Files
MobileGL/MobileGL/MG_Backend/ClientReadback.cpp
T

492 lines
26 KiB
C++

// MobileGL - MobileGL/MG_Backend/ClientReadback.cpp
// Copyright (c) 2025-2026 MobileGL-Dev
// Licensed under the GNU Lesser General Public License v3.0:
// https://www.gnu.org/licenses/gpl-3.0.txt
// https://www.gnu.org/licenses/lgpl-3.0.txt
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#include "ClientReadback.h"
#include <MG_Backend/MGPipe/PipeInputs.h>
#include <MG_Util/Math/HalfFloat.h>
#include <MG_Util/Math/SmallFloat.h>
#include <algorithm>
#include <cmath>
namespace MobileGL::MG_Backend {
// ---- Client-format readback conversion helpers -------------------------------------------------
// ReadPixels/GetTexImage read a guaranteed wide RGBA(_INTEGER) layout from the ES driver and repack
// it on the CPU into the client's (format, type) layout. Everything here is pure byte shuffling so
// unit tests can assert the exact packed words; field positions follow GL 3.3 table 3.6 and mirror
// the GL CTS packed_pixels oracle (glcPackedPixelsTests.cpp pack_UNSIGNED_* helpers).
namespace ClientReadback {
using MG_Util::DecodeHalfBitsToFloat;
using MG_Util::EncodeFloatToHalfBits;
Bool GetReadbackChannelMapping(GLenum format, ReadbackChannelMapping& outMapping) {
switch (format) {
case GL_RED:
outMapping = {{0, 0, 0, 0}, 1, false};
return true;
case GL_RED_INTEGER:
outMapping = {{0, 0, 0, 0}, 1, true};
return true;
// Desktop-GL single-channel client formats (GL CTS packed_pixels rgba8_format_green/blue):
// the destination holds one component sourced from the named channel of the wide RGBA read.
// GL_ALPHA is mapped here from the raw enum because the state layer folds it into Red for the
// legacy alpha-texture upload hack.
case GL_GREEN:
outMapping = {{1, 0, 0, 0}, 1, false};
return true;
case GL_GREEN_INTEGER:
outMapping = {{1, 0, 0, 0}, 1, true};
return true;
case GL_BLUE:
outMapping = {{2, 0, 0, 0}, 1, false};
return true;
case GL_BLUE_INTEGER:
outMapping = {{2, 0, 0, 0}, 1, true};
return true;
case GL_ALPHA:
outMapping = {{3, 0, 0, 0}, 1, false};
return true;
case GL_ALPHA_INTEGER:
outMapping = {{3, 0, 0, 0}, 1, true};
return true;
case GL_RG:
outMapping = {{0, 1, 0, 0}, 2, false};
return true;
case GL_RG_INTEGER:
outMapping = {{0, 1, 0, 0}, 2, true};
return true;
case GL_RGB:
outMapping = {{0, 1, 2, 0}, 3, false};
return true;
case GL_RGB_INTEGER:
outMapping = {{0, 1, 2, 0}, 3, true};
return true;
case GL_BGR:
outMapping = {{2, 1, 0, 0}, 3, false};
return true;
case GL_BGR_INTEGER:
outMapping = {{2, 1, 0, 0}, 3, true};
return true;
case GL_RGBA:
outMapping = {{0, 1, 2, 3}, 4, false};
return true;
case GL_RGBA_INTEGER:
outMapping = {{0, 1, 2, 3}, 4, true};
return true;
case GL_BGRA:
outMapping = {{2, 1, 0, 3}, 4, false};
return true;
case GL_BGRA_INTEGER:
outMapping = {{2, 1, 0, 3}, 4, true};
return true;
default:
return false;
}
}
Bool GetPackedReadbackLayout(GLenum type, PackedReadbackLayout& out) {
switch (type) {
// Non-REV types pack the first format component starting at the most significant bit,
// *_REV types starting at the least significant bit (GL CTS pack_UNSIGNED_SHORT_5_6_5:
// R bits 15-11; pack_UNSIGNED_SHORT_1_5_5_5_REV: R bits 4-0, A bit 15).
