[RISCV] Enable fixed-length vectorization of LoopVectorizer for RISC-V Vector

By implementing the method "unsigned RISCVTTIImpl::getRegisterBitWidth(bool Vector)",
fixed-length vectorization is enabled when possible. Without this method, the
"#pragma clang loop" directive is needed to enable vectorization(or the cost model
may inform LLVM that "Vectorization is possible but not beneficial").

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D97549

2 files changed, 47 insertions, 0 deletions

diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index 5177f81..ad9c1b6 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -51,6 +51,15 @@ public:
   bool shouldExpandReduction(const IntrinsicInst *II) const;
   bool supportsScalableVectors() const { return ST->hasStdExtV(); }
   Optional<unsigned> getMaxVScale() const;
+
+  unsigned getRegisterBitWidth(bool Vector) const {
+    if (Vector) {
+      if (ST->hasStdExtV())
+        return ST->getMinRVVVectorSizeInBits();
+      return 0;
+    }
+    return ST->getXLen();
+  }
 };
 
 } // end namespace llvm
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-unroll.ll b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-unroll.ll
new file mode 100644
index 0000000..efbdc3a
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-unroll.ll
@@ -0,0 +1,38 @@
+; RUN: opt < %s -loop-vectorize -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -S | FileCheck %s
+
+; Function Attrs: nounwind
+define i32* @array_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32* %c, i32 %size) {
+;CHECK-LABEL: array_add
+;CHECK: load <4 x i32>
+;CHECK: load <4 x i32>
+;CHECK: add nsw <4 x i32>
+;CHECK: store <4 x i32>
+;CHECK: ret
+entry:
+  %cmp10 = icmp sgt i32 %size, 0
+  br i1 %cmp10, label %for.body.preheader, label %for.end
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %1 = load i32, i32* %arrayidx2, align 4
+  %add = add nsw i32 %1, %0
+  %arrayidx4 = getelementptr inbounds i32, i32* %c, i64 %indvars.iv
+  store i32 %add, i32* %arrayidx4, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %size
+  br i1 %exitcond, label %for.end.loopexit, label %for.body
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret i32* %c
+}