shader: support DS_WRITE_B8_D16_HI (#794)

Decode GFX10 DS opcode 0xa0 as DS_WRITE_B8_D16_HI (next to
DS_WRITE_B16_D16_HI at 0xa1) and lower it through the existing 8-bit
shared-memory write. The stored byte is bits 23:16 of the data VGPR,
selected with SDWA BYTE_2 on src1.

Add captured-instruction decode coverage (from GTA V, PPSA04264) and a
runtime regression that writes one byte of a distinctive source value
into a pre-filled LDS dword.
This commit is contained in:
Deniz ŞAHİN
2026-09-23 23:44:39 +03:00
committed by GitHub
parent 569ec04d1a
commit fc86509aac
6 changed files with 60 additions and 1 deletions
@@ -107,6 +107,7 @@ constexpr MemoryOpcodeInfo DS_OPCODE_LIST[] = {
{0x4du, Opcode::DS_WRITE_B64, 2, 32}, {0x4eu, Opcode::DS_WRITE2_B64, 4, 32},
{0x4fu, Opcode::DS_WRITE2ST64_B64, 4, 32}, {0x76u, Opcode::DS_READ_B64, 2, 32},
{0x77u, Opcode::DS_READ2_B64, 4, 32}, {0x78u, Opcode::DS_READ2ST64_B64, 4, 32},
{0xa0u, Opcode::DS_WRITE_B8_D16_HI, 1, 8},
{0xa1u, Opcode::DS_WRITE_B16_D16_HI, 1, 16},
{0xa6u, Opcode::DS_READ_U16_D16, 1, 16},
{0xa7u, Opcode::DS_READ_U16_D16_HI, 1, 16},
@@ -147,6 +148,7 @@ bool IsDsWriteOpcode(Opcode opcode) {
switch (opcode) {
case Opcode::DS_WRITE_B8:
case Opcode::DS_WRITE_B16:
case Opcode::DS_WRITE_B8_D16_HI:
case Opcode::DS_WRITE_B16_D16_HI:
case Opcode::DS_WRITE2_B32:
case Opcode::DS_WRITE2ST64_B32:
@@ -429,7 +431,9 @@ void DecodeDs(uint32_t pc, std::span<const uint32_t> code, uint32_t word_index,
}
DecodeVectorGpr(addr, inst.src0);
DecodeVectorGpr(data0, inst.src1);
if (inst.opcode == Opcode::DS_WRITE_B16_D16_HI) {
if (inst.opcode == Opcode::DS_WRITE_B8_D16_HI) {
inst.src1.sdwa_sel = 2u;
} else if (inst.opcode == Opcode::DS_WRITE_B16_D16_HI) {
inst.src1.sdwa_sel = 5u;
}
DecodeVectorGpr(data1, inst.src2);
@@ -694,6 +694,7 @@ std::string InstructionToString(const Instruction& inst) {
case Opcode::DS_READ_B128:
case Opcode::DS_WRITE_B8:
case Opcode::DS_WRITE_B16:
case Opcode::DS_WRITE_B8_D16_HI:
case Opcode::DS_WRITE_B16_D16_HI:
case Opcode::DS_WRITE2_B32:
case Opcode::DS_WRITE2ST64_B32:
@@ -541,6 +541,7 @@ enum class Opcode {
DS_READ_B128,
DS_WRITE_B8,
DS_WRITE_B16,
DS_WRITE_B8_D16_HI,
DS_WRITE_B16_D16_HI,
DS_WRITE2_B32,
DS_WRITE2ST64_B32,
@@ -235,6 +235,7 @@ Decoder::Operand MemorySourceAt(const Decoder::Instruction& decoded, uint32_t in
return index == 0u ? decoded.src1 : index == 1u ? decoded.src0 : decoded.src2;
case Decoder::Opcode::DS_WRITE_B8:
case Decoder::Opcode::DS_WRITE_B16:
case Decoder::Opcode::DS_WRITE_B8_D16_HI:
case Decoder::Opcode::DS_WRITE_B16_D16_HI:
case Decoder::Opcode::DS_WRITE_B32:
case Decoder::Opcode::DS_WRITE_B64:
@@ -1076,6 +1077,7 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst) {
case Decoder::Opcode::DS_WRITE2ST64_B64: return DS_WRITE2(inst);
case Decoder::Opcode::DS_WRITE_B8:
case Decoder::Opcode::DS_WRITE_B16:
case Decoder::Opcode::DS_WRITE_B8_D16_HI:
case Decoder::Opcode::DS_WRITE_B16_D16_HI:
case Decoder::Opcode::DS_WRITE_B32:
case Decoder::Opcode::DS_WRITE_B64:
+34
View File
@@ -16416,6 +16416,7 @@ CoverageClass ClassifyOpcode(ShaderOpcode opcode,
case Opcode::DS_READ_B128:
case Opcode::DS_WRITE_B8:
case Opcode::DS_WRITE_B16:
case Opcode::DS_WRITE_B8_D16_HI:
case Opcode::DS_WRITE_B16_D16_HI:
case Opcode::DS_WRITE2_B32:
case Opcode::DS_WRITE2ST64_B32:
@@ -24688,6 +24689,38 @@ TestCase DsWriteB16D16HiCapturedUsesHighHalf() {
return test;
}
TestCase DsWriteB8D16HiWritesByteTwo() {
using O = ShaderOpcode;
std::vector<u32> code;
AppendVMovU32(&code, 1, 0);
AppendVMovLiteral(&code, 3, 0xdeadbeefu);
code.push_back(EncodeDs0(0x0d));
code.push_back(EncodeDs1(0, 3, 1)); // ds_write_b32 v1, v3
// Every byte of the source differs, so selecting any byte but 23:16 fails.
