PTX: Unify handling of loads/stores

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140533 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 38 insertions, 206 deletions

diff --git a/lib/Target/PTX/PTXAsmPrinter.cpp b/lib/Target/PTX/PTXAsmPrinter.cpp
index beabd77..d1b6653 100644
--- a/lib/Target/PTX/PTXAsmPrinter.cpp
+++ b/lib/Target/PTX/PTXAsmPrinter.cpp
@@ -68,6 +68,8 @@ public:
                        const char *Modifier = 0);
   void printParamOperand(const MachineInstr *MI, int opNum, raw_ostream &OS,
                          const char *Modifier = 0);
+  void printLocalOperand(const MachineInstr *MI, int opNum, raw_ostream &OS,
+                         const char *Modifier = 0);
   void printReturnOperand(const MachineInstr *MI, int opNum, raw_ostream &OS,
                           const char *Modifier = 0);
   void printPredicateOperand(const MachineInstr *MI, raw_ostream &O);
@@ -297,7 +299,7 @@ void PTXAsmPrinter::EmitFunctionBodyStart() {
     if (FrameInfo->getObjectSize(i) > 0) {
       std::string def = "\t.local .b";
       def += utostr(FrameInfo->getObjectSize(i)*8); // Convert to bits
-      def += " __local_";
+      def += " __local";
       def += utostr(i);
       def += ";";
       OutStreamer.EmitRawText(Twine(def));
@@ -458,6 +460,11 @@ void PTXAsmPrinter::printReturnOperand(const MachineInstr *MI, int opNum,
   OS << "__ret";
 }
 
+void PTXAsmPrinter::printLocalOperand(const MachineInstr *MI, int opNum,
+                                      raw_ostream &OS, const char *Modifier) {
+  OS << "__local" << MI->getOperand(opNum).getImm();
+}
+
 void PTXAsmPrinter::EmitVariableDeclaration(const GlobalVariable *gv) {
   // Check to see if this is a special global used by LLVM, if so, emit it.
   if (EmitSpecialLLVMGlobal(gv))
diff --git a/lib/Target/PTX/PTXInstrInfo.td b/lib/Target/PTX/PTXInstrInfo.td
index 50499a5..6b18f13 100644
--- a/lib/Target/PTX/PTXInstrInfo.td
+++ b/lib/Target/PTX/PTXInstrInfo.td
@@ -147,6 +147,14 @@ def MEMri64 : Operand<i64> {
   let PrintMethod = "printMemOperand";
   let MIOperandInfo = (ops RegI64, i64imm);
 }
+def LOCALri32 : Operand<i32> {
+  let PrintMethod = "printLocalOperand";
+  let MIOperandInfo = (ops RegI32, i32imm);
+}
+def LOCALri64 : Operand<i64> {
+  let PrintMethod = "printLocalOperand";
+  let MIOperandInfo = (ops RegI64, i64imm);
+}
 def MEMii32 : Operand<i32> {
   let PrintMethod = "printMemOperand";
   let MIOperandInfo = (ops i32imm, i32imm);
@@ -602,6 +610,21 @@ multiclass PTX_LD<string opstr, string typestr,
                      Requires<[Use64BitAddresses]>;
 }
 
