+ (!Available[IDFetch].empty() || !Available[IDOther].empty());
+
+ if (CurInstKind == IDAlu && !Available[IDFetch].empty()) {
+ // We use the heuristic provided by AMD Accelerated Parallel Processing
+ // OpenCL Programming Guide :
+ // The approx. number of WF that allows TEX inst to hide ALU inst is :
+ // 500 (cycles for TEX) / (AluFetchRatio * 8 (cycles for ALU))
+ float ALUFetchRationEstimate =
+ (AluInstCount + AvailablesAluCount() + Pending[IDAlu].size()) /
+ (FetchInstCount + Available[IDFetch].size());
+ unsigned NeededWF = 62.5f / ALUFetchRationEstimate;
+ DEBUG( dbgs() << NeededWF << " approx. Wavefronts Required\n" );
+ // We assume the local GPR requirements to be "dominated" by the requirement
+ // of the TEX clause (which consumes 128 bits regs) ; ALU inst before and
+ // after TEX are indeed likely to consume or generate values from/for the
+ // TEX clause.
+ // Available[IDFetch].size() * 2 : GPRs required in the Fetch clause
+ // We assume that fetch instructions are either TnXYZW = TEX TnXYZW (need
+ // one GPR) or TmXYZW = TnXYZW (need 2 GPR).
+ // (TODO : use RegisterPressure)
+ // If we are going too use too many GPR, we flush Fetch instruction to lower
+ // register pressure on 128 bits regs.
+ unsigned NearRegisterRequirement = 2 * Available[IDFetch].size();
+ if (NeededWF > getWFCountLimitedByGPR(NearRegisterRequirement))
+ AllowSwitchFromAlu = true;
+ }
+
+
+ // We want to scheduled AR defs as soon as possible to make sure they aren't
+ // put in a different ALU clause from their uses.
+ if (!SU && !UnscheduledARDefs.empty()) {
+ SU = UnscheduledARDefs[0];
+ UnscheduledARDefs.erase(UnscheduledARDefs.begin());
+ NextInstKind = IDAlu;
+ }