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
@@ -268,6 +268,7 @@
     {Intrinsic::floor, MVT::v4f32, 9},
     {Intrinsic::floor, MVT::v8f32, 9},
     {Intrinsic::floor, MVT::v16f32, 9},
+    {Intrinsic::floor, MVT::nxv1f32, 9},
     {Intrinsic::floor, MVT::nxv2f32, 9},
     {Intrinsic::floor, MVT::nxv4f32, 9},
     {Intrinsic::floor, MVT::nxv8f32, 9},
@@ -284,6 +285,7 @@
     {Intrinsic::ceil, MVT::v4f32, 9},
     {Intrinsic::ceil, MVT::v8f32, 9},
     {Intrinsic::ceil, MVT::v16f32, 9},
+    {Intrinsic::ceil, MVT::nxv1f32, 9},
     {Intrinsic::ceil, MVT::nxv2f32, 9},
     {Intrinsic::ceil, MVT::nxv4f32, 9},
     {Intrinsic::ceil, MVT::nxv8f32, 9},
@@ -300,6 +302,7 @@
     {Intrinsic::trunc, MVT::v4f32, 7},
     {Intrinsic::trunc, MVT::v8f32, 7},
     {Intrinsic::trunc, MVT::v16f32, 7},
+    {Intrinsic::trunc, MVT::nxv1f32, 7},
     {Intrinsic::trunc, MVT::nxv2f32, 7},
     {Intrinsic::trunc, MVT::nxv4f32, 7},
     {Intrinsic::trunc, MVT::nxv8f32, 7},
@@ -316,6 +319,7 @@
     {Intrinsic::round, MVT::v4f32, 9},
     {Intrinsic::round, MVT::v8f32, 9},
     {Intrinsic::round, MVT::v16f32, 9},
+    {Intrinsic::round, MVT::nxv1f32, 9},
     {Intrinsic::round, MVT::nxv2f32, 9},
     {Intrinsic::round, MVT::nxv4f32, 9},
     {Intrinsic::round, MVT::nxv8f32, 9},
@@ -332,6 +336,7 @@
     {Intrinsic::roundeven, MVT::v4f32, 9},
     {Intrinsic::roundeven, MVT::v8f32, 9},
     {Intrinsic::roundeven, MVT::v16f32, 9},
+    {Intrinsic::roundeven, MVT::nxv1f32, 9},
     {Intrinsic::roundeven, MVT::nxv2f32, 9},
     {Intrinsic::roundeven, MVT::nxv4f32, 9},
     {Intrinsic::roundeven, MVT::nxv8f32, 9},
@@ -348,6 +353,7 @@
     {Intrinsic::fabs, MVT::v4f32, 1},
     {Intrinsic::fabs, MVT::v8f32, 1},
     {Intrinsic::fabs, MVT::v16f32, 1},
+    {Intrinsic::fabs, MVT::nxv1f32, 1},
     {Intrinsic::fabs, MVT::nxv2f32, 1},
     {Intrinsic::fabs, MVT::nxv4f32, 1},
     {Intrinsic::fabs, MVT::nxv8f32, 1},
@@ -364,6 +370,7 @@
     {Intrinsic::sqrt, MVT::v4f32, 1},
     {Intrinsic::sqrt, MVT::v8f32, 1},
     {Intrinsic::sqrt, MVT::v16f32, 1},
+    {Intrinsic::sqrt, MVT::nxv1f32, 1},
     {Intrinsic::sqrt, MVT::nxv2f32, 1},
     {Intrinsic::sqrt, MVT::nxv4f32, 1},
     {Intrinsic::sqrt, MVT::nxv8f32, 1},
@@ -380,6 +387,7 @@
     {Intrinsic::bswap, MVT::v4i16, 3},
     {Intrinsic::bswap, MVT::v8i16, 3},
     {Intrinsic::bswap, MVT::v16i16, 3},
+    {Intrinsic::bswap, MVT::nxv1i16, 3},
     {Intrinsic::bswap, MVT::nxv2i16, 3},
     {Intrinsic::bswap, MVT::nxv4i16, 3},
     {Intrinsic::bswap, MVT::nxv8i16, 3},
@@ -388,6 +396,7 @@
     {Intrinsic::bswap, MVT::v4i32, 12},
     {Intrinsic::bswap, MVT::v8i32, 12},
     {Intrinsic::bswap, MVT::v16i32, 12},
+    {Intrinsic::bswap, MVT::nxv1i32, 12},
     {Intrinsic::bswap, MVT::nxv2i32, 12},
     {Intrinsic::bswap, MVT::nxv4i32, 12},
     {Intrinsic::bswap, MVT::nxv8i32, 12},
@@ -396,6 +405,7 @@
     {Intrinsic::bswap, MVT::v4i64, 31},
     {Intrinsic::bswap, MVT::v8i64, 31},
     {Intrinsic::bswap, MVT::v16i64, 31},
+    {Intrinsic::bswap, MVT::nxv1i64, 31},
     {Intrinsic::bswap, MVT::nxv2i64, 31},
     {Intrinsic::bswap, MVT::nxv4i64, 31},
     {Intrinsic::bswap, MVT::nxv8i64, 31},
@@ -403,6 +413,7 @@
     {Intrinsic::bitreverse, MVT::v4i8, 17},
     {Intrinsic::bitreverse, MVT::v8i8, 17},
     {Intrinsic::bitreverse, MVT::v16i8, 17},
+    {Intrinsic::bitreverse, MVT::nxv1i8, 17},
     {Intrinsic::bitreverse, MVT::nxv2i8, 17},
     {Intrinsic::bitreverse, MVT::nxv4i8, 17},
     {Intrinsic::bitreverse, MVT::nxv8i8, 17},
@@ -411,6 +422,7 @@
     {Intrinsic::bitreverse, MVT::v4i16, 24},
     {Intrinsic::bitreverse, MVT::v8i16, 24},
     {Intrinsic::bitreverse, MVT::v16i16, 24},
+    {Intrinsic::bitreverse, MVT::nxv1i16, 24},
     {Intrinsic::bitreverse, MVT::nxv2i16, 24},
     {Intrinsic::bitreverse, MVT::nxv4i16, 24},
     {Intrinsic::bitreverse, MVT::nxv8i16, 24},
@@ -419,6 +431,7 @@
     {Intrinsic::bitreverse, MVT::v4i32, 33},
     {Intrinsic::bitreverse, MVT::v8i32, 33},
     {Intrinsic::bitreverse, MVT::v16i32, 33},
+    {Intrinsic::bitreverse, MVT::nxv1i32, 33},
     {Intrinsic::bitreverse, MVT::nxv2i32, 33},
     {Intrinsic::bitreverse, MVT::nxv4i32, 33},
     {Intrinsic::bitreverse, MVT::nxv8i32, 33},
@@ -427,6 +440,7 @@
     {Intrinsic::bitreverse, MVT::v4i64, 52},
     {Intrinsic::bitreverse, MVT::v8i64, 52},
     {Intrinsic::bitreverse, MVT::v16i64, 52},
+    {Intrinsic::bitreverse, MVT::nxv1i64, 52},
     {Intrinsic::bitreverse, MVT::nxv2i64, 52},
     {Intrinsic::bitreverse, MVT::nxv4i64, 52},
     {Intrinsic::bitreverse, MVT::nxv8i64, 52},
@@ -434,6 +448,7 @@
     {Intrinsic::ctpop, MVT::v4i8, 12},
     {Intrinsic::ctpop, MVT::v8i8, 12},
     {Intrinsic::ctpop, MVT::v16i8, 12},
+    {Intrinsic::ctpop, MVT::nxv1i8, 12},
     {Intrinsic::ctpop, MVT::nxv2i8, 12},
     {Intrinsic::ctpop, MVT::nxv4i8, 12},
     {Intrinsic::ctpop, MVT::nxv8i8, 12},
@@ -442,6 +457,7 @@
     {Intrinsic::ctpop, MVT::v4i16, 19},
     {Intrinsic::ctpop, MVT::v8i16, 19},
     {Intrinsic::ctpop, MVT::v16i16, 19},
+    {Intrinsic::ctpop, MVT::nxv1i16, 19},
     {Intrinsic::ctpop, MVT::nxv2i16, 19},
     {Intrinsic::ctpop, MVT::nxv4i16, 19},
     {Intrinsic::ctpop, MVT::nxv8i16, 19},
@@ -450,6 +466,7 @@
     {Intrinsic::ctpop, MVT::v4i32, 20},
     {Intrinsic::ctpop, MVT::v8i32, 20},
     {Intrinsic::ctpop, MVT::v16i32, 20},
+    {Intrinsic::ctpop, MVT::nxv1i32, 20},
     {Intrinsic::ctpop, MVT::nxv2i32, 20},
     {Intrinsic::ctpop, MVT::nxv4i32, 20},
     {Intrinsic::ctpop, MVT::nxv8i32, 20},
@@ -458,6 +475,7 @@
     {Intrinsic::ctpop, MVT::v4i64, 21},
     {Intrinsic::ctpop, MVT::v8i64, 21},
     {Intrinsic::ctpop, MVT::v16i64, 21},
+    {Intrinsic::ctpop, MVT::nxv1i64, 21},
     {Intrinsic::ctpop, MVT::nxv2i64, 21},
     {Intrinsic::ctpop, MVT::nxv4i64, 21},
     {Intrinsic::ctpop, MVT::nxv8i64, 21},
diff --git a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
--- a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -660,18 +660,21 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %14 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %15 = call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x half> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %27 = call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x half> @llvm.fmuladd.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x half> undef, <vscale x 1 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x half> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x double> @llvm.fmuladd.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %30 = call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call half @llvm.fmuladd.f16(half undef, half undef, half undef)
@@ -689,14 +692,17 @@