case GL_UNSIGNED_BYTE_3_3_2:
out = {3, {3, 3, 2, 0}, {5, 2, 0, 0}, 1, false};
return true;
case GL_UNSIGNED_BYTE_2_3_3_REV:
out = {3, {3, 3, 2, 0}, {0, 3, 6, 0}, 1, false};
return true;
case GL_UNSIGNED_SHORT_5_6_5:
out = {3, {5, 6, 5, 0}, {11, 5, 0, 0}, 2, false};
return true;
case GL_UNSIGNED_SHORT_5_6_5_REV:
out = {3, {5, 6, 5, 0}, {0, 5, 11, 0}, 2, false};
return true;
case GL_UNSIGNED_SHORT_4_4_4_4:
out = {4, {4, 4, 4, 4}, {12, 8, 4, 0}, 2, false};
return true;
case GL_UNSIGNED_SHORT_4_4_4_4_REV:
out = {4, {4, 4, 4, 4}, {0, 4, 8, 12}, 2, false};
return true;
case GL_UNSIGNED_SHORT_5_5_5_1:
out = {4, {5, 5, 5, 1}, {11, 6, 1, 0}, 2, false};
return true;
case GL_UNSIGNED_SHORT_1_5_5_5_REV:
out = {4, {5, 5, 5, 1}, {0, 5, 10, 15}, 2, false};
return true;
case GL_UNSIGNED_INT_8_8_8_8:
out = {4, {8, 8, 8, 8}, {24, 16, 8, 0}, 4, false};
return true;
case GL_UNSIGNED_INT_8_8_8_8_REV:
out = {4, {8, 8, 8, 8}, {0, 8, 16, 24}, 4, false};
return true;
case GL_UNSIGNED_INT_10_10_10_2:
out = {4, {10, 10, 10, 2}, {22, 12, 2, 0}, 4, false};
return true;
case GL_UNSIGNED_INT_2_10_10_10_REV:
out = {4, {10, 10, 10, 2}, {0, 10, 20, 30}, 4, false};
return true;
// Packed-float RGB types: fields hold unsigned small floats; 5_9_9_9_REV's shared 5-bit
// exponent (bits 31-27) is emitted by EncodeSharedExponentRGB9E5, not a component field.
case GL_UNSIGNED_INT_10F_11F_11F_REV:
out = {3, {11, 11, 10, 0}, {0, 11, 22, 0}, 4, true};
return true;
case GL_UNSIGNED_INT_5_9_9_9_REV:
out = {3, {9, 9, 9, 0}, {0, 9, 18, 0}, 4, true};
return true;
default:
return false;
}
}
SizeT GetReadbackComponentSize(GLenum type) {
PackedReadbackLayout packedLayout{};
if (GetPackedReadbackLayout(type, packedLayout)) {
return packedLayout.byteSize;
}
switch (type) {
case GL_UNSIGNED_BYTE:
case GL_BYTE:
return 1;
case GL_UNSIGNED_SHORT:
case GL_SHORT:
case GL_HALF_FLOAT:
return 2;
case GL_UNSIGNED_INT:
case GL_INT:
case GL_FLOAT:
return 4;
default:
return 0;
}
}
SizeT GetReadbackDstPixelSize(const ReadbackChannelMapping& mapping, GLenum type) {
PackedReadbackLayout packedLayout{};
if (GetPackedReadbackLayout(type, packedLayout)) {
if (packedLayout.fieldCount != mapping.channelCount) {
return 0; // 3-field packed types pair with 3-component formats only, 4 with 4
}
if (mapping.isInteger && packedLayout.isFloatPacked) {
return 0; // packed-float RGB types never pair with integer formats
}
return packedLayout.byteSize;
}
if (mapping.isInteger && (type == GL_FLOAT || type == GL_HALF_FLOAT)) {
return 0;
}
const SizeT componentSize = GetReadbackComponentSize(type);
return componentSize == 0 ? 0 : static_cast<SizeT>(mapping.channelCount) * componentSize;
}
namespace {
void WritePackedReadbackWord(Uint8* dst, Uint32 word, SizeT byteSize) {
switch (byteSize) {
case 1: {
const auto out = static_cast<Uint8>(word);
Memcpy(dst, &out, sizeof(out));
break;
}
case 2: {
const auto out = static_cast<Uint16>(word);
Memcpy(dst, &out, sizeof(out));
break;
}
default:
Memcpy(dst, &word, sizeof(word));
break;
}
}
} // namespace
// Shared encoders live in MG_Util/Math/SmallFloat.h so the upload conversion
// (PixelStoreProcessor) uses byte-identical packing; kept exported here for unit tests.
