info.block, bpp_log2, info.tile_width_spacing);
     const Extent3D mip_block = AdjustMipBlockSize(num_tiles, info.block, 0);
     return Extent3D{
-        .width = Common::AlignBits(num_tiles.width, alignment),
-        .height = Common::AlignBits(num_tiles.height, GOB_SIZE_Y_SHIFT + mip_block.height),
-        .depth = Common::AlignBits(num_tiles.depth, GOB_SIZE_Z_SHIFT + mip_block.depth),
+        .width = Common::AlignUpLog2(num_tiles.width, alignment),
+        .height = Common::AlignUpLog2(num_tiles.height, GOB_SIZE_Y_SHIFT + mip_block.height),
+        .depth = Common::AlignUpLog2(num_tiles.depth, GOB_SIZE_Z_SHIFT + mip_block.depth),
     };
 }
 
diff --git a/src/video_core/textures/decoders.cpp b/src/video_core/textures/decoders.cpp
index 9f5181318..62685a183 100644
--- a/src/video_core/textures/decoders.cpp
+++ b/src/video_core/textures/decoders.cpp
@@ -49,7 +49,7 @@ void Swizzle(std::span<u8> output, std::span<const u8> input, u32 bytes_per_pixe
     // We can configure here a custom pitch
     // As it's not exposed 'width * bpp' will be the expected pitch.
     const u32 pitch = width * bytes_per_pixel;
-    const u32 stride = Common::AlignBits(width, stride_alignment) * bytes_per_pixel;
+    const u32 stride = Common::AlignUpLog2(width, stride_alignment) * bytes_per_pixel;
 
     const u32 gobs_in_x = Common::DivCeilLog2(stride, GOB_SIZE_X_SHIFT);
     const u32 block_size = gobs_in_x << (GOB_SIZE_SHIFT + block_height + block_depth);
@@ -217,9 +217,9 @@ void SwizzleKepler(const u32 width, const u32 height, const u32 dst_x, const u32
 std::size_t CalculateSize(bool tiled, u32 bytes_per_pixel, u32 width, u32 height, u32 depth,
                           u32 block_height, u32 block_depth) {
     if (tiled) {
-        const u32 aligned_width = Common::AlignBits(width * bytes_per_pixel, GOB_SIZE_X_SHIFT);
-        const u32 aligned_height = Common::AlignBits(height, GOB_SIZE_Y_SHIFT + block_height);
-        const u32 aligned_depth = Common::AlignBits(depth, GOB_SIZE_Z_SHIFT + block_depth);
+        const u32 aligned_width = Common::AlignUpLog2(width * bytes_per_pixel, GOB_SIZE_X_SHIFT);
+        const u32 aligned_height = Common::AlignUpLog2(height, GOB_SIZE_Y_SHIFT + block_height);
+        const u32 aligned_depth = Common::AlignUpLog2(depth, GOB_SIZE_Z_SHIFT + block_depth);
         return aligned_width * aligned_height * aligned_depth;
     } else {
         return width * height * depth * bytes_per_pixel;