From: Tom Stellard <thomas.stellard@amd.com>
Date: Tue, 28 Apr 2015 21:22:56 +0000 (+0000)
Subject: Merging r231658:
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=9a6615d18d3ade984a65f6f9a157dec8987b7798;p=llvm

Merging r231658:

------------------------------------------------------------------------
r231658 | marek.olsak | 2015-03-09 11:48:00 -0400 (Mon, 09 Mar 2015) | 2 lines

R600/SI: Fix getNumSGPRsAllowed for VI

------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@236037 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/R600/SIRegisterInfo.cpp b/lib/Target/R600/SIRegisterInfo.cpp
index 9224e1435dd..160ff655bad 100644
--- a/lib/Target/R600/SIRegisterInfo.cpp
+++ b/lib/Target/R600/SIRegisterInfo.cpp
@@ -14,7 +14,6 @@
 
 
 #include "SIRegisterInfo.h"
-#include "AMDGPUSubtarget.h"
 #include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
@@ -53,7 +52,8 @@ BitVector SIRegisterInfo::getReservedRegs(const MachineFunction &MF) const {
 unsigned SIRegisterInfo::getRegPressureSetLimit(unsigned Idx) const {
 
   // FIXME: We should adjust the max number of waves based on LDS size.
-  unsigned SGPRLimit = getNumSGPRsAllowed(ST.getMaxWavesPerCU());
+  unsigned SGPRLimit = getNumSGPRsAllowed(ST.getGeneration(),
+                                          ST.getMaxWavesPerCU());
   unsigned VGPRLimit = getNumVGPRsAllowed(ST.getMaxWavesPerCU());
 
   for (regclass_iterator I = regclass_begin(), E = regclass_end();
@@ -494,14 +494,24 @@ unsigned SIRegisterInfo::getNumVGPRsAllowed(unsigned WaveCount) const {
   }
 }
 
-unsigned SIRegisterInfo::getNumSGPRsAllowed(unsigned WaveCount) const {
-  switch(WaveCount) {
-    case 10: return 48;
-    case 9:  return 56;
-    case 8:  return 64;
-    case 7:  return 72;
-    case 6:  return 80;
-    case 5:  return 96;
-    default: return 103;
+unsigned SIRegisterInfo::getNumSGPRsAllowed(AMDGPUSubtarget::Generation gen,
+                                            unsigned WaveCount) const {
+  if (gen >= AMDGPUSubtarget::VOLCANIC_ISLANDS) {
+    switch (WaveCount) {
+      case 10: return 80;
+      case 9:  return 80;
+      case 8:  return 96;
+      default: return 102;
+    }
+  } else {
+    switch(WaveCount) {
+      case 10: return 48;
+      case 9:  return 56;
+      case 8:  return 64;
+      case 7:  return 72;
+      case 6:  return 80;
+      case 5:  return 96;
+      default: return 103;
+    }
   }
 }
diff --git a/lib/Target/R600/SIRegisterInfo.h b/lib/Target/R600/SIRegisterInfo.h
index d908ffd12d2..1dfe53093eb 100644
--- a/lib/Target/R600/SIRegisterInfo.h
+++ b/lib/Target/R600/SIRegisterInfo.h
@@ -17,6 +17,7 @@
 #define LLVM_LIB_TARGET_R600_SIREGISTERINFO_H
 
 #include "AMDGPURegisterInfo.h"
+#include "AMDGPUSubtarget.h"
 #include "llvm/Support/Debug.h"
 
 namespace llvm {
@@ -111,7 +112,8 @@ struct SIRegisterInfo : public AMDGPURegisterInfo {
 
   /// \brief Give the maximum number of SGPRs that can be used by \p WaveCount
   ///        concurrent waves.
-  unsigned getNumSGPRsAllowed(unsigned WaveCount) const;
+  unsigned getNumSGPRsAllowed(AMDGPUSubtarget::Generation gen,
+                              unsigned WaveCount) const;
 
   unsigned findUnusedRegister(const MachineRegisterInfo &MRI,
                               const TargetRegisterClass *RC) const;