[X86] Enable BT to be used in place of TEST for single bit checks under optsize

[craig.topper]

Summary

We already do this for 64-bit when it won't fit into a 64-bit AND/TEST's immediate field. This adds an additional qualifier to do it for any single bit constant under optsize

[craig.topper]

Don't do this immediates that fit in a byte, It won't save anything

[RKSimon]

LGTM - don't suppose we have any load fold tests for BT do we?

[craig.topper]

Doesn't look like we do. I'll look into that.

lib/Target/X86/X86ISelLowering.cpp

static SDValue LowerAndToBT(SDValue And, ISD::CondCode CC,
   } else if (Op1.getOpcode() == ISD::Constant) {
     ConstantSDNode *AndRHS = cast<ConstantSDNode>(Op1);
     uint64_t AndRHSVal = AndRHS->getZExtValue();
     SDValue AndLHS = Op0;
 
     if (AndRHSVal == 1 && AndLHS.getOpcode() == ISD::SRL) {
       LHS = AndLHS.getOperand(0);
       RHS = AndLHS.getOperand(1);
-    }
-
-    // Use BT if the immediate can't be encoded in a TEST instruction.
-    if (!isUInt<32>(AndRHSVal) && isPowerOf2_64(AndRHSVal)) {
+    } else {
+      // Use BT if the immediate can't be encoded in a TEST instruction or we
+      // are optimizing for size and the immedaite won't fit in a byte.
+      bool OptForSize = DAG.getMachineFunction().getFunction().optForSize();
+      if ((!isUInt<32>(AndRHSVal) || (OptForSize && !isUInt<8>(AndRHSVal))) &&
+          isPowerOf2_64(AndRHSVal)) {
         LHS = AndLHS;
         RHS = DAG.getConstant(Log2_64_Ceil(AndRHSVal), dl, LHS.getValueType());
       }
     }
+  }
 
   if (LHS.getNode())
     return getBitTestCondition(LHS, RHS, CC, dl, DAG);
 
   return SDValue();
 }
 
 /// Turns an ISD::CondCode into a value suitable for SSE floating-point mask

test/CodeGen/X86/test-vs-bittest.ll

no:
   ret void
 }
 
 define void @test64_optsize_2(i64 inreg %x) optsize {
 ; CHECK-LABEL: test64_optsize_2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    testl $2048, %edi # imm = 0x800
-; CHECK-NEXT:    je .LBB3_2
+; CHECK-NEXT:    btl $11, %edi
+; CHECK-NEXT:    jae .LBB3_2
 ; CHECK-NEXT:  # %bb.1: # %yes
 ; CHECK-NEXT:    callq bar
 ; CHECK-NEXT:  .LBB3_2: # %no
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
   %t = and i64 %x, 2048
   %s = icmp eq i64 %t, 0
   br i1 %s, label %no, label %yes
no:
   ret void
 }
 
 define void @test32_optsize_2(i32 inreg %x) optsize {
 ; CHECK-LABEL: test32_optsize_2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    testl $2048, %edi # imm = 0x800
-; CHECK-NEXT:    je .LBB11_2
+; CHECK-NEXT:    btl $11, %edi
+; CHECK-NEXT:    jae .LBB11_2
 ; CHECK-NEXT:  # %bb.1: # %yes
 ; CHECK-NEXT:    callq bar
 ; CHECK-NEXT:  .LBB11_2: # %no
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
   %t = and i32 %x, 2048
   %s = icmp eq i32 %t, 0
   br i1 %s, label %no, label %yes
no:
   ret void
 }
 
 define void @test16_optsize_2(i16 inreg %x) optsize {
 ; CHECK-LABEL: test16_optsize_2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    testl $2048, %edi # imm = 0x800
-; CHECK-NEXT:    je .LBB15_2
+; CHECK-NEXT:    btl $11, %edi
+; CHECK-NEXT:    jae .LBB15_2
 ; CHECK-NEXT:  # %bb.1: # %yes
 ; CHECK-NEXT:    callq bar
 ; CHECK-NEXT:  .LBB15_2: # %no
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
   %t = and i16 %x, 2048
   %s = icmp eq i16 %t, 0
   br i1 %s, label %no, label %yes