[AArch64] Improve cost of vector division by constant

With custom lowering for vector MULLH{S,U}, it is now profitable to
vectorize a divide by constant loop for the custom types (v16i8, v8i16,
and v4i32).  The cost if based on TargetLowering::Build{S,U}DIV which
uses a multiply by constant plus adjustment to express a divide by
constant.

Both {u,s}mull{2} are expressed as Instruction::Mul and shifts by
Instruction::AShr.

llvm-svn: 331873

2 files changed, 67 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 316ea048436..098272dc2e2 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -520,6 +520,28 @@ int AArch64TTIImpl::getArithmeticInstrCost(
     }
     LLVM_FALLTHROUGH;
   case ISD::UDIV:
+    if (Opd2Info == TargetTransformInfo::OK_UniformConstantValue) {
+      auto VT = TLI->getValueType(DL, Ty);
+      if (TLI->isOperationLegalOrCustom(ISD::MULHU, VT)) {
+        // Vector signed division by constant are expanded to the
+        // sequence MULHS + ADD/SUB + SRA + SRL + ADD, and unsigned division
+        // to MULHS + SUB + SRL + ADD + SRL.
+        int MulCost = getArithmeticInstrCost(Instruction::Mul, Ty, Opd1Info,
+                                             Opd2Info,
+                                             TargetTransformInfo::OP_None,
+                                             TargetTransformInfo::OP_None);
+        int AddCost = getArithmeticInstrCost(Instruction::Add, Ty, Opd1Info,
+                                             Opd2Info,
+                                             TargetTransformInfo::OP_None,
+                                             TargetTransformInfo::OP_None);
+        int ShrCost = getArithmeticInstrCost(Instruction::AShr, Ty, Opd1Info,
+                                             Opd2Info,
+                                             TargetTransformInfo::OP_None,
+                                             TargetTransformInfo::OP_None);
+        return MulCost * 2 + AddCost * 2 + ShrCost * 2 + 1;
+      }
+    }
+
     Cost += BaseT::getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info,
                                           Opd1PropInfo, Opd2PropInfo);
     if (Ty->isVectorTy()) {
diff --git a/llvm/test/Analysis/CostModel/AArch64/div_cte.ll b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
new file mode 100644
index 00000000000..ab7fc23cdad
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
@@ -0,0 +1,45 @@
+; RUN: opt -cost-model -analyze -mtriple=aarch64-linux-gnu -mattr=+neon < %s | FileCheck %s
+
+; Verify the cost of integer division by constant.
+
+define <16 x i8> @sdiv8xi16(<16 x i8> %x) {
+; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv8xi16':
+; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+  %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+  ret <16 x i8> %div
+}
+
+define <8 x i16> @sdiv16xi8(<8 x i16> %x) {
+; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv16xi8':
+; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+  %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+  ret <8 x i16> %div
+}
+
+define <4 x i32> @sdiv32xi4(<4 x i32> %x) {
+; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv32xi4':
+; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+  %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+  ret <4 x i32> %div
+}
+
+define <16 x i8> @udiv8xi16(<16 x i8> %x) {
+; CHECK-LABEL: 'Cost Model Analysis' for function 'udiv8xi16':
+; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+  %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
+  ret <16 x i8> %div
+}
+
+define <8 x i16> @udiv16xi8(<8 x i16> %x) {
+; CHECK-LABEL: 'Cost Model Analysis' for function 'udiv16xi8':
+; CHECK: Found an estimated cost of 9 for instruction:   %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+  %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+  ret <8 x i16> %div
+}
+
+define <4 x i32> @udiv32xi4(<4 x i32> %x) {
+; CHECK-LABEL: Printing analysis 'Cost Model Analysis' for function 'udiv32xi4':
+; CHECK: Found an estimated cost of 9 for instruction:   %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+  %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+  ret <4 x i32> %div
+}