raphiaura/KytyPS5
1
0
Fork 0
mirror of https://github.com/KytyPS5/KytyPS5.git synced 2026-10-20 10:56:58 +02:00
Code Issues Packages Projects Releases Wiki Activity

shader: support DS_READ_U16_D16_HI (#356)

Browse Source 
Decode the high-half D16 LDS read and route it through the existing unsigned-short load lowering. Represent the destination as a high-half partial write so the low 16 bits of the VGPR remain intact. Add captured-instruction decode coverage and a Vulkan execution regression that verifies the preserved half.

Co-authored-by: SueryRD <the.ai.tester2@gmail.com>
This commit is contained in:
GodsWill Dev
2026-08-29 02:39:45 -04:00
committed by GitHub
parent 715539804b
commit 18b6c9059b
5 changed files with 45 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/graphics/shader/recompiler/frontend/decode/MemoryOps.cpp
+5 -3
View File
@@ -104,6 +104,7 @@ constexpr MemoryOpcodeInfo DS_OPCODE_LIST[] = {
{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},
{0xa6u, Opcode::DS_READ_U16_D16, 1, 16},
{0xa7u, Opcode::DS_READ_U16_D16_HI, 1, 16},
{0xb0u, Opcode::DS_WRITE_ADDTID_B32, 1, 32}, {0xb1u, Opcode::DS_READ_ADDTID_B32, 1, 32},
{0xdeu, Opcode::DS_WRITE_B96, 3, 32}, {0xdfu, Opcode::DS_WRITE_B128, 4, 32},
{0xfeu, Opcode::DS_READ_B96, 3, 32}, {0xffu, Opcode::DS_READ_B128, 4, 32},
@@ -421,10 +422,11 @@ void DecodeDs(uint32_t pc, std::span<const uint32_t> code, uint32_t word_index,
}
DecodeVectorGpr(vdst, inst.dst);
if (inst.opcode == Opcode::DS_READ_U16_D16) {
if (inst.opcode == Opcode::DS_READ_U16_D16 ||
inst.opcode == Opcode::DS_READ_U16_D16_HI) {
// Native D16 reads update only the selected destination half. Reuse the partial
// destination representation so typed IR translation preserves the upper word.
inst.dst.sdwa_sel = 4u;
// destination representation so typed IR translation preserves the other half.
inst.dst.sdwa_sel = inst.opcode == Opcode::DS_READ_U16_D16 ? 4u : 5u;
}
DecodeVectorGpr(addr, inst.src0);
DecodeVectorGpr(data0, inst.src1);
src/graphics/shader/recompiler/frontend/decode/ShaderDecoder.h
+1
View File
@@ -497,6 +497,7 @@ enum class Opcode {
DS_READ_I16,
DS_READ_U16,
DS_READ_U16_D16,
DS_READ_U16_D16_HI,
DS_READ2_B32,
DS_READ2ST64_B32,
DS_READ_B32,
src/graphics/shader/recompiler/frontend/translate/Memory.cpp
+1
View File
@@ -1050,6 +1050,7 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst, std::string* error
case Decoder::Opcode::DS_READ_I16:
case Decoder::Opcode::DS_READ_U16:
case Decoder::Opcode::DS_READ_U16_D16:
case Decoder::Opcode::DS_READ_U16_D16_HI:
case Decoder::Opcode::DS_READ_B32:
case Decoder::Opcode::DS_READ_B64:
case Decoder::Opcode::DS_READ_B96: