[X86] Allow load folding into PUSH instructions

Adds pushes to the folding tables.
This also required a fix to the TD definition, since the memory forms of 
the push instructions did not have the right mayLoad/mayStore flags.

Differential Revision: http://reviews.llvm.org/D11340

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243010 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/X86/X86.td

@@ -181,6 +181,11 @@ def FeatureSlowDivide64 : SubtargetFeature<"idivq-to-divw",
 def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions",
                                      "PadShortFunctions", "true",
                                      "Pad short functions">;
+// TODO: This feature ought to be renamed.
+// What it really refers to are CPUs where instruction that cause MSROM
+// lookups are expensive, so alternative sequences should be preferred.
+// The best examples of this are the memory forms of CALL and PUSH
+// instructions, which should be avoided in favor of a MOV + register CALL/PUSH.
 def FeatureCallRegIndirect : SubtargetFeature<"call-reg-indirect",
                                      "CallRegIndirect", "true",
                                      "Call register indirect">;

lib/Target/X86/X86InstrInfo.cpp

@@ -332,6 +332,9 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     { X86::MUL8r,       X86::MUL8m,         TB_FOLDED_LOAD },
     { X86::PEXTRDrr,    X86::PEXTRDmr,      TB_FOLDED_STORE },
     { X86::PEXTRQrr,    X86::PEXTRQmr,      TB_FOLDED_STORE },
+    { X86::PUSH16r,     X86::PUSH16rmm,     TB_FOLDED_LOAD },
+    { X86::PUSH32r,     X86::PUSH32rmm,     TB_FOLDED_LOAD },
+    { X86::PUSH64r,     X86::PUSH64rmm,     TB_FOLDED_LOAD },
     { X86::SETAEr,      X86::SETAEm,        TB_FOLDED_STORE },
     { X86::SETAr,       X86::SETAm,         TB_FOLDED_STORE },
     { X86::SETBEr,      X86::SETBEm,        TB_FOLDED_STORE },
@@ -4878,10 +4881,14 @@ MachineInstr *X86InstrInfo::foldMemoryOperandImpl(
   bool isCallRegIndirect = Subtarget.callRegIndirect();
   bool isTwoAddrFold = false;
 
-  // For CPUs that favor the register form of a call,
+  // For CPUs that favor the register form of a call or push,
-  // do not fold loads into calls.
+  // do not fold loads into calls or pushes, unless optimizing for size
-  if (isCallRegIndirect &&
+  // aggressively.
-    (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r))
+  if (isCallRegIndirect && 
+      !MF.getFunction()->hasFnAttribute(Attribute::MinSize) &&
+      (MI->getOpcode() == X86::CALL32r || MI->getOpcode() == X86::CALL64r ||
+       MI->getOpcode() == X86::PUSH16r || MI->getOpcode() == X86::PUSH32r ||
+       MI->getOpcode() == X86::PUSH64r))
     return nullptr;
 
   unsigned NumOps = MI->getDesc().getNumOperands();

lib/Target/X86/X86InstrInfo.td

@@ -1022,12 +1022,8 @@ def PUSH32r  : I<0x50, AddRegFrm, (outs), (ins GR32:$reg), "push{l}\t$reg",[],
                  IIC_PUSH_REG>, OpSize32, Requires<[Not64BitMode]>;
 def PUSH16rmr: I<0xFF, MRM6r, (outs), (ins GR16:$reg), "push{w}\t$reg",[],
                  IIC_PUSH_REG>, OpSize16;
-def PUSH16rmm: I<0xFF, MRM6m, (outs), (ins i16mem:$src), "push{w}\t$src",[],
-                 IIC_PUSH_MEM>, OpSize16;
 def PUSH32rmr: I<0xFF, MRM6r, (outs), (ins GR32:$reg), "push{l}\t$reg",[],
                  IIC_PUSH_REG>, OpSize32, Requires<[Not64BitMode]>;
-def PUSH32rmm: I<0xFF, MRM6m, (outs), (ins i32mem:$src), "push{l}\t$src",[],
-                 IIC_PUSH_MEM>, OpSize32, Requires<[Not64BitMode]>;
 