+multiclass PTX_LOCAL_LD_ST<string typestr, RegisterClass RC> {
+  def LDri32 : InstPTX<(outs RC:$d), (ins LOCALri32:$a),
+                      !strconcat("ld.local", !strconcat(typestr, "\t$d, [$a]")),
+                       [(set RC:$d, (load_local ADDRlocal32:$a))]>;
+  def LDri64 : InstPTX<(outs RC:$d), (ins LOCALri64:$a),
+                      !strconcat("ld.local", !strconcat(typestr, "\t$d, [$a]")),
+                       [(set RC:$d, (load_local ADDRlocal64:$a))]>;
+  def STri32 : InstPTX<(outs), (ins RC:$d, LOCALri32:$a),
+                      !strconcat("st.local", !strconcat(typestr, "\t[$a], $d")),
+                       [(store_local RC:$d, ADDRlocal32:$a)]>;
+  def STri64 : InstPTX<(outs), (ins RC:$d, LOCALri64:$a),
+                      !strconcat("st.local", !strconcat(typestr, "\t[$a], $d")),
+                       [(store_local RC:$d, ADDRlocal64:$a)]>;
+}
+
 multiclass PTX_LD_ALL<string opstr, PatFrag pat_load> {
   defm u16 : PTX_LD<opstr, ".u16", RegI16, pat_load>;
   defm u32 : PTX_LD<opstr, ".u32", RegI32, pat_load>;
@@ -960,86 +983,18 @@ let hasSideEffects = 1 in {
                    [(pat_store RC:$d, ADDRri64:$a)]>,
                    Requires<[Use64BitAddresses]>;
                      */
-let hasSideEffects = 1 in {
-  def LDLOCALpiPred : InstPTX<(outs RegPred:$d), (ins MEMri32:$a),
-                              "ld.local.pred\t$d, [__local_$a]",
-                              [(set RegPred:$d, (load_local ADDRlocal32:$a))]>;
-  def LDLOCALpiU16  : InstPTX<(outs RegI16:$d), (ins MEMri32:$a),
-                              "ld.local.u16\t$d, [__local_$a]",
-                              [(set RegI16:$d, (load_local ADDRlocal32:$a))]>;
-  def LDLOCALpiU32  : InstPTX<(outs RegI32:$d), (ins MEMri32:$a),
-                              "ld.local.u32\t$d, [__local_$a]",
-                              [(set RegI32:$d, (load_local ADDRlocal32:$a))]>;
-  def LDLOCALpiU64  : InstPTX<(outs RegI64:$d), (ins MEMri32:$a),
-                              "ld.local.u64\t$d, [__local_$a]",
-                              [(set RegI64:$d, (load_local ADDRlocal32:$a))]>;
-  def LDLOCALpiF32 : InstPTX<(outs RegF32:$d), (ins MEMri32:$a),
-                              "ld.local.f32\t$d, [__local_$a]",
-                              [(set RegF32:$d, (load_local ADDRlocal32:$a))]>;
-  def LDLOCALpiF64 : InstPTX<(outs RegF64:$d), (ins MEMri32:$a),
-                              "ld.local.f64\t$d, [__local_$a]",
-                              [(set RegF64:$d, (load_local ADDRlocal32:$a))]>;
-
-  def STLOCALpiPred : InstPTX<(outs), (ins RegPred:$d, MEMri32:$a),
-                              "st.local.pred\t[__local_$a], $d",
-                              [(store_local RegPred:$d, ADDRlocal32:$a)]>;
-  def STLOCALpiU16 : InstPTX<(outs), (ins RegI16:$d, MEMri32:$a),
-                              "st.local.u16\t[__local_$a], $d",
-                              [(store_local RegI16:$d, ADDRlocal32:$a)]>;
-  def STLOCALpiU32 : InstPTX<(outs), (ins RegI32:$d, MEMri32:$a),
-                              "st.local.u32\t[__local_$a], $d",
-                              [(store_local RegI32:$d, ADDRlocal32:$a)]>;
-  def STLOCALpiU64 : InstPTX<(outs), (ins RegI64:$d, MEMri32:$a),
-                              "st.local.u64\t[__local_$a], $d",
-                              [(store_local RegI64:$d, ADDRlocal32:$a)]>;
-  def STLOCALpiF32 : InstPTX<(outs), (ins RegF32:$d, MEMri32:$a),
-                              "st.local.f32\t[__local_$a], $d",
-                              [(store_local RegF32:$d, ADDRlocal32:$a)]>;
-  def STLOCALpiF64 : InstPTX<(outs), (ins RegF64:$d, MEMri32:$a),
-                              "st.local.f64\t[__local_$a], $d",
-                              [(store_local RegF64:$d, ADDRlocal32:$a)]>;
-
-  /*def LDLOCALpiU16  : InstPTX<(outs RegI16:$d), (ins MEMpi:$a),
-                         "ld.param.u16\t$d, [$a]",
-                         [(set RegI16:$d, (PTXloadparam timm:$a))]>;
-  def LDLOCALpiU32  : InstPTX<(outs RegI32:$d), (ins MEMpi:$a),
-                         "ld.param.u32\t$d, [$a]",
-                         [(set RegI32:$d, (PTXloadparam timm:$a))]>;
-  def LDLOCALpiU64  : InstPTX<(outs RegI64:$d), (ins MEMpi:$a),
-                         "ld.param.u64\t$d, [$a]",
-                         [(set RegI64:$d, (PTXloadparam timm:$a))]>;
-  def LDLOCALpiF32  : InstPTX<(outs RegF32:$d), (ins MEMpi:$a),
-                         "ld.param.f32\t$d, [$a]",
-                         [(set RegF32:$d, (PTXloadparam timm:$a))]>;
-  def LDLOCALpiF64  : InstPTX<(outs RegF64:$d), (ins MEMpi:$a),
-                         "ld.param.f64\t$d, [$a]",
-                         [(set RegF64:$d, (PTXloadparam timm:$a))]>;
-
-  def STLOCALpiPred : InstPTX<(outs), (ins MEMpi:$d, RegPred:$a),
-                         "st.param.pred\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegPred:$a)]>;
-  def STLOCALpiU16  : InstPTX<(outs), (ins MEMpi:$d, RegI16:$a),
-                         "st.param.u16\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegI16:$a)]>;
-  def STLOCALpiU32  : InstPTX<(outs), (ins MEMpi:$d, RegI32:$a),
-                         "st.param.u32\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegI32:$a)]>;
-  def STLOCALpiU64  : InstPTX<(outs), (ins MEMpi:$d, RegI64:$a),
-                         "st.param.u64\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegI64:$a)]>;
-  def STLOCALpiF32  : InstPTX<(outs), (ins MEMpi:$d, RegF32:$a),
-                         "st.param.f32\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegF32:$a)]>;
-  def STLOCALpiF64  : InstPTX<(outs), (ins MEMpi:$d, RegF64:$a),
-                         "st.param.f64\t[$d], $a",
-                         [(PTXstoreparam timm:$d, RegF64:$a)]>;*/
-}
 
