[AArch64] Multiply extended 32-bit ints with `[U|S]MADDL'

During instruction selection, the AArch64 backend can recognise the
following pattern and generate an [U|S]MADDL instruction, i.e. a
multiply of two 32-bit operands with a 64-bit result:

(mul (sext i32), (sext i32))
However, when one of the operands is constant, the sign extension
gets folded into the constant in SelectionDAG::getNode(). This means
that the instruction selection sees this:

(mul (sext i32), i64)
...which doesn't match the pattern. Sign-extension and 64-bit
multiply instructions are generated, which are slower than one 32-bit
multiply.

Add a pattern to match this and generate the correct instruction, for
both signed and unsigned multiplies.

Patch by Chris Diamand!

llvm-svn: 259800

1 files changed, 40 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index 4f052e81de2..53999b9a6fc 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -528,6 +528,12 @@ def i64imm_32bit : ImmLeaf<i64, [{
   return (Imm & 0xffffffffULL) == static_cast<uint64_t>(Imm);
 }]>;
 
+def s64imm_32bit : ImmLeaf<i64, [{
+  int64_t Imm64 = static_cast<int64_t>(Imm);
+  return Imm64 >= std::numeric_limits<int32_t>::min() &&
+         Imm64 <= std::numeric_limits<int32_t>::max();
+}]>;
+
 def trunc_imm : SDNodeXForm<imm, [{
   return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i32);
 }]>;
@@ -734,6 +740,40 @@ def : Pat<(i64 (ineg (mul (sext GPR32:$Rn), (sext GPR32:$Rm)))),
           (SMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
 def : Pat<(i64 (ineg (mul (zext GPR32:$Rn), (zext GPR32:$Rm)))),
           (UMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
+
+def : Pat<(i64 (mul (sext GPR32:$Rn), (s64imm_32bit:$C))),
+          (SMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+def : Pat<(i64 (mul (zext GPR32:$Rn), (i64imm_32bit:$C))),
+          (UMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+def : Pat<(i64 (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C))),
+          (SMADDLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
+                     (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+
+def : Pat<(i64 (ineg (mul (sext GPR32:$Rn), (s64imm_32bit:$C)))),
+          (SMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+def : Pat<(i64 (ineg (mul (zext GPR32:$Rn), (i64imm_32bit:$C)))),
+          (UMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+def : Pat<(i64 (ineg (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C)))),
+          (SMSUBLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
+                     (MOVi32imm (trunc_imm imm:$C)), XZR)>;
+
+def : Pat<(i64 (add (mul (sext GPR32:$Rn), (s64imm_32bit:$C)), GPR64:$Ra)),
+          (SMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
+def : Pat<(i64 (add (mul (zext GPR32:$Rn), (i64imm_32bit:$C)), GPR64:$Ra)),
+          (UMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
+def : Pat<(i64 (add (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C)),
+                    GPR64:$Ra)),
+          (SMADDLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
+                     (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
+
+def : Pat<(i64 (sub (mul (sext GPR32:$Rn), (s64imm_32bit:$C)), GPR64:$Ra)),
+          (SMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
+def : Pat<(i64 (sub (mul (zext GPR32:$Rn), (i64imm_32bit:$C)), GPR64:$Ra)),
+          (UMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
+def : Pat<(i64 (sub (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C)),
+                    GPR64:$Ra)),
+          (SMSUBLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
+                     (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
 } // AddedComplexity = 5
 
 def : MulAccumWAlias<"mul", MADDWrrr>;