   call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
   call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
   call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
+  call <vscale x 1 x half> @llvm.fmuladd.nxv1f16(<vscale x 1 x half> undef, <vscale x 1 x half> undef, <vscale x 1 x half> undef)
   call <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x half> undef)
   call <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x half> undef)
   call <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x half> undef)
   call <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x half> undef)
+  call <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
   call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
+  call <vscale x 1 x double> @llvm.fmuladd.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x double> undef)
   call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
   call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
   call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
@@ -799,14 +805,17 @@
 declare <4 x double> @llvm.fmuladd.v4f64(<4 x double>, <4 x double>, <4 x double>)
 declare <8 x double> @llvm.fmuladd.v8f64(<8 x double>, <8 x double>, <8 x double>)
 declare <16 x double> @llvm.fmuladd.v16f64(<16 x double>, <16 x double>, <16 x double>)
+declare <vscale x 1 x half> @llvm.fmuladd.nxv1f16(<vscale x 1 x half>, <vscale x 1 x half>, <vscale x 1 x half>)
 declare <vscale x 2 x half> @llvm.fmuladd.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
 declare <vscale x 4 x half> @llvm.fmuladd.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
 declare <vscale x 8 x half> @llvm.fmuladd.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
 declare <vscale x 16 x half> @llvm.fmuladd.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, <vscale x 16 x half>)
+declare <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float>, <vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, <vscale x 8 x float>)
 declare <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, <vscale x 16 x float>)
+declare <vscale x 1 x double> @llvm.fmuladd.nxv1f64(<vscale x 1 x double>, <vscale x 1 x double>, <vscale x 1 x double>)
 declare <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, <vscale x 4 x double>)
 declare <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>, <vscale x 8 x double>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
--- a/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-min-max-abs.ll
@@ -8,19 +8,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.fabs.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.fabs.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.fabs.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.fabs.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.fabs.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.fabs.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.fabs.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.fabs.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.fabs.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.fabs.f32(float undef)
@@ -28,6 +29,7 @@
   call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
   call <8 x float> @llvm.fabs.v8f32(<8 x float> undef)
   call <16 x float> @llvm.fabs.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.fabs.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.fabs.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.fabs.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.fabs.nvx8f32(<vscale x 8 x float> undef)
@@ -51,19 +53,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.minnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.minnum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.minnum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.minnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.minnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.minnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.minnum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.minnum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.minnum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.minnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.minnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.minnum.f32(float undef, float undef)
@@ -71,6 +74,7 @@
   call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.minnum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.minnum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.minnum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.minnum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.minnum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -94,19 +98,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.maxnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.maxnum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.maxnum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.maxnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.maxnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.maxnum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.maxnum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.maxnum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.maxnum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.maxnum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.maxnum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.maxnum.f32(float undef, float undef)
@@ -114,6 +119,7 @@
   call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.maxnum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.maxnum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.maxnum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.maxnum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.maxnum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -137,19 +143,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.minimum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.minimum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.minimum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.minimum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.minimum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.minimum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.minimum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.minimum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.minimum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.minimum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.minimum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.minimum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.minimum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.minimum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.minimum.f32(float undef, float undef)
