[llvm] c417266 - [RISCV] Model interleave and deinterleave shuffles in cost model

[Luke Lau via llvm-commits]

Author: Luke Lau
Date: 2023-03-10T01:10:00Z
New Revision: c417266db506c2e000931c1f7a78e81879135c0d

URL: https://github.com/llvm/llvm-project/commit/c417266db506c2e000931c1f7a78e81879135c0d
DIFF: https://github.com/llvm/llvm-project/commit/c417266db506c2e000931c1f7a78e81879135c0d.diff

LOG: [RISCV] Model interleave and deinterleave shuffles in cost model

Interleave and deinterleave shuffles are lowered by a more efficient
sequence if the element size is smaller than ELEN.

Reviewed By: reames

Differential Revision: https://reviews.llvm.org/D145678

Added: 
    

Modified: 
    llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 6ae7b5ee1dbf4..b68080dc4b18e 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -8,7 +8,9 @@
 
 #include "RISCVTargetTransformInfo.h"
 #include "MCTargetDesc/RISCVMatInt.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Analysis/VectorUtils.h"
 #include "llvm/CodeGen/BasicTTIImpl.h"
 #include "llvm/CodeGen/CostTable.h"
 #include "llvm/CodeGen/TargetLowering.h"
@@ -323,6 +325,34 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
     return LT.first * getLMULCost(LT.second);
   }
 
+  if (isa<FixedVectorType>(Tp) && Kind == TTI::SK_PermuteSingleSrc &&
+      Mask.size() >= 2) {
+    std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Tp);
+    if (LT.second.isFixedLengthVector()) {
+      MVT EltTp = LT.second.getVectorElementType();
+      // If the size of the element is < ELEN then shuffles of interleaves and
+      // deinterleaves of 2 vectors can be lowered into the following sequences
+      if (EltTp.getScalarSizeInBits() < ST->getELEN()) {
+        auto InterleaveMask = createInterleaveMask(Mask.size() / 2, 2);
+        // Example sequence:
+        //   vsetivli	zero, 4, e8, mf4, ta, ma (ignored)
+        //   vwaddu.vv	v10, v8, v9
+        //   li		a0, -1                   (ignored)
+        //   vwmaccu.vx	v10, a0, v9
+        if (equal(InterleaveMask, Mask))
+          return 2 * LT.first * getLMULCost(LT.second);
+
+        if (Mask[0] == 0 || Mask[0] == 1) {
+          auto DeinterleaveMask = createStrideMask(Mask[0], 2, Mask.size());
+          // Example sequence:
+          //   vnsrl.wi	v10, v8, 0
+          if (equal(DeinterleaveMask, Mask))
+            return LT.first * getLMULCost(LT.second);
+        }
+      }
+    }
+  }
+
   return BaseT::getShuffleCost(Kind, Tp, Mask, CostKind, Index, SubTp);
 }
 

diff  --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll
index 52b708eb2153b..aed68b52fe2cc 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll
@@ -4,7 +4,7 @@
 define <8 x i8> @interleave2_v8i8(<4 x i8> %v0, <4 x i8> %v1) {
 ; CHECK-LABEL: 'interleave2_v8i8'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i8> %concat, <8 x i8> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = shufflevector <8 x i8> %concat, <8 x i8> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -15,7 +15,7 @@ define <8 x i8> @interleave2_v8i8(<4 x i8> %v0, <4 x i8> %v1) {
 define <8 x i32> @interleave2_v8i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: 'interleave2_v8i32'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i32> %concat, <8 x i32> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = shufflevector <8 x i32> %concat, <8 x i32> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i32> %res
 ;
   %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>