[ScheduleDAG] Allow disabling the SchedModel / Itineraries during Scheduling (llvm#138057)

This provides the `disable-schedmodel-in-sched-mi` flag. Using this, we
will disable the SchedModel / Itineraries during scheduling. This has
the effect of not using any latency / hardware resource information for
scheduling decisions.

We have the `schedmodel` flag, but this disables the `SchedModel` for
all passes. This allows disabling only for scheduling while preserving
the behavior of other passes (e.g. MachineLICM). This is conceptually
similar to other flags like `enable-aa-sched-mi`

Author: jrbyrnes

llvm/include/llvm/CodeGen/TargetSchedule.h

@@ -45,6 +45,16 @@ class TargetSchedModel {
 
   unsigned computeInstrLatency(const MCSchedClassDesc &SCDesc) const;
 
+  // EnableSchedModel and EnableSchedItins are used to control whether or not to
+  // use the Target's {SchedMachineModel, InstrItins} for hardware infor based
+  // Scheduling decisions. If both are enabled, as is the default, preference
+  // will be given to one based on the API implementation. By disabling one, we
+  // can force preference of the other. By disabling both, we will throw away
+  // any target specific hardware details for scheduling decisions, and fall
+  // into things that provide generic info such as defaultDefLatency.
+  bool EnableSchedModel = true;
+  bool EnableSchedItins = true;
+
 public:
   TargetSchedModel() : SchedModel(MCSchedModel::Default) {}
 
@@ -53,7 +63,8 @@ class TargetSchedModel {
   /// The machine model API keeps a copy of the top-level MCSchedModel table
   /// indices and may query TargetSubtargetInfo and TargetInstrInfo to resolve
   /// dynamic properties.
-  void init(const TargetSubtargetInfo *TSInfo);
+  void init(const TargetSubtargetInfo *TSInfo, bool EnableSModel = true,
+            bool EnableSItins = true);
 
   /// Return the MCSchedClassDesc for this instruction.
   const MCSchedClassDesc *resolveSchedClass(const MachineInstr *MI) const;

llvm/lib/CodeGen/ScheduleDAGInstrs.cpp

@@ -69,6 +69,14 @@ static cl::opt<bool>
 static cl::opt<bool> UseTBAA("use-tbaa-in-sched-mi", cl::Hidden,
     cl::init(true), cl::desc("Enable use of TBAA during MI DAG construction"));
 
+static cl::opt<bool>
+    EnableSchedModel("schedmodel", cl::Hidden, cl::init(true),
+                     cl::desc("Use TargetSchedModel for latency lookup"));
+
+static cl::opt<bool>
+    EnableSchedItins("scheditins", cl::Hidden, cl::init(true),
+                     cl::desc("Use InstrItineraryData for latency lookup"));
+
 // Note: the two options below might be used in tuning compile time vs
 // output quality. Setting HugeRegion so large that it will never be
 // reached means best-effort, but may be slow.
@@ -121,7 +129,7 @@ ScheduleDAGInstrs::ScheduleDAGInstrs(MachineFunction &mf,
   DbgValues.clear();
 
   const TargetSubtargetInfo &ST = mf.getSubtarget();
-  SchedModel.init(&ST);
+  SchedModel.init(&ST, EnableSchedModel, EnableSchedItins);
 }
 
 /// If this machine instr has memory reference information and it can be

llvm/lib/CodeGen/TargetSchedule.cpp

@@ -30,12 +30,6 @@
 
 using namespace llvm;
 
-static cl::opt<bool> EnableSchedModel("schedmodel", cl::Hidden, cl::init(true),
-  cl::desc("Use TargetSchedModel for latency lookup"));
-
-static cl::opt<bool> EnableSchedItins("scheditins", cl::Hidden, cl::init(true),
-  cl::desc("Use InstrItineraryData for latency lookup"));
-
 static cl::opt<bool> ForceEnableIntervals(
     "sched-model-force-enable-intervals", cl::Hidden, cl::init(false),
     cl::desc("Force the use of resource intervals in the schedule model"));
@@ -48,12 +42,16 @@ bool TargetSchedModel::hasInstrItineraries() const {
   return EnableSchedItins && !InstrItins.isEmpty();
 }
 
-void TargetSchedModel::init(const TargetSubtargetInfo *TSInfo) {
+void TargetSchedModel::init(const TargetSubtargetInfo *TSInfo,
+                            bool EnableSModel, bool EnableSItins) {
   STI = TSInfo;
   SchedModel = TSInfo->getSchedModel();
   TII = TSInfo->getInstrInfo();
   STI->initInstrItins(InstrItins);
 