@@ -157,6 +164,7 @@
   call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.minimum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.minimum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.minimum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.minimum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.minimum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -180,19 +188,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.maximum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.maximum.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.maximum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.maximum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.maximum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.maximum.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.maximum.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.maximum.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.maximum.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.maximum.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.maximum.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.maximum.f32(float undef, float undef)
@@ -200,6 +209,7 @@
   call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.maximum.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.maximum.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.maximum.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.maximum.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.maximum.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -223,19 +233,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.copysign.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.copysign.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.copysign.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.copysign.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.copysign.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.copysign.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.copysign.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.copysign.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.copysign.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.copysign.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.copysign.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.copysign.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.copysign.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.copysign.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.copysign.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.copysign.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.copysign.f32(float undef, float undef)
@@ -243,6 +254,7 @@
   call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.copysign.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.copysign.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.copysign.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.copysign.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -264,6 +276,7 @@
 declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
 declare <8 x float> @llvm.fabs.v8f32(<8 x float>)
 declare <16 x float> @llvm.fabs.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.fabs.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.fabs.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.fabs.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.fabs.nvx8f32(<vscale x 8 x float>)
@@ -283,6 +296,7 @@
 declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.minnum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.minnum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.minnum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.minnum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.minnum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.minnum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
@@ -302,6 +316,7 @@
 declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.maxnum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.maxnum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.maxnum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.maxnum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.maxnum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.maxnum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
@@ -321,6 +336,7 @@
 declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.minimum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.minimum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.minimum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.minimum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.minimum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.minimum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
@@ -340,6 +356,7 @@
 declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.maximum.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.maximum.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.maximum.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.maximum.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.maximum.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
@@ -359,6 +376,7 @@
 declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.copysign.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.copysign.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.copysign.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.copysign.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.copysign.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
--- a/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-sqrt-pow.ll
@@ -8,19 +8,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.sqrt.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x float> @llvm.sqrt.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call double @llvm.sqrt.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.sqrt.f32(float undef)
@@ -28,6 +29,7 @@
   call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
   call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
   call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.sqrt.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float> undef)
@@ -49,6 +51,7 @@
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
 declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
 declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.sqrt.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float>)
