diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -23,7 +23,7 @@
     cl::desc(
         "The LMUL to use for getRegisterBitWidth queries. Affects LMUL used "
         "by autovectorized code. Fractional LMULs are not supported."),
-    cl::init(1), cl::Hidden);
+    cl::init(2), cl::Hidden);
 
 static cl::opt<unsigned> SLPMaxVF(
     "riscv-v-slp-max-vf",
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/lmul.ll b/llvm/test/Transforms/LoopVectorize/RISCV/lmul.ll
--- a/llvm/test/Transforms/LoopVectorize/RISCV/lmul.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/lmul.ll
@@ -9,25 +9,43 @@
 ; DEFAULT-LABEL: @load_store(
 ; DEFAULT-NEXT:  entry:
 ; DEFAULT-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP0]]
+; DEFAULT-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
 ; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; DEFAULT:       vector.ph:
-; DEFAULT-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP1]]
+; DEFAULT-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; DEFAULT-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
 ; DEFAULT-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
 ; DEFAULT-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; DEFAULT:       vector.body:
 ; DEFAULT-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; DEFAULT-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 0
-; DEFAULT-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i64, ptr [[P:%.*]], i64 [[TMP2]]
-; DEFAULT-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i64, ptr [[TMP3]], i32 0
-; DEFAULT-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 1 x i64>, ptr [[TMP4]], align 4
-; DEFAULT-NEXT:    [[TMP5:%.*]] = add <vscale x 1 x i64> [[WIDE_LOAD]], shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 1, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer)
-; DEFAULT-NEXT:    store <vscale x 1 x i64> [[TMP5]], ptr [[TMP4]], align 4
-; DEFAULT-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
-; DEFAULT-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; DEFAULT-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; DEFAULT-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
+; DEFAULT-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 2
+; DEFAULT-NEXT:    [[TMP7:%.*]] = add i64 [[TMP6]], 0
+; DEFAULT-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 1
+; DEFAULT-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], [[TMP8]]
+; DEFAULT-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[P:%.*]], i64 [[TMP4]]
+; DEFAULT-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[P]], i64 [[TMP9]]
+; DEFAULT-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[TMP10]], i32 0
+; DEFAULT-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP12]], align 4
+; DEFAULT-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 2
+; DEFAULT-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i64, ptr [[TMP10]], i64 [[TMP14]]
+; DEFAULT-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 2 x i64>, ptr [[TMP15]], align 4
+; DEFAULT-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[WIDE_LOAD]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; DEFAULT-NEXT:    [[TMP17:%.*]] = add <vscale x 2 x i64> [[WIDE_LOAD1]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
+; DEFAULT-NEXT:    store <vscale x 2 x i64> [[TMP16]], ptr [[TMP12]], align 4
+; DEFAULT-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP19:%.*]] = mul i64 [[TMP18]], 2
+; DEFAULT-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i64, ptr [[TMP10]], i64 [[TMP19]]
+; DEFAULT-NEXT:    store <vscale x 2 x i64> [[TMP17]], ptr [[TMP20]], align 4
+; DEFAULT-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 4
+; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP22]]
+; DEFAULT-NEXT:    [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; DEFAULT-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; DEFAULT:       middle.block:
 ; DEFAULT-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
 ; DEFAULT-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]