raphiaura/KytyPS5
1
0
Fork 0
mirror of https://github.com/KytyPS5/KytyPS5.git synced 2026-10-20 19:07:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

shader: implement V_COS_F16

Browse Source
This commit is contained in:
nmzik
2026-08-29 19:03:33 +04:00
parent 5bd447d2a2
commit 1a87cfedb5
7 changed files with 90 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ShaderRecompilerComputeTests.cpp
+41
View File
@@ -11896,6 +11896,7 @@ CoverageClass ClassifyOpcode(ShaderOpcode opcode,
case Opcode::V_RSQ_F16:
case Opcode::V_LOG_F16:
case Opcode::V_EXP_F16:
case Opcode::V_COS_F16:
case Opcode::V_MAD_MIXLO_F16:
case Opcode::V_MAD_MIXHI_F16:
case Opcode::DS_MIN_F32:
@@ -14489,6 +14490,45 @@ TestCase VectorSpecialF16Ops() {
O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
}
TestCase VectorCosF16CapturedSdwaAndEdges() {
using O = ShaderOpcode;
std::vector<u32> code;
AppendVMovLiteral(&code, 4, 0x34001234u); // high=+0.25h, low sentinel
code.push_back(0x7e08c2f9u);
code.push_back(0x00051504u); // captured v_cos_f16 v4.word1, v4.word1
AppendVMovLiteral(&code, 5, 0x00008000u); // -0.0h
code.push_back(EncodeVop1(0x61, 6, Vgpr(5)));
AppendVMovLiteral(&code, 7, 0x00007bffu); // max finite
code.push_back(EncodeVop1(0x61, 8, Vgpr(7)));
AppendVMovLiteral(&code, 9, 0x00007c00u); // +inf
code.push_back(EncodeVop1(0x61, 10, Vgpr(9)));
AppendVMovLiteral(&code, 11, 0x00000001u); // minimum positive denormal
code.push_back(EncodeVop1(0x61, 12, Vgpr(11)));
AppendVMovLiteral(&code, 13, 0x00003800u); // +0.5h
code.push_back(EncodeVop1(0x61, 14, Vgpr(13)));
for (u32 i = 0; i < 6; i++) {
AppendStoreVgpr(&code, 4 + i * 2, i);
}
AppendEnd(&code);
TestCase test{"VectorCosF16CapturedSdwaAndEdges",
code,
{},
{0x00001234u, 0x00003c00u, 0x00003c00u, 0x0000fe00u,
0x00003c00u, 0x0000bc00u},
{O::V_MOV_B32, O::V_COS_F16, O::BUFFER_STORE_DWORD,
O::S_ENDPGM}};
test.decoded_counts = {{"V_COS_F16", 6},
{"V_COS_F16 v4.sdwa(sel=5,sext=0), "
"v4.sdwa(sel=5,sext=0)",
1}};
test.ir_counts = {{" = FPCos ", 6}};
test.required_spirv = {" Fract ", " Cos ", " PackHalf2x16 "};
test.forbidden_spirv = {"OpCapability Float16"};
return test;
}
TestCase VectorWritelaneIgnoresExecMask() {
using O = ShaderOpcode;
@@ -20688,6 +20728,7 @@ std::vector<TestCase> MakeCases() {
AddCase(VectorCvtU16F16Sdwa);
AddCase(VectorMinMaxMed3F16Ops);
AddCase(VectorSpecialF16Ops);
AddCase(VectorCosF16CapturedSdwaAndEdges);
AddCase(VectorWritelaneIgnoresExecMask);
AddCase(VectorReadlaneFromInactiveWrittenLane);
AddCase(VectorLaneWave32RuntimeSelectorWraps);
tests/shaderCfgTests.cpp
+16
View File
@@ -4031,6 +4031,22 @@ void TestNewShaderDecoderArchitecture() {
ffbh_i32.src0.reg == 14u,
"decoder rejected the captured VOP1 V_FFBH_I32 instruction");
const uint32_t cos_f16_code[] = {0x7e08c2f9u, 0x00051504u};
Instruction cos_f16;
Check(DecodeInstruction(cos_f16_code, 0u, cos_f16, &error), error.c_str());
Check(cos_f16.family == Family::VOP1 &&
cos_f16.opcode == Opcode::V_COS_F16 &&
cos_f16.word_count == 2u && cos_f16.src_count == 1u &&
cos_f16.dst.kind == OperandKind::Vgpr && cos_f16.dst.reg == 4u &&
cos_f16.dst.sdwa_sel == 5u &&
cos_f16.dst.sdwa_dst_unused == 2u && !cos_f16.dst.clamp &&
cos_f16.dst.omod == 0u &&
cos_f16.src0.kind == OperandKind::Vgpr &&
cos_f16.src0.reg == 4u && cos_f16.src0.sdwa_sel == 5u &&
!cos_f16.src0.sdwa_sext && !cos_f16.src0.negate &&
!cos_f16.src0.absolute,
"decoder rejected the captured VOP1 SDWA V_COS_F16 instruction");
const uint32_t literal_code[] = {EncodeVop1(0x01, 2, 255u), 0x12345678u};
Instruction literal;
Check(DecodeInstruction(literal_code, 0u, literal, &error), error.c_str());