+  EnableSchedModel = EnableSModel;
+  EnableSchedItins = EnableSItins;
+
   unsigned NumRes = SchedModel.getNumProcResourceKinds();
   ResourceFactors.resize(NumRes);
   ResourceLCM = SchedModel.IssueWidth;

llvm/test/CodeGen/AMDGPU/sched-no-schedmodel.mir

@@ -0,0 +1,50 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -misched-cluster=false --misched-prera-direction=topdown -run-pass=machine-scheduler --schedmodel=1 -o - %s | FileCheck -check-prefix=GCN %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -misched-cluster=false --misched-prera-direction=topdown -run-pass=machine-scheduler --schedmodel=0 -o - %s | FileCheck -check-prefix=GCN-NO-SCHEDMODEL %s
+
+---
+name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
+tracksRegLiveness: true
+body: |
+  bb.0:
+
+    ; GCN-LABEL: name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
+    ; GCN: [[DEF:%[0-9]+]]:vreg_128_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vreg_128_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: early-clobber %2:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 [[DEF]].sub0_sub1, [[DEF1]].sub0_sub1, 0, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: dead [[DS_READ_U16_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF2]], 0, 0, implicit $exec
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: dead [[DS_READ_U16_gfx9_1:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF3]], 0, 0, implicit $exec
+    ; GCN-NEXT: [[DEF4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: dead [[DS_READ_U16_gfx9_2:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF4]], 0, 0, implicit $exec
+    ; GCN-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 %2.sub0, %2.sub1, implicit $exec
+    ; GCN-NEXT: early-clobber %3:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 [[DEF]].sub0_sub1, [[DEF1]].sub0_sub1, 0, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NEXT: S_ENDPGM 0, implicit %2, implicit %3, implicit [[V_MUL_LO_U32_e64_]]
+    ;
+    ; GCN-NO-SCHEDMODEL-LABEL: name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
+    ; GCN-NO-SCHEDMODEL: [[DEF:%[0-9]+]]:vreg_128_align2 = IMPLICIT_DEF
+    ; GCN-NO-SCHEDMODEL-NEXT: [[DEF1:%[0-9]+]]:vreg_128_align2 = IMPLICIT_DEF
+    ; GCN-NO-SCHEDMODEL-NEXT: early-clobber %2:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 [[DEF]].sub0_sub1, [[DEF1]].sub0_sub1, 0, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: early-clobber %3:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 [[DEF]].sub0_sub1, [[DEF1]].sub0_sub1, 0, 0, 0, 0, implicit $mode, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 %2.sub0, %2.sub1, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NO-SCHEDMODEL-NEXT: dead [[DS_READ_U16_gfx9_:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF2]], 0, 0, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NO-SCHEDMODEL-NEXT: dead [[DS_READ_U16_gfx9_1:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF3]], 0, 0, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: [[DEF4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NO-SCHEDMODEL-NEXT: dead [[DS_READ_U16_gfx9_2:%[0-9]+]]:vgpr_32 = DS_READ_U16_gfx9 [[DEF4]], 0, 0, implicit $exec
+    ; GCN-NO-SCHEDMODEL-NEXT: S_ENDPGM 0, implicit %2, implicit %3, implicit [[V_MUL_LO_U32_e64_]]
+    %0:vreg_128_align2 = IMPLICIT_DEF
+    %1:vreg_128_align2 = IMPLICIT_DEF
+    %2:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 %0.sub0_sub1:vreg_128_align2, %1.sub0_sub1:vreg_128_align2, 0, 0, 0, 0, implicit $mode, implicit $exec
+    %3:vreg_512_align2 = contract V_MFMA_F32_32X32X16_FP8_FP8_vgprcd_e64 %0.sub0_sub1:vreg_128_align2, %1.sub0_sub1:vreg_128_align2, 0, 0, 0, 0, implicit $mode, implicit $exec
+    %4:vgpr_32 = nsw V_MUL_LO_U32_e64 %2.sub0, %2.sub1, implicit $exec
+    %5:vgpr_32 = IMPLICIT_DEF
+    %6:vgpr_32 = DS_READ_U16_gfx9 %5, 0, 0, implicit $exec
+    %7:vgpr_32 = IMPLICIT_DEF
+    %8:vgpr_32 = DS_READ_U16_gfx9 %7, 0, 0, implicit $exec
+    %9:vgpr_32 = IMPLICIT_DEF
+    %10:vgpr_32 = DS_READ_U16_gfx9 %9, 0, 0, implicit $exec
+    S_ENDPGM 0, implicit %2, implicit %3, implicit %4
+...