void emitFlow(const Instruction *);
+ void emitSHFL(const Instruction *);
+
void emitVOTE(const Instruction *);
void emitSULDGB(const TexInstruction *);
{
const ImmediateValue *imm = ref.get()->asImm();
- return imm && (imm->reg.data.u32 & ((ty == TYPE_F32) ? 0xfff : 0xfff00000));
+ if (ty == TYPE_F32)
+ return imm && imm->reg.data.u32 & 0xfff;
+ else
+ return imm && (imm->reg.data.s32 > 0x7ffff ||
+ imm->reg.data.s32 < -0x80000);
}
void
code[1] |= ((u64 & 0x7fe0000000000000ULL) >> 53);
code[1] |= ((u64 & 0x8000000000000000ULL) >> 36);
} else {
- assert((u32 & 0xfff00000) == 0 || (u32 & 0xfff00000) == 0xfff00000);
+ assert((u32 & 0xfff80000) == 0 || (u32 & 0xfff80000) == 0xfff80000);
code[0] |= (u32 & 0x001ff) << 23;
code[1] |= (u32 & 0x7fe00) >> 9;
code[1] |= (u32 & 0x80000) << 8;
assert(!i->src(0).mod.neg() && !i->src(1).mod.neg());
assert(!i->src(0).mod.abs() && !i->src(1).mod.abs());
- if (i->src(1).getFile() == FILE_IMMEDIATE) {
+ if (isLIMM(i->src(1), TYPE_S32)) {
emitForm_L(i, 0x280, 2, Modifier(0));
if (i->subOp == NV50_IR_SUBOP_MUL_HIGH)
}
}
+void
+CodeEmitterGK110::emitSHFL(const Instruction *i)
+{
+ const ImmediateValue *imm;
+
+ code[0] = 0x00000002;
+ code[1] = 0x78800000 | (i->subOp << 1);
+
+ emitPredicate(i);
+
+ defId(i->def(0), 2);
+ srcId(i->src(0), 10);
+
+ switch (i->src(1).getFile()) {
+ case FILE_GPR:
+ srcId(i->src(1), 23);
+ break;
+ case FILE_IMMEDIATE:
+ imm = i->getSrc(1)->asImm();
+ assert(imm && imm->reg.data.u32 < 0x20);
+ code[0] |= imm->reg.data.u32 << 23;
+ code[0] |= 1 << 31;
+ break;
+ default:
+ assert(!"invalid src1 file");
+ break;
+ }
+
+ switch (i->src(2).getFile()) {
+ case FILE_GPR:
+ srcId(i->src(2), 42);
+ break;
+ case FILE_IMMEDIATE:
+ imm = i->getSrc(2)->asImm();
+ assert(imm && imm->reg.data.u32 < 0x2000);
+ code[1] |= imm->reg.data.u32 << 5;
+ code[1] |= 1;
+ break;
+ default:
+ assert(!"invalid src2 file");
+ break;
+ }
+
+ if (!i->defExists(1))
+ code[1] |= 7 << 19;
+ else {
+ assert(i->def(1).getFile() == FILE_PREDICATE);
+ defId(i->def(1), 51);
+ }
+}
+
void
CodeEmitterGK110::emitVOTE(const Instruction *i)
{
- assert(i->src(0).getFile() == FILE_PREDICATE);
+ const ImmediateValue *imm;
+ uint32_t u32;
code[0] = 0x00000002;
code[1] = 0x86c00000 | (i->subOp << 19);
code[0] |= 255 << 2;
if (!(rp & 2))
code[1] |= 7 << 16;
- if (i->src(0).mod == Modifier(NV50_IR_MOD_NOT))
- code[1] |= 1 << 13;
- srcId(i->src(0), 42);
+
+ switch (i->src(0).getFile()) {
+ case FILE_PREDICATE:
+ if (i->src(0).mod == Modifier(NV50_IR_MOD_NOT))
+ code[0] |= 1 << 13;
+ srcId(i->src(0), 42);
+ break;
+ case FILE_IMMEDIATE:
+ imm = i->getSrc(0)->asImm();
+ assert(imm);
+ u32 = imm->reg.data.u32;
+ assert(u32 == 0 || u32 == 1);
+ code[1] |= (u32 == 1 ? 0x7 : 0xf) << 10;
+ break;
+ default:
+ assert(!"Unhandled src");
+ break;
+ }
}
void
case SV_INVOCATION_ID: return 0x11;
case SV_YDIR: return 0x12;
case SV_THREAD_KILL: return 0x13;
+ case SV_COMBINED_TID: return 0x20;
case SV_TID: return 0x21 + SDATA(ref).sv.index;
case SV_CTAID: return 0x25 + SDATA(ref).sv.index;
case SV_NTID: return 0x29 + SDATA(ref).sv.index;
case SV_NCTAID: return 0x2d + SDATA(ref).sv.index;
case SV_LBASE: return 0x34;
case SV_SBASE: return 0x30;
+ case SV_LANEMASK_EQ: return 0x38;
+ case SV_LANEMASK_LT: return 0x39;
+ case SV_LANEMASK_LE: return 0x3a;
+ case SV_LANEMASK_GT: return 0x3b;
+ case SV_LANEMASK_GE: return 0x3c;
case SV_CLOCK: return 0x50 + SDATA(ref).sv.index;
default:
assert(!"no sreg for system value");
case OP_CCTL:
emitCCTL(insn);
break;
+ case OP_SHFL:
+ emitSHFL(insn);
+ break;
case OP_VOTE:
emitVOTE(insn);
break;