Uint32 EncodeFloatToUnsignedF11(Float value) {
return MG_Util::EncodeFloatToUnsignedF11(value);
}
Uint32 EncodeFloatToUnsignedF10(Float value) {
return MG_Util::EncodeFloatToUnsignedF10(value);
}
Uint32 EncodeSharedExponentRGB9E5(const Float rgb[3]) {
return MG_Util::EncodeSharedExponentRGB9E5(rgb);
}
void ConvertWideReadbackRow(const Uint8* src, Uint8* dst, SizeT width, GLenum wideType,
const ReadbackChannelMapping& mapping, GLenum type) {
PackedReadbackLayout packedLayout{};
const Bool isPacked = GetPackedReadbackLayout(type, packedLayout);
const SizeT dstComponentSize = GetReadbackComponentSize(type);
const SizeT dstPixelBytes = GetReadbackDstPixelSize(mapping, type);
const SizeT srcPixelBytes = 4 * GetReadbackComponentSize(wideType);
for (SizeT col = 0; col < width; ++col) {
const Uint8* srcPixel = src + col * srcPixelBytes;
Uint8* dstPixel = dst + col * dstPixelBytes;
if (mapping.isInteger) {
Int64 srcValues[4];
for (Int c = 0; c < 4; ++c) {
srcValues[c] = wideType == GL_INT
? static_cast<Int64>(reinterpret_cast<const Int32*>(srcPixel)[c])
: static_cast<Int64>(reinterpret_cast<const Uint32*>(srcPixel)[c]);
}
if (isPacked) {
// Integer sources clamp each component to the unsigned range of its field
// (GL 3.3 section 4.3.1 final conversion).
Uint32 word = 0;
for (Int ch = 0; ch < packedLayout.fieldCount; ++ch) {
const Int64 fieldMax = (Int64{1} << packedLayout.width[ch]) - 1;
const auto v = static_cast<Uint32>(
std::clamp<Int64>(srcValues[mapping.sourceChannel[ch]], 0, fieldMax));
word |= v << packedLayout.shift[ch];
}
WritePackedReadbackWord(dstPixel, word, packedLayout.byteSize);
} else {
for (Int ch = 0; ch < mapping.channelCount; ++ch) {
const Int64 v = srcValues[mapping.sourceChannel[ch]];
Uint8* dstComponent = dstPixel + static_cast<SizeT>(ch) * dstComponentSize;
switch (type) {
case GL_UNSIGNED_BYTE:
*dstComponent = static_cast<Uint8>(std::clamp<Int64>(v, 0, 255));
break;
case GL_BYTE: {
const auto out = static_cast<Int8>(std::clamp<Int64>(v, -128, 127));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_UNSIGNED_SHORT: {
const auto out = static_cast<Uint16>(std::clamp<Int64>(v, 0, 65535));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_SHORT: {
const auto out = static_cast<Int16>(std::clamp<Int64>(v, -32768, 32767));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_UNSIGNED_INT: {
const auto out = static_cast<Uint32>(std::clamp<Int64>(v, 0, 4294967295LL));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_INT: {
const auto out = static_cast<Int32>(std::clamp<Int64>(v, -2147483648LL, 2147483647LL));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
default:
break;
}
}
}
} else {
Float srcValues[4];
switch (wideType) {
case GL_UNSIGNED_BYTE:
for (Int c = 0; c < 4; ++c) {
srcValues[c] = static_cast<Float>(srcPixel[c]) / 255.0f;
}
break;
case GL_BYTE:
for (Int c = 0; c < 4; ++c) {
srcValues[c] = std::max(
static_cast<Float>(reinterpret_cast<const Int8*>(srcPixel)[c]) / 127.0f, -1.0f);
}
break;
case GL_UNSIGNED_SHORT:
for (Int c = 0; c < 4; ++c) {
srcValues[c] = static_cast<Float>(reinterpret_cast<const Uint16*>(srcPixel)[c]) / 65535.0f;
}
break;
case GL_SHORT:
for (Int c = 0; c < 4; ++c) {
srcValues[c] = std::max(
static_cast<Float>(reinterpret_cast<const Int16*>(srcPixel)[c]) / 32767.0f, -1.0f);
}
break;
case GL_HALF_FLOAT:
for (Int c = 0; c < 4; ++c) {
srcValues[c] = DecodeHalfBitsToFloat(reinterpret_cast<const Uint16*>(srcPixel)[c]);
}
break;
default: // GL_FLOAT
for (Int c = 0; c < 4; ++c) {
srcValues[c] = reinterpret_cast<const Float*>(srcPixel)[c];
}
break;
}
if (isPacked) {
Uint32 word = 0;
if (packedLayout.isFloatPacked) {
const Float fields[3] = {srcValues[mapping.sourceChannel[0]],
srcValues[mapping.sourceChannel[1]],
srcValues[mapping.sourceChannel[2]]};
word = type == GL_UNSIGNED_INT_5_9_9_9_REV
? EncodeSharedExponentRGB9E5(fields)
: (EncodeFloatToUnsignedF11(fields[0]) << packedLayout.shift[0]) |
(EncodeFloatToUnsignedF11(fields[1]) << packedLayout.shift[1]) |
(EncodeFloatToUnsignedF10(fields[2]) << packedLayout.shift[2]);
} else {
// Normalized encode: round(clamp(v, 0, 1) * (2^bits - 1)) into each field.