AppendVMovU32(&code, 20, 1);
AppendVMovLiteral(&code, 2, 0x11a22233u);
AppendVMovLiteral(&code, 0, 0x87654321u);
code.push_back(EncodeDs0(0xa0));
code.push_back(EncodeDs1(0, 2, 20)); // ds_write_b8_d16_hi v20, v2
code.push_back(EncodeDs0(0x36));
code.push_back(EncodeDs1(4, 0, 1)); // ds_read_b32 v4, v1
AppendStoreVgpr(&code, 4, 0);
AppendStoreVgpr(&code, 0, 1);
AppendEnd(&code);
TestCase test{"DsWriteB8D16HiWritesByteTwo",
code,
std::vector<u32>(2, 0),
{0xdeada2efu, 0x87654321u},
{O::V_MOV_B32, O::DS_WRITE_B32, O::DS_WRITE_B8_D16_HI,
O::DS_READ_B32, O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
test.decoded_counts = {{"DS_WRITE_B8_D16_HI", 1}};
return test;
}
TestCase DsReadU16D16HiCapturedPreservesLowHalf() {
using O = ShaderOpcode;
@@ -28177,6 +28210,7 @@ std::vector<TestCase> MakeCases() {
AddCase(ScratchIsPrivatePerInvocation);
AddCase(DsReadWriteVariants);
AddCase(DsWriteB16D16HiCapturedUsesHighHalf);
AddCase(DsWriteB8D16HiWritesByteTwo);
AddCase(DsReadU16D16CapturedPreservesHighHalf);
AddCase(DsReadU16D16HiCapturedPreservesLowHalf);
AddCase(DsAppendConsumeUsesEncodedLdsSelector);
+17
View File
@@ -4458,6 +4458,23 @@ void TestNewShaderDecoderArchitecture() {
d16_hi_write.src1.sdwa_sel == 5u,
"DS decoder rejected the captured high-half D16 write");
// Captured from GTA V (PPSA04264) compute shader, pc 0x1598.
const uint32_t d16_hi_byte_write_ds[] = {0xda800200u, 0x00001413u};
Instruction d16_hi_byte_write;
ShaderRecompiler::Decoder::DecodeInstruction(d16_hi_byte_write_ds, 0u,
d16_hi_byte_write);
Check(d16_hi_byte_write.family == Family::DS &&
d16_hi_byte_write.opcode == Opcode::DS_WRITE_B8_D16_HI &&
d16_hi_byte_write.word_count == 2u &&
d16_hi_byte_write.src_count == 2u &&
d16_hi_byte_write.data_dwords == 1u &&
d16_hi_byte_write.data_bits == 8u &&
d16_hi_byte_write.offset == 0x200u && !d16_hi_byte_write.gds &&
d16_hi_byte_write.src0.reg == 19u &&
d16_hi_byte_write.src1.reg == 20u &&
d16_hi_byte_write.src1.sdwa_sel == 2u,
"DS decoder rejected the captured high-half byte write");
constexpr uint32_t packed_source_selectors[][2] = {
{0xcc0e0000u, 0x0c0a0300u}, // Source 0: instruction bit 59.
{0xcc0e0000u, 0x140a0300u}, // Source 1: instruction bit 60.