[llvm] f2b749b - [CostModel][SVE] Add cost model for shuffle reverse with i1 and scalable vector

[Caroline Concatto via llvm-commits]

Author: Caroline Concatto
Date: 2021-03-04T18:52:59Z
New Revision: f2b749be15688a8cebebdefe6b2be5a5dfaf5dd5

URL: https://github.com/llvm/llvm-project/commit/f2b749be15688a8cebebdefe6b2be5a5dfaf5dd5
DIFF: https://github.com/llvm/llvm-project/commit/f2b749be15688a8cebebdefe6b2be5a5dfaf5dd5.diff

LOG: [CostModel][SVE]  Add cost model for shuffle reverse with i1 and scalable vector

This patch adds the cost model for experimental.vector.reverse
with scalable vector types: nxv16i1, nxv8i1, nxv4i1 and nxv2i1.
These types are missing from the previous cost model patch D95603.

The cost model for experimental.vector.reverse with 1 bit mask is used by
loop vectorization in the patch D95363

Differential Revision: https://reviews.llvm.org/D97758

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 7902f01f4dc7..4851458e13e9 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1279,6 +1279,10 @@ int AArch64TTIImpl::getShuffleCost(TTI::ShuffleKind Kind, VectorType *Tp,
       { TTI::SK_Reverse, MVT::nxv8bf16, 1 },
       { TTI::SK_Reverse, MVT::nxv4f32,  1 },
       { TTI::SK_Reverse, MVT::nxv2f64,  1 },
+      { TTI::SK_Reverse, MVT::nxv16i1,  1 },
+      { TTI::SK_Reverse, MVT::nxv8i1,   1 },
+      { TTI::SK_Reverse, MVT::nxv4i1,   1 },
+      { TTI::SK_Reverse, MVT::nxv2i1,   1 },
     };
     std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
     if (const auto *Entry = CostTableLookup(ShuffleTbl, Kind, LT.second))

diff  --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 6653c394d7fd..d068d480120a 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -133,6 +133,11 @@ define void @vector_reverse() #0 {
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
+
   %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
   %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
   %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
@@ -149,6 +154,10 @@ define void @vector_reverse() #0 {
   %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
   %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
   %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
+  %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
+  %reverse_nxv8i1 =  call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
+  %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
+  %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
   ret void
 }
 declare <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8>)
@@ -167,5 +176,9 @@ declare <vscale x 2 x double> @llvm.experimental.vector.reverse.nxv2f64(<vscale
 declare <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double>)
 declare <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat>)
 declare <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat>)
+declare <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1>)
+declare <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1>)
+declare <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1>)
+declare <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1>)
 
 attributes #0 = { "target-features"="+sve,+bf16" }