for (Int ch = 0; ch < packedLayout.fieldCount; ++ch) {
const auto fieldMax = static_cast<Float>((1u << packedLayout.width[ch]) - 1u);
const auto v = static_cast<Uint32>(std::llround(
std::clamp(srcValues[mapping.sourceChannel[ch]], 0.0f, 1.0f) * fieldMax));
word |= v << packedLayout.shift[ch];
}
}
WritePackedReadbackWord(dstPixel, word, packedLayout.byteSize);
} else {
for (Int ch = 0; ch < mapping.channelCount; ++ch) {
const Float v = srcValues[mapping.sourceChannel[ch]];
Uint8* dstComponent = dstPixel + static_cast<SizeT>(ch) * dstComponentSize;
switch (type) {
case GL_UNSIGNED_BYTE:
*dstComponent = static_cast<Uint8>(std::llround(std::clamp(v, 0.0f, 1.0f) * 255.0));
break;
case GL_BYTE: {
const auto out = static_cast<Int8>(std::llround(std::clamp(v, -1.0f, 1.0f) * 127.0));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_UNSIGNED_SHORT: {
const auto out = static_cast<Uint16>(std::llround(std::clamp(v, 0.0f, 1.0f) * 65535.0));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_SHORT: {
const auto out = static_cast<Int16>(std::llround(std::clamp(v, -1.0f, 1.0f) * 32767.0));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_UNSIGNED_INT: {
const auto out = static_cast<Uint32>(
std::llround(static_cast<Double>(std::clamp(v, 0.0f, 1.0f)) * 4294967295.0));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_INT: {
const auto out = static_cast<Int32>(
std::llround(static_cast<Double>(std::clamp(v, -1.0f, 1.0f)) * 2147483647.0));
Memcpy(dstComponent, &out, sizeof(out));
break;
}
case GL_FLOAT:
Memcpy(dstComponent, &v, sizeof(v));
break;
case GL_HALF_FLOAT: {
const Uint16 out = EncodeFloatToHalfBits(v);
Memcpy(dstComponent, &out, sizeof(out));
break;
}
default:
break;
}
}
}
}
}
}
static SizeT AlignReadbackRow(SizeT rowBytes, Int alignment) {
const SizeT align = alignment > 0 ? static_cast<SizeT>(alignment) : 1;
return (rowBytes + align - 1) / align * align;
}
// Walks the client-side destination the PACK parameters describe and hands each row to
// `fillRow(slice, row, dstRow)`, which writes width * dstPixelBytes bytes of finished client
// texels. Shared by the converting and the raw-word stores so both address the destination
// identically. The destination is always client memory: a readback into a pack buffer takes
// the verb path and never reaches these stores.
// applyPackImageParams: GL_PACK_IMAGE_HEIGHT / GL_PACK_SKIP_IMAGES apply only to GetTexImage
// of 3D/array images; ReadPixels and 2D GetTexImage ignore them (GL 3.3 sections 4.3.1, 6.1.4).
// Per the GL addressing rules, slice k row j lands at
// SKIP_IMAGES*imageStride + SKIP_ROWS*rowStride + SKIP_PIXELS*pixelBytes
// + k*imageStride + j*rowStride, with imageStride = max(IMAGE_HEIGHT, sliceHeight)*rowStride.
template <typename FillRow>
static Bool StoreClientRows(SizeT dstPixelBytes, SizeT swapGroupSize, GLsizei width, GLsizei sliceHeight,
GLsizei sliceCount, void* pixels, Bool applyPackImageParams, FillRow&& fillRow) {
// Destination layout is computed from the client-side PACK parameters; only the actual pixel
// rows are written so skip regions of the destination stay untouched.