 // Stores
 defm STg : PTX_ST_ALL<"st.global", store_global>;
 //defm STl : PTX_ST_ALL<"st.local",  store_local>;
 defm STs : PTX_ST_ALL<"st.shared", store_shared>;
 
+defm LOCALPRED : PTX_LOCAL_LD_ST<".pred", RegPred>;
+defm LOCALU16  : PTX_LOCAL_LD_ST<".u16", RegI16>;
+defm LOCALU32  : PTX_LOCAL_LD_ST<".u32", RegI32>;
+defm LOCALU64  : PTX_LOCAL_LD_ST<".u64", RegI64>;
+defm LOCALF32  : PTX_LOCAL_LD_ST<".f32", RegF32>;
+defm LOCALF64  : PTX_LOCAL_LD_ST<".f64", RegF64>;
 
 
 // defm STp : PTX_ST_ALL<"st.param",  store_parameter>;
diff --git a/lib/Target/PTX/PTXRegisterInfo.cpp b/lib/Target/PTX/PTXRegisterInfo.cpp
index 6f2e876..acc74f3 100644
--- a/lib/Target/PTX/PTXRegisterInfo.cpp
+++ b/lib/Target/PTX/PTXRegisterInfo.cpp
@@ -65,5 +65,5 @@ void PTXRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator II,
 
   // This frame index is post stack slot re-use assignments
   //MI.getOperand(Index).ChangeToRegister(Reg, false);
-  MI.getOperand(Index).ChangeToImmediate(0);
+  MI.getOperand(Index).ChangeToImmediate(FrameIndex);
 }
diff --git a/test/CodeGen/PTX/ld.ll b/test/CodeGen/PTX/ld.ll
index 95941dc..81fd33a 100644
--- a/test/CodeGen/PTX/ld.ll
+++ b/test/CodeGen/PTX/ld.ll
@@ -6,9 +6,6 @@
 ;CHECK: .extern .const .b8 array_constant_i16[20];
 @array_constant_i16 = external addrspace(1) constant [10 x i16]
 
-;CHECK: .extern .local .b8 array_local_i16[20];
-@array_local_i16 = external addrspace(2) global [10 x i16]
-
 ;CHECK: .extern .shared .b8 array_shared_i16[20];
 @array_shared_i16 = external addrspace(4) global [10 x i16]
 
@@ -18,9 +15,6 @@
 ;CHECK: .extern .const .b8 array_constant_i32[40];
 @array_constant_i32 = external addrspace(1) constant [10 x i32]
 
