shader: implement DS_BPERMUTE_B32

Co-authored-by: Techx3 <56268269+Techx3@users.noreply.github.com>
This commit is contained in:
nmzik
2026-08-29 18:40:22 +04:00
parent a4fc58e908
commit 5bd447d2a2
10 changed files with 157 additions and 21 deletions
@@ -107,6 +107,7 @@ constexpr MemoryOpcodeInfo DS_OPCODE_LIST[] = {
{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},
{0xb3u, Opcode::DS_BPERMUTE_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},
};
@@ -195,6 +196,7 @@ uint32_t DsSourceCount(Opcode opcode) {
case Opcode::DS_WRITE2ST64_B64:
case Opcode::DS_MIN_F32:
case Opcode::DS_MAX_F32: return 3u;
case Opcode::DS_BPERMUTE_B32: return 2u;
case Opcode::DS_READ_ADDTID_B32:
case Opcode::DS_CONSUME:
case Opcode::DS_APPEND: return 0u;
@@ -395,9 +397,10 @@ void DecodeDs(uint32_t pc, std::span<const uint32_t> code, uint32_t word_index,
SetUnsupported(inst, Family::DS, opcode, "DS swizzle FFT mode is not implemented");
}
if (inst.gds &&
(inst.opcode == Opcode::DS_SWIZZLE_B32 || inst.opcode == Opcode::DS_WRITE_ADDTID_B32 ||
(inst.opcode == Opcode::DS_SWIZZLE_B32 || inst.opcode == Opcode::DS_BPERMUTE_B32 ||
inst.opcode == Opcode::DS_WRITE_ADDTID_B32 ||
inst.opcode == Opcode::DS_READ_ADDTID_B32)) {
SetUnsupported(inst, Family::DS, opcode, "DS swizzle/addtid is available only for LDS");
SetUnsupported(inst, Family::DS, opcode, "DS lane operation is available only for LDS");
}
if (inst.opcode == Opcode::DS_WRITE_ADDTID_B32 && data1 != 0u) {
SetUnsupported(inst, Family::DS, opcode,
@@ -661,6 +661,7 @@ std::string InstructionToString(const Instruction& inst) {
case Opcode::DS_MIN_F32:
case Opcode::DS_MAX_F32:
case Opcode::DS_SWIZZLE_B32:
case Opcode::DS_BPERMUTE_B32:
case Opcode::DS_READ_I8:
case Opcode::DS_READ_U8:
case Opcode::DS_READ_I16:
@@ -492,6 +492,7 @@ enum class Opcode {
DS_MIN_F32,
DS_MAX_F32,
DS_SWIZZLE_B32,
DS_BPERMUTE_B32,
DS_CONSUME,
DS_APPEND,
DS_READ_I8,
@@ -878,6 +878,13 @@ bool Translator::DS_SWIZZLE_B32(const Decoder::Instruction& inst) {
return true;
}
bool Translator::DS_BPERMUTE_B32(const Decoder::Instruction& inst) {
const auto address = ir.IAdd(ReadU32(inst.src0), IR::U32(IR::Value(inst.offset)));
WriteOperand(inst.dst, ir.Emit(IR::ValueOpcode::BpermuteU32,
{ReadU32(inst.src1), address, ir.GetExec()}));
return true;
}
bool Translator::EmitMemory(const Decoder::Instruction& inst, std::string* error) {
switch (inst.opcode) {
case Decoder::Opcode::S_LOAD_DWORD:
@@ -1036,6 +1043,7 @@ bool Translator::EmitMemory(const Decoder::Instruction& inst, std::string* error
case Decoder::Opcode::DS_MAX_F32:
return DS_MINMAX_F32(inst, IR::ValueOpcode::SharedAtomicFMax32);
case Decoder::Opcode::DS_SWIZZLE_B32: return DS_SWIZZLE_B32(inst);
case Decoder::Opcode::DS_BPERMUTE_B32: return DS_BPERMUTE_B32(inst);
case Decoder::Opcode::DS_CONSUME:
return DS_APPEND_CONSUME(inst, IR::ValueOpcode::DataConsume);
case Decoder::Opcode::DS_APPEND:
@@ -109,6 +109,7 @@ private:
bool DS_APPEND_CONSUME(const Decoder::Instruction& inst, IR::ValueOpcode opcode);
bool DS_ADDTID(const Decoder::Instruction& inst, bool write);
bool DS_SWIZZLE_B32(const Decoder::Instruction& inst);
bool DS_BPERMUTE_B32(const Decoder::Instruction& inst);
IR::F32 SelectF32(IR::U1 condition, IR::F32 true_value, IR::F32 false_value);
IR::U32 ConvertF32ToU32Saturated(IR::F32 value, float upper_bound, float safe_upper,