[SelectionDAG] Prevent warnings when extracting fixed length vector from scalable.

[paulwalker-arm]

Summary

ComputeNumSignBits and computeKnownBits both trigger "Scalable flag
may be dropped" warnings when a fixed length vector is extracted
from a scalable vector. This patch assumes nothing about the
demanded elements thus matching the behaviour when extracting a
scalable vector from a scalable vector.

[paulwalker-arm]

Made new test consistent with the others in the file.

[efriedma]

LGTM

[david-arm]

LGTM too! I'm wiping the tears of joy from my eyes as I type ...

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

if (!!DemandedSrcElts) {
       Known.One &= Known2.One;
       Known.Zero &= Known2.Zero;
     }
     break;
   }
   case ISD::EXTRACT_SUBVECTOR: {
     // Offset the demanded elts by the subvector index.
     SDValue Src = Op.getOperand(0);
+    // Bail until we can represent demanded elements for scalable vectors.
+    if (Src.getValueType().isScalableVector())
+      break;
     uint64_t Idx = Op.getConstantOperandVal(1);
     unsigned NumSrcElts = Src.getValueType().getVectorNumElements();
     APInt DemandedSrcElts = DemandedElts.zextOrSelf(NumSrcElts).shl(Idx);
     Known = computeKnownBits(Src, DemandedSrcElts, Depth + 1);
     break;
   }
   case ISD::SCALAR_TO_VECTOR: {
     // We know about scalar_to_vector as much as we know about it source,
if (ConstEltNo && ConstEltNo->getAPIntValue().ult(NumSrcElts))
       DemandedSrcElts =
           APInt::getOneBitSet(NumSrcElts, ConstEltNo->getZExtValue());
 
     return ComputeNumSignBits(InVec, DemandedSrcElts, Depth + 1);
   }
   case ISD::EXTRACT_SUBVECTOR: {
     // Offset the demanded elts by the subvector index.
     SDValue Src = Op.getOperand(0);
+    // Bail until we can represent demanded elements for scalable vectors.
+    if (Src.getValueType().isScalableVector())
+      break;
     uint64_t Idx = Op.getConstantOperandVal(1);
     unsigned NumSrcElts = Src.getValueType().getVectorNumElements();
     APInt DemandedSrcElts = DemandedElts.zextOrSelf(NumSrcElts).shl(Idx);
     return ComputeNumSignBits(Src, DemandedSrcElts, Depth + 1);
   }
   case ISD::CONCAT_VECTORS: {
     // Determine the minimum number of sign bits across all demanded
     // elts of the input vectors. Early out if the result is already 1.

llvm/test/CodeGen/AArch64/sve-fixed-length-subvector.ll

 ; RUN: llc -aarch64-sve-vector-bits-min=128  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefix=NO_SVE
 ; RUN: llc -aarch64-sve-vector-bits-min=256  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK
 ; RUN: llc -aarch64-sve-vector-bits-min=384  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK
 ; RUN: llc -aarch64-sve-vector-bits-min=512  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512
 ; RUN: llc -aarch64-sve-vector-bits-min=640  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512
 ; RUN: llc -aarch64-sve-vector-bits-min=768  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512
 ; RUN: llc -aarch64-sve-vector-bits-min=896  -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512
 ; RUN: llc -aarch64-sve-vector-bits-min=1024 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1152 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1280 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1408 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1536 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1664 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1792 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
 ; RUN: llc -aarch64-sve-vector-bits-min=1920 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024
-; RUN: llc -aarch64-sve-vector-bits-min=2048 -aarch64-enable-atomic-cfg-tidy=false < %s | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024,VBITS_GE_2048
+; RUN: llc -aarch64-sve-vector-bits-min=2048 -aarch64-enable-atomic-cfg-tidy=false < %s 2>%t | FileCheck %s -check-prefixes=CHECK,VBITS_GE_512,VBITS_GE_1024,VBITS_GE_2048
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; WARN-NOT: warning
 
 ; Test we can code generater patterns of the form:
 ;   fixed_length_vector = ISD::EXTRACT_SUBVECTOR scalable_vector, 0
 ;   scalable_vector = ISD::INSERT_SUBVECTOR scalable_vector, fixed_length_vector, 0
 ;
 ; NOTE: Currently shufflevector does not support scalable vectors so it cannot
 ; be used to model the above operations.  Instead these tests rely on knowing
 ; how fixed length operation are lowered to scalable ones, with multiple blocks
; CHECK: ret
   %a = load <64 x i32>, <64 x i32>* %in
   br label %bb1
 
 bb1:
   store <64 x i32> %a, <64 x i32>* %out
   ret void
 }
 
+;
+define <8 x i1> @no_warn_dropped_scalable(<8 x i32>* %in) #0 {
+; CHECK-LABEL: no_warn_dropped_scalable:
+; CHECK: ptrue [[PG:p[0-9]+]].s, vl8
+; CHECK: ld1w { z{{[0-9]+}}.s }, [[PG]]/z, [x0]
+; CHECK-COUNT-8: cmp w{{[0-9]+}}, #0
+; CHECK: ret
+  %a = load <8 x i32>, <8 x i32>* %in
+  br label %bb1
+
+bb1:
+  %cond = icmp sgt <8 x i32> %a, zeroinitializer
+  ret <8 x i1> %cond
+}
+
 attributes #0 = { "target-features"="+sve" }