[CodeGen][SVE] Add patterns for whole vector predicate select

Added patterns to implement `select i1 %p, <vty> %a, <vty> %b`

Reviewed By: efriedma

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D79356

2 files changed, 144 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 3270ba27..899b18f 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -876,6 +876,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
     for (MVT VT : MVT::integer_scalable_vector_valuetypes()) {
       if (isTypeLegal(VT)) {
         setOperationAction(ISD::SPLAT_VECTOR, VT, Custom);
+        setOperationAction(ISD::SELECT, VT, Custom);
         setOperationAction(ISD::SDIV, VT, Custom);
         setOperationAction(ISD::UDIV, VT, Custom);
         setOperationAction(ISD::SMIN, VT, Custom);
@@ -893,6 +894,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
     for (MVT VT : MVT::fp_scalable_vector_valuetypes()) {
       if (isTypeLegal(VT)) {
         setOperationAction(ISD::SPLAT_VECTOR, VT, Custom);
+        setOperationAction(ISD::SELECT, VT, Custom);
       }
     }
   }
@@ -5710,6 +5712,14 @@ SDValue AArch64TargetLowering::LowerSELECT(SDValue Op,
   SDValue FVal = Op->getOperand(2);
   SDLoc DL(Op);
 
+  EVT Ty = Op.getValueType();
+  if (Ty.isScalableVector()) {
+    SDValue TruncCC = DAG.getNode(ISD::TRUNCATE, DL, MVT::i1, CCVal);
+    MVT PredVT = MVT::getVectorVT(MVT::i1, Ty.getVectorElementCount());
+    SDValue SplatPred = DAG.getNode(ISD::SPLAT_VECTOR, DL, PredVT, TruncCC);
+    return DAG.getNode(ISD::VSELECT, DL, Ty, SplatPred, TVal, FVal);
+  }
+
   // Optimize {s|u}{add|sub|mul}.with.overflow feeding into a select
   // instruction.
   if (ISD::isOverflowIntrOpRes(CCVal)) {
diff --git a/llvm/test/CodeGen/AArch64/select-sve.ll b/llvm/test/CodeGen/AArch64/select-sve.ll
new file mode 100644
index 0000000..b0959d2
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/select-sve.ll
@@ -0,0 +1,134 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -verify-machineinstrs < %s | FileCheck %s
+
+define <vscale x  16 x i8> @select_nxv16i8(i1 %cond, <vscale x  16 x i8> %a, <vscale x  16 x i8> %b) {
+; CHECK-LABEL: select_nxv16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.b, xzr, x8
+; CHECK-NEXT:    sel z0.b, p0, z0.b, z1.b
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  16 x i8> %a, <vscale x  16 x i8> %b
+  ret <vscale x  16 x i8> %res
+}
+
+define <vscale x  8 x i16> @select_nxv8i16(i1 %cond, <vscale x  8 x i16> %a, <vscale x  8 x i16> %b) {
+; CHECK-LABEL: select_nxv8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.h, xzr, x8
+; CHECK-NEXT:    sel z0.h, p0, z0.h, z1.h
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  8 x i16> %a, <vscale x  8 x i16> %b
+  ret <vscale x  8 x i16> %res
+}
+
+define <vscale x  4 x i32> @select_nxv4i32(i1 %cond, <vscale x  4 x i32> %a, <vscale x  4 x i32> %b) {
+; CHECK-LABEL: select_nxv4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.s, xzr, x8
+; CHECK-NEXT:    sel z0.s, p0, z0.s, z1.s
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  4 x i32> %a, <vscale x  4 x i32> %b
+  ret <vscale x  4 x i32> %res
+}
+
+define <vscale x  2 x i64> @select_nxv2i64(i1 %cond, <vscale x  2 x i64> %a, <vscale x  2 x i64> %b) {
+; CHECK-LABEL: select_nxv2i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.d, xzr, x8
+; CHECK-NEXT:    sel z0.d, p0, z0.d, z1.d
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  2 x i64> %a, <vscale x  2 x i64> %b
+  ret <vscale x  2 x i64> %res
+}
+
+define <vscale x  8 x half> @select_nxv8f16(i1 %cond, <vscale x  8 x half> %a, <vscale x  8 x half> %b) {
+; CHECK-LABEL: select_nxv8f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.h, xzr, x8
+; CHECK-NEXT:    sel z0.h, p0, z0.h, z1.h
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  8 x half> %a, <vscale x  8 x half> %b
+  ret <vscale x  8 x half> %res
+}
+
+define <vscale x  4 x float> @select_nxv4f32(i1 %cond, <vscale x  4 x float> %a, <vscale x  4 x float> %b) {
+; CHECK-LABEL: select_nxv4f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.s, xzr, x8
+; CHECK-NEXT:    sel z0.s, p0, z0.s, z1.s
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  4 x float> %a, <vscale x  4 x float> %b
+  ret <vscale x  4 x float> %res
+}
+
+define <vscale x  2 x double> @select_nxv2f64(i1 %cond, <vscale x  2 x double> %a, <vscale x  2 x double> %b) {
+; CHECK-LABEL: select_nxv2f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p0.d, xzr, x8
+; CHECK-NEXT:    sel z0.d, p0, z0.d, z1.d
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  2 x double> %a, <vscale x  2 x double> %b
+  ret <vscale x  2 x double> %res
+}
+
+define <vscale x  16 x i1> @select_nxv16i1(i1 %cond, <vscale x  16 x i1> %a, <vscale x  16 x i1> %b) {
+; CHECK-LABEL: select_nxv16i1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p2.b, xzr, x8
+; CHECK-NEXT:    sel p0.b, p2, p0.b, p1.b
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  16 x i1> %a, <vscale x  16 x i1> %b
+  ret <vscale x  16 x i1> %res
+}
+
+define <vscale x  8 x i1> @select_nxv8i1(i1 %cond, <vscale x  8 x i1> %a, <vscale x  8 x i1> %b) {
+; CHECK-LABEL: select_nxv8i1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p2.h, xzr, x8
+; CHECK-NEXT:    sel p0.b, p2, p0.b, p1.b
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  8 x i1> %a, <vscale x  8 x i1> %b
+  ret <vscale x  8 x i1> %res
+}
+
+define <vscale x  4 x i1> @select_nxv4i1(i1 %cond, <vscale x  4 x i1> %a, <vscale x  4 x i1> %b) {
+; CHECK-LABEL: select_nxv4i1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p2.s, xzr, x8
+; CHECK-NEXT:    sel p0.b, p2, p0.b, p1.b
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  4 x i1> %a, <vscale x  4 x i1> %b
+  ret <vscale x  4 x i1> %res
+}
+
+define <vscale x  2 x i1> @select_nxv2i1(i1 %cond, <vscale x  2 x i1> %a, <vscale x  2 x i1> %b) {
+; CHECK-LABEL: select_nxv2i1:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $w0 killed $w0 def $x0
+; CHECK-NEXT:    sbfx x8, x0, #0, #1
+; CHECK-NEXT:    whilelo p2.d, xzr, x8
+; CHECK-NEXT:    sel p0.b, p2, p0.b, p1.b
+; CHECK-NEXT:    ret
+  %res = select i1 %cond, <vscale x  2 x i1> %a, <vscale x  2 x i1> %b
+  ret <vscale x  2 x i1> %res
+}