-;CHECK: .extern .local .b8 array_local_i32[40];
-@array_local_i32 = external addrspace(2) global [10 x i32]
-
 ;CHECK: .extern .shared .b8 array_shared_i32[40];
 @array_shared_i32 = external addrspace(4) global [10 x i32]
 
@@ -30,9 +24,6 @@
 ;CHECK: .extern .const .b8 array_constant_i64[80];
 @array_constant_i64 = external addrspace(1) constant [10 x i64]
 
-;CHECK: .extern .local .b8 array_local_i64[80];
-@array_local_i64 = external addrspace(2) global [10 x i64]
-
 ;CHECK: .extern .shared .b8 array_shared_i64[80];
 @array_shared_i64 = external addrspace(4) global [10 x i64]
 
@@ -42,9 +33,6 @@
 ;CHECK: .extern .const .b8 array_constant_float[40];
 @array_constant_float = external addrspace(1) constant [10 x float]
 
-;CHECK: .extern .local .b8 array_local_float[40];
-@array_local_float = external addrspace(2) global [10 x float]
-
 ;CHECK: .extern .shared .b8 array_shared_float[40];
 @array_shared_float = external addrspace(4) global [10 x float]
 
@@ -54,9 +42,6 @@
 ;CHECK: .extern .const .b8 array_constant_double[80];
 @array_constant_double = external addrspace(1) constant [10 x double]
 
-;CHECK: .extern .local .b8 array_local_double[80];
-@array_local_double = external addrspace(2) global [10 x double]
-
 ;CHECK: .extern .shared .b8 array_shared_double[80];
 @array_shared_double = external addrspace(4) global [10 x double]
 
@@ -296,56 +281,6 @@ entry:
   ret double %x
 }
 
-define ptx_device i16 @t4_local_u16() {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i16;
-;CHECK: ld.local.u16 %ret{{[0-9]+}}, [%r[[R0]]];
-;CHECK: ret;
-  %i = getelementptr [10 x i16] addrspace(2)* @array_local_i16, i32 0, i32 0
-  %x = load i16 addrspace(2)* %i
-  ret i16 %x
-}
-
-define ptx_device i32 @t4_local_u32() {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i32;
-;CHECK: ld.local.u32 %ret{{[0-9]+}}, [%r[[R0]]];
-;CHECK: ret;
-  %i = getelementptr [10 x i32] addrspace(2)* @array_local_i32, i32 0, i32 0
-  %x = load i32 addrspace(2)* %i
-  ret i32 %x
-}
-
-define ptx_device i64 @t4_local_u64() {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i64;
-;CHECK: ld.local.u64 %ret{{[0-9]+}}, [%r[[R0]]];
-;CHECK: ret;
-  %i = getelementptr [10 x i64] addrspace(2)* @array_local_i64, i32 0, i32 0
-  %x = load i64 addrspace(2)* %i
-  ret i64 %x
-}
-
-define ptx_device float @t4_local_f32() {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_float;
-;CHECK: ld.local.f32 %ret{{[0-9]+}}, [%r[[R0]]];
-;CHECK: ret;
-  %i = getelementptr [10 x float] addrspace(2)* @array_local_float, i32 0, i32 0
-  %x = load float addrspace(2)* %i
-  ret float %x
-}
-
-define ptx_device double @t4_local_f64() {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_double;
-;CHECK: ld.local.f64 %ret{{[0-9]+}}, [%r[[R0]]];
-;CHECK: ret;
-  %i = getelementptr [10 x double] addrspace(2)* @array_local_double, i32 0, i32 0
-  %x = load double addrspace(2)* %i
-  ret double %x
-}
-
 define ptx_device i16 @t4_shared_u16() {
 entry:
 ;CHECK: mov.u32 %r[[R0:[0-9]+]], array_shared_i16;
diff --git a/test/CodeGen/PTX/st.ll b/test/CodeGen/PTX/st.ll
index beff0cf..63ef58c 100644
--- a/test/CodeGen/PTX/st.ll
+++ b/test/CodeGen/PTX/st.ll
@@ -6,9 +6,6 @@
 ;CHECK: .extern .const .b8 array_constant_i16[20];
 @array_constant_i16 = external addrspace(1) constant [10 x i16]
 
