aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/R600/AMDGPUTargetMachine.cpp
diff options
context:
space:
mode:
authorVincent Lejeune <vljn@ovi.com>2013-03-05 18:41:32 +0000
committerVincent Lejeune <vljn@ovi.com>2013-03-05 18:41:32 +0000
commit62f38ca141f87ff3ed9334fbe6a5e1c45d40ca86 (patch)
tree35d3d58f736ff178343b366036dfab5de893de9b /lib/Target/R600/AMDGPUTargetMachine.cpp
parent1c9bdf1e5e4b128206e1699c1bb82457118601e4 (diff)
downloadexternal_llvm-62f38ca141f87ff3ed9334fbe6a5e1c45d40ca86.zip
external_llvm-62f38ca141f87ff3ed9334fbe6a5e1c45d40ca86.tar.gz
external_llvm-62f38ca141f87ff3ed9334fbe6a5e1c45d40ca86.tar.bz2
R600: initial scheduler code
This is a skeleton for a pre-RA MachineInstr scheduler strategy. Currently it only tries to expose more parallelism for ALU instructions (this also makes the distribution of GPR channels more uniform and increases the chances of ALU instructions to be packed together in a single VLIW group). Also it tries to reduce clause switching by grouping instruction of the same kind (ALU/FETCH/CF) together. Vincent Lejeune: - Support for VLIW4 Slot assignement - Recomputation of ScheduleDAG to get more parallelism opportunities Tom Stellard: - Fix assertion failure when trying to determine an instruction's slot based on its destination register's class - Fix some compiler warnings Vincent Lejeune: [v2] - Remove recomputation of ScheduleDAG (will be provided in a later patch) - Improve estimation of an ALU clause size so that heuristic does not emit cf instructions at the wrong position. - Make schedule heuristic smarter using SUnit Depth - Take constant read limitations into account Vincent Lejeune: [v3] - Fix some uninitialized values in ConstPair - Add asserts to ensure an ALU slot is always populated git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176498 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/R600/AMDGPUTargetMachine.cpp')
-rw-r--r--lib/Target/R600/AMDGPUTargetMachine.cpp17
1 files changed, 16 insertions, 1 deletions
diff --git a/lib/Target/R600/AMDGPUTargetMachine.cpp b/lib/Target/R600/AMDGPUTargetMachine.cpp
index 70b34b0..eb58853 100644
--- a/lib/Target/R600/AMDGPUTargetMachine.cpp
+++ b/lib/Target/R600/AMDGPUTargetMachine.cpp
@@ -17,6 +17,7 @@
#include "AMDGPU.h"
#include "R600ISelLowering.h"
#include "R600InstrInfo.h"
+#include "R600MachineScheduler.h"
#include "SIISelLowering.h"
#include "SIInstrInfo.h"
#include "llvm/Analysis/Passes.h"
@@ -39,6 +40,14 @@ extern "C" void LLVMInitializeR600Target() {
RegisterTargetMachine<AMDGPUTargetMachine> X(TheAMDGPUTarget);
}
+static ScheduleDAGInstrs *createR600MachineScheduler(MachineSchedContext *C) {
+ return new ScheduleDAGMI(C, new R600SchedStrategy());
+}
+
+static MachineSchedRegistry
+SchedCustomRegistry("r600", "Run R600's custom scheduler",
+ createR600MachineScheduler);
+
AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
TargetOptions Options,
@@ -70,7 +79,13 @@ namespace {
class AMDGPUPassConfig : public TargetPassConfig {
public:
AMDGPUPassConfig(AMDGPUTargetMachine *TM, PassManagerBase &PM)
- : TargetPassConfig(TM, PM) {}
+ : TargetPassConfig(TM, PM) {
+ const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
+ if (ST.device()->getGeneration() <= AMDGPUDeviceInfo::HD6XXX) {
+ enablePass(&MachineSchedulerID);
+ MachineSchedRegistry::setDefault(createR600MachineScheduler);
+ }
+ }
AMDGPUTargetMachine &getAMDGPUTargetMachine() const {
return getTM<AMDGPUTargetMachine>();