[PATCH] D137547: [AArch64][SVE] Use PTRUE instruction for get_active_lane_mask intrinsic if the range is appropriate for predicator constant

Dinar Temirbulatov via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Nov 18 08:21:47 PST 2022


This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG44e2c6a428cc: [AArch64][SVE] Use PTRUE instruction instead of WHILELO if the range is… (authored by dtemirbulatov).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D137547/new/

https://reviews.llvm.org/D137547

Files:
  llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
  llvm/test/CodeGen/AArch64/active_lane_mask.ll


Index: llvm/test/CodeGen/AArch64/active_lane_mask.ll
===================================================================
--- llvm/test/CodeGen/AArch64/active_lane_mask.ll
+++ llvm/test/CodeGen/AArch64/active_lane_mask.ll
@@ -475,6 +475,58 @@
   ret <2 x i1> %active.lane.mask
 }
 
+define <vscale x 4 x i1> @lane_mask_nxv4i1_imm3() {
+; CHECK-LABEL: lane_mask_nxv4i1_imm3:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ptrue p0.s, vl3
+; CHECK-NEXT:    ret
+entry:
+  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 3)
+  ret <vscale x 4 x i1> %active.lane.mask
+}
+
+define <vscale x 4 x i1> @lane_mask_nxv4i1_imm5() {
+; CHECK-LABEL: lane_mask_nxv4i1_imm5:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mov w8, #5
+; CHECK-NEXT:    whilelo p0.s, xzr, x8
+; CHECK-NEXT:    ret
+entry:
+  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 5)
+  ret <vscale x 4 x i1> %active.lane.mask
+}
+
+define <vscale x 4 x i1> @lane_mask_nxv4i1_imm4() {
+; CHECK-LABEL: lane_mask_nxv4i1_imm4:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ptrue p0.s, vl4
+; CHECK-NEXT:    ret
+entry:
+  %active.lane.mask = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 10, i64 14)
+  ret <vscale x 4 x i1> %active.lane.mask
+}
+
+define <vscale x 16 x i1> @lane_mask_nxv16i1_imm10() {
+; CHECK-LABEL: lane_mask_nxv16i1_imm10:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mov w8, #10
+; CHECK-NEXT:    whilelo p0.b, xzr, x8
+; CHECK-NEXT:    ret
+entry:
+  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 0, i64 10)
+  ret <vscale x 16 x i1> %active.lane.mask
+}
+
+define <vscale x 16 x i1> @lane_mask_nxv16i1_imm256() vscale_range(16, 16) {
+; CHECK-LABEL: lane_mask_nxv16i1_imm256:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ptrue p0.b, vl256
+; CHECK-NEXT:    ret
+entry:
+  %active.lane.mask = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 0, i64 256)
+  ret <vscale x 16 x i1> %active.lane.mask
+}
+
 
 declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i32(i32, i32)
 declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32, i32)
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -4749,6 +4749,22 @@
                                                  Op.getOperand(1))));
     return SDValue();
   }
+  case Intrinsic::aarch64_sve_whilelo: {
+    if (isa<ConstantSDNode>(Op.getOperand(1)) &&
+        isa<ConstantSDNode>(Op.getOperand(2))) {
+      unsigned MinSVEVectorSize =
+          std::max(Subtarget->getMinSVEVectorSizeInBits(), 128u);
+      unsigned ElementSize = 128 / Op.getValueType().getVectorMinNumElements();
+      unsigned NumActiveElems =
+          Op.getConstantOperandVal(2) - Op.getConstantOperandVal(1);
+      Optional<unsigned> PredPattern =
+          getSVEPredPatternFromNumElements(NumActiveElems);
+      if ((PredPattern != None) &&
+          NumActiveElems <= (MinSVEVectorSize / ElementSize))
+        return getPTrue(DAG, dl, Op.getValueType(), *PredPattern);
+    }
+    return SDValue();
+  }
   case Intrinsic::aarch64_sve_sunpkhi:
     return DAG.getNode(AArch64ISD::SUNPKHI, dl, Op.getValueType(),
                        Op.getOperand(1));


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D137547.476489.patch
Type: text/x-patch
Size: 3475 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221118/25aefed2/attachment.bin>


More information about the llvm-commits mailing list