 def PUSH16i8 : Ii8<0x6a, RawFrm, (outs), (ins i16i8imm:$imm),
                    "push{w}\t$imm", [], IIC_PUSH_IMM>, OpSize16;
@@ -1041,6 +1037,14 @@ def PUSHi32  : Ii32<0x68, RawFrm, (outs), (ins i32imm:$imm),
                    "push{l}\t$imm", [], IIC_PUSH_IMM>, OpSize32,
                    Requires<[Not64BitMode]>;
 } // mayStore, SchedRW
+
+let mayLoad = 1, mayStore = 1, SchedRW = [WriteRMW] in {
+def PUSH16rmm: I<0xFF, MRM6m, (outs), (ins i16mem:$src), "push{w}\t$src",[],
+                 IIC_PUSH_MEM>, OpSize16;
+def PUSH32rmm: I<0xFF, MRM6m, (outs), (ins i32mem:$src), "push{l}\t$src",[],
+                 IIC_PUSH_MEM>, OpSize32, Requires<[Not64BitMode]>;
+} // mayLoad, mayStore, SchedRW
+
 }
 
 let Defs = [ESP, EFLAGS], Uses = [ESP], mayLoad = 1, hasSideEffects=0,
@@ -1073,9 +1077,11 @@ def PUSH64r  : I<0x50, AddRegFrm, (outs), (ins GR64:$reg), "push{q}\t$reg", [],
                  IIC_PUSH_REG>, OpSize32, Requires<[In64BitMode]>;
 def PUSH64rmr: I<0xFF, MRM6r, (outs), (ins GR64:$reg), "push{q}\t$reg", [],
                  IIC_PUSH_REG>, OpSize32, Requires<[In64BitMode]>;
+} // mayStore, SchedRW
+let mayLoad = 1, mayStore = 1, SchedRW = [WriteRMW] in {
 def PUSH64rmm: I<0xFF, MRM6m, (outs), (ins i64mem:$src), "push{q}\t$src", [],
                  IIC_PUSH_MEM>, OpSize32, Requires<[In64BitMode]>;
-} // mayStore, SchedRW
+} // mayLoad, mayStore, SchedRW
 }
 
 let Defs = [RSP], Uses = [RSP], hasSideEffects = 0, mayStore = 1,

test/CodeGen/X86/fold-push.ll

@@ -0,0 +1,40 @@
+; RUN: llc < %s -mtriple=i686-windows | FileCheck %s -check-prefix=CHECK -check-prefix=NORMAL
+; RUN: llc < %s -mtriple=i686-windows -mattr=call-reg-indirect | FileCheck %s -check-prefix=CHECK -check-prefix=SLM
+
+declare void @foo(i32 %r)
+
+define void @test(i32 %a, i32 %b) optsize {
+; CHECK-LABEL: test:
+; CHECK: movl [[EAX:%e..]], (%esp)
+; CHECK-NEXT: pushl [[EAX]]
+; CHECK-NEXT: calll
+; CHECK-NEXT: addl $4, %esp
+; CHECK: nop
+; NORMAL: pushl (%esp)
+; SLM: movl (%esp), [[RELOAD:%e..]]
+; SLM-NEXT: pushl [[RELOAD]]
+; CHECK: calll
+; CHECK-NEXT: addl $4, %esp
+  %c = add i32 %a, %b
+  call void @foo(i32 %c)
+  call void asm sideeffect "nop", "~{ax},~{bx},~{cx},~{dx},~{bp},~{si},~{di}"()
+  call void @foo(i32 %c)
+  ret void
+}
+
+define void @test_min(i32 %a, i32 %b) minsize {
+; CHECK-LABEL: test_min:
+; CHECK: movl [[EAX:%e..]], (%esp)
+; CHECK-NEXT: pushl [[EAX]]
+; CHECK-NEXT: calll
+; CHECK-NEXT: addl $4, %esp
+; CHECK: nop
+; CHECK: pushl (%esp)
+; CHECK: calll
+; CHECK-NEXT: addl $4, %esp
+  %c = add i32 %a, %b
+  call void @foo(i32 %c)
+  call void asm sideeffect "nop", "~{ax},~{bx},~{cx},~{dx},~{bp},~{si},~{di}"()
+  call void @foo(i32 %c)
+  ret void
+}