const auto packParams = MG_Pipe::gPipeInputs->GetPixelStoreParameters(false);
const SizeT rowPixels = static_cast<SizeT>(packParams.RowLength > 0 ? packParams.RowLength : width);
const SizeT dstRowStride = AlignReadbackRow(rowPixels * dstPixelBytes, packParams.Alignment);
const SizeT imageRows = applyPackImageParams && packParams.ImageHeight > 0
? static_cast<SizeT>(packParams.ImageHeight)
: static_cast<SizeT>(sliceHeight);
const SizeT dstImageStride = imageRows * dstRowStride;
const SizeT skipImages =
applyPackImageParams ? static_cast<SizeT>(std::max(packParams.SkipImages, 0)) : SizeT{0};
const SizeT dstSkipOffset = skipImages * dstImageStride +
static_cast<SizeT>(std::max(packParams.SkipRows, 0)) * dstRowStride +
static_cast<SizeT>(std::max(packParams.SkipPixels, 0)) * dstPixelBytes;
const SizeT dstRowBytes = static_cast<SizeT>(width) * dstPixelBytes;
Vector<Uint8> convertedRow(dstRowBytes);
for (GLsizei slice = 0; slice < sliceCount; ++slice) {
for (GLsizei row = 0; row < sliceHeight; ++row) {
fillRow(slice, row, convertedRow.data());
if (packParams.SwapBytes && swapGroupSize > 1) {
for (SizeT offset = 0; offset + swapGroupSize <= dstRowBytes; offset += swapGroupSize) {
std::reverse(convertedRow.data() + offset, convertedRow.data() + offset + swapGroupSize);
}
}
const SizeT dstOffset = dstSkipOffset + static_cast<SizeT>(slice) * dstImageStride +
static_cast<SizeT>(row) * dstRowStride;
Memcpy(static_cast<Uint8*>(pixels) + dstOffset, convertedRow.data(), dstRowBytes);
}
}
return true;
}
// Repacks wide RGBA(_INTEGER) rows into the client's (format, type) layout, honoring the
// client-side PACK parameters. `wide` holds
// `sliceHeight * sliceCount` rows of `width` texels (slice-major, tightly stacked),
// 4 components x GetReadbackComponentSize(wideType) bytes each.
Bool StoreWideRowsToClient(const Uint8* wide, GLenum wideType, GLsizei width, GLsizei sliceHeight,
GLsizei sliceCount, const ReadbackChannelMapping& mapping, GLenum type, void* pixels,
Bool applyPackImageParams) {
const SizeT dstPixelBytes = GetReadbackDstPixelSize(mapping, type);
if (dstPixelBytes == 0) {
return false;
}
PackedReadbackLayout packedLayout{};
const Bool isPackedType = GetPackedReadbackLayout(type, packedLayout);
const SizeT swapGroupSize = isPackedType ? packedLayout.byteSize : GetReadbackComponentSize(type);
const SizeT srcPixelBytes = 4 * GetReadbackComponentSize(wideType);
return StoreClientRows(
dstPixelBytes, swapGroupSize, width, sliceHeight, sliceCount, pixels, applyPackImageParams,
[&](GLsizei slice, GLsizei row, Uint8* dstRow) {
const SizeT flatRow =
static_cast<SizeT>(slice) * static_cast<SizeT>(sliceHeight) + static_cast<SizeT>(row);
const Uint8* srcRow = wide + flatRow * static_cast<SizeT>(width) * srcPixelBytes;
ConvertWideReadbackRow(srcRow, dstRow, static_cast<SizeT>(width), wideType, mapping, type);
});
}
Bool StorePackedWordsToClient(const Uint8* srcWords, GLsizei width, GLsizei sliceHeight, GLsizei sliceCount,
GLenum type, void* pixels, Bool applyPackImageParams) {
PackedReadbackLayout packedLayout{};
if (!GetPackedReadbackLayout(type, packedLayout) || packedLayout.byteSize != 4) {
return false;
}
const SizeT srcRowBytes = static_cast<SizeT>(width) * 4;
return StoreClientRows(4, packedLayout.byteSize, width, sliceHeight, sliceCount, pixels,
applyPackImageParams, [&](GLsizei slice, GLsizei row, Uint8* dstRow) {
const SizeT flatRow =
static_cast<SizeT>(slice) * static_cast<SizeT>(sliceHeight) +
static_cast<SizeT>(row);
Memcpy(dstRow, srcWords + flatRow * srcRowBytes, srcRowBytes);
});
}
} // namespace ClientReadback
} // namespace MobileGL::MG_Backend