AMDGPU/SI: Implement a custom MachineSchedStrategy

Summary:
GCNSchedStrategy re-uses most of GenericScheduler, it's just uses
a different method to compute the excess and critical register
pressure limits.

It's not enabled by default, to enable it you need to pass -misched=gcn
to llc.

Shader DB stats:

32464 shaders in 17874 tests
Totals:
SGPRS: 1542846 -> 1643125 (6.50 %)
VGPRS: 1005595 -> 904653 (-10.04 %)
Spilled SGPRs: 29929 -> 27745 (-7.30 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 36688188 -> 37034900 (0.95 %) bytes
LDS: 1913 -> 1913 (0.00 %) blocks
Max Waves: 254101 -> 265125 (4.34 %)
Wait states: 0 -> 0 (0.00 %)

Totals from affected shaders:
SGPRS: 1338220 -> 1438499 (7.49 %)
VGPRS: 886221 -> 785279 (-11.39 %)
Spilled SGPRs: 29869 -> 27685 (-7.31 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 34315716 -> 34662428 (1.01 %) bytes
LDS: 1551 -> 1551 (0.00 %) blocks
Max Waves: 188127 -> 199151 (5.86 %)
Wait states: 0 -> 0 (0.00 %)

Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick

Subscribers: arsenm, kzhuravl, llvm-commits

Differential Revision: https://reviews.llvm.org/D23688

llvm-svn: 279995

1 files changed, 15 insertions, 1 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index a86603a..f144ce2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -18,6 +18,7 @@
 #include "AMDGPUCallLowering.h"
 #include "AMDGPUTargetObjectFile.h"
 #include "AMDGPUTargetTransformInfo.h"
+#include "GCNSchedStrategy.h"
 #include "R600ISelLowering.h"
 #include "R600InstrInfo.h"
 #include "R600MachineScheduler.h"
@@ -96,6 +97,14 @@ static ScheduleDAGInstrs *createSIMachineScheduler(MachineSchedContext *C) {
   return new SIScheduleDAGMI(C);
 }
 
+static ScheduleDAGInstrs *
+createGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
+  ScheduleDAGMILive *DAG =
+      new ScheduleDAGMILive(C, make_unique<GCNMaxOccupancySchedStrategy>(C));
+  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
+  return DAG;
+}
+
 static MachineSchedRegistry
 R600SchedRegistry("r600", "Run R600's custom scheduler",
                    createR600MachineScheduler);
@@ -104,6 +113,11 @@ static MachineSchedRegistry
 SISchedRegistry("si", "Run SI's custom scheduler",
                 createSIMachineScheduler);
 
+static MachineSchedRegistry
+GCNMaxOccupancySchedRegistry("gcn-max-occupancy",
+                             "Run GCN scheduler to maximize occupancy",
+                             createGCNMaxOccupancyMachineScheduler);
+
 static StringRef computeDataLayout(const Triple &TT) {
   if (TT.getArch() == Triple::r600) {
     // 32-bit pointers.
@@ -467,7 +481,7 @@ ScheduleDAGInstrs *GCNPassConfig::createMachineScheduler(
   const SISubtarget &ST = C->MF->getSubtarget<SISubtarget>();
   if (ST.enableSIScheduler())
     return createSIMachineScheduler(C);
-  return nullptr;
+  return createGCNMaxOccupancyMachineScheduler(C);
 }
 
 bool GCNPassConfig::addPreISel() {