-;CHECK: .extern .local .b8 array_local_i16[20];
-@array_local_i16 = external addrspace(2) global [10 x i16]
-
 ;CHECK: .extern .shared .b8 array_shared_i16[20];
 @array_shared_i16 = external addrspace(4) global [10 x i16]
 
@@ -18,9 +15,6 @@
 ;CHECK: .extern .const .b8 array_constant_i32[40];
 @array_constant_i32 = external addrspace(1) constant [10 x i32]
 
-;CHECK: .extern .local .b8 array_local_i32[40];
-@array_local_i32 = external addrspace(2) global [10 x i32]
-
 ;CHECK: .extern .shared .b8 array_shared_i32[40];
 @array_shared_i32 = external addrspace(4) global [10 x i32]
 
@@ -30,9 +24,6 @@
 ;CHECK: .extern .const .b8 array_constant_i64[80];
 @array_constant_i64 = external addrspace(1) constant [10 x i64]
 
-;CHECK: .extern .local .b8 array_local_i64[80];
-@array_local_i64 = external addrspace(2) global [10 x i64]
-
 ;CHECK: .extern .shared .b8 array_shared_i64[80];
 @array_shared_i64 = external addrspace(4) global [10 x i64]
 
@@ -42,9 +33,6 @@
 ;CHECK: .extern .const .b8 array_constant_float[40];
 @array_constant_float = external addrspace(1) constant [10 x float]
 
-;CHECK: .extern .local .b8 array_local_float[40];
-@array_local_float = external addrspace(2) global [10 x float]
-
 ;CHECK: .extern .shared .b8 array_shared_float[40];
 @array_shared_float = external addrspace(4) global [10 x float]
 
@@ -54,9 +42,6 @@
 ;CHECK: .extern .const .b8 array_constant_double[80];
 @array_constant_double = external addrspace(1) constant [10 x double]
 
-;CHECK: .extern .local .b8 array_local_double[80];
-@array_local_double = external addrspace(2) global [10 x double]
-
 ;CHECK: .extern .shared .b8 array_shared_double[80];
 @array_shared_double = external addrspace(4) global [10 x double]
 
@@ -251,56 +236,6 @@ entry:
   ret void
 }
 
-define ptx_device void @t4_local_u16(i16 %x) {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i16;
-;CHECK: st.local.u16 [%r[[R0]]], %rh{{[0-9]+}};
-;CHECK: ret;
-  %i = getelementptr [10 x i16] addrspace(2)* @array_local_i16, i32 0, i32 0
-  store i16 %x, i16 addrspace(2)* %i
-  ret void
-}
-
-define ptx_device void @t4_local_u32(i32 %x) {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i32;
-;CHECK: st.local.u32 [%r[[R0]]], %r{{[0-9]+}};
-;CHECK: ret;
-  %i = getelementptr [10 x i32] addrspace(2)* @array_local_i32, i32 0, i32 0
-  store i32 %x, i32 addrspace(2)* %i
-  ret void
-}
-
-define ptx_device void @t4_local_u64(i64 %x) {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_i64;
-;CHECK: st.local.u64 [%r[[R0]]], %rd{{[0-9]+}};
-;CHECK: ret;
-  %i = getelementptr [10 x i64] addrspace(2)* @array_local_i64, i32 0, i32 0
-  store i64 %x, i64 addrspace(2)* %i
-  ret void
-}
-
-define ptx_device void @t4_local_f32(float %x) {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_float;
-;CHECK: st.local.f32 [%r[[R0]]], %f{{[0-9]+}};
-;CHECK: ret;
-  %i = getelementptr [10 x float] addrspace(2)* @array_local_float, i32 0, i32 0
-  store float %x, float addrspace(2)* %i
-  ret void
-}
-
-define ptx_device void @t4_local_f64(double %x) {
-entry:
-;CHECK: mov.u32 %r[[R0:[0-9]+]], array_local_double;
-;CHECK: st.local.f64 [%r[[R0]]], %fd{{[0-9]+}};
-;CHECK: ret;
-  %i = getelementptr [10 x double] addrspace(2)* @array_local_double, i32 0, i32 0
-  store double %x, double addrspace(2)* %i
-  ret void
-}
-
 define ptx_device void @t4_shared_u16(i16 %x) {
 entry:
 ;CHECK: mov.u32 %r[[R0:[0-9]+]], array_shared_i16;