@@ -70,19 +73,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.pow.v4f32(<4 x float> undef, <4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.pow.v8f32(<8 x float> undef, <8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.pow.v16f32(<16 x float> undef, <16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.pow.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.pow.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.pow.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.pow.f64(double undef, double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.pow.v2f64(<2 x double> undef, <2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.pow.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.pow.v8f64(<8 x double> undef, <8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.pow.v16f64(<16 x double> undef, <16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.pow.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.pow.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.pow.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.pow.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.pow.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.pow.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.pow.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.pow.f64(double undef, double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.pow.v2f64(<2 x double> undef, <2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.pow.v4f64(<4 x double> undef, <4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.pow.v8f64(<8 x double> undef, <8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.pow.v16f64(<16 x double> undef, <16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.pow.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.pow.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.pow.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.pow.f32(float undef, float undef)
@@ -90,6 +94,7 @@
   call <4 x float> @llvm.pow.v4f32(<4 x float> undef, <4 x float> undef)
   call <8 x float> @llvm.pow.v8f32(<8 x float> undef, <8 x float> undef)
   call <16 x float> @llvm.pow.v16f32(<16 x float> undef, <16 x float> undef)
+  call <vscale x 1 x float> @llvm.pow.nvx1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.pow.nvx2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.pow.nvx4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.pow.nvx8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
@@ -111,6 +116,7 @@
 declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
 declare <8 x float> @llvm.pow.v8f32(<8 x float>, <8 x float>)
 declare <16 x float> @llvm.pow.v16f32(<16 x float>, <16 x float>)
+declare <vscale x 1 x float> @llvm.pow.nvx1f32(<vscale x 1 x float>, <vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.pow.nvx2f32(<vscale x 2 x float>, <vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.pow.nvx4f32(<vscale x 4 x float>, <vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.pow.nvx8f32(<vscale x 8 x float>, <vscale x 8 x float>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fp-trig-log-exp.ll b/llvm/test/Analysis/CostModel/RISCV/fp-trig-log-exp.ll
--- a/llvm/test/Analysis/CostModel/RISCV/fp-trig-log-exp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fp-trig-log-exp.ll
@@ -8,19 +8,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.sin.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.sin.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.sin.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.sin.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.sin.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.sin.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.sin.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.sin.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.sin.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.sin.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.sin.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.sin.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.sin.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.sin.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.sin.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.sin.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.sin.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.sin.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.sin.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.sin.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.sin.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.sin.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.sin.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.sin.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.sin.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.sin.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.sin.f32(float undef)
@@ -28,6 +29,7 @@
   call <4 x float> @llvm.sin.v4f32(<4 x float> undef)
   call <8 x float> @llvm.sin.v8f32(<8 x float> undef)
   call <16 x float> @llvm.sin.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.sin.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.sin.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.sin.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.sin.nvx8f32(<vscale x 8 x float> undef)
@@ -51,19 +53,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.cos.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.cos.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.cos.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.cos.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.cos.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.cos.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.cos.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.cos.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.cos.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.cos.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.cos.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.cos.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.cos.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.cos.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.cos.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.cos.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.cos.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.cos.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.cos.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.cos.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.cos.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.cos.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.cos.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.cos.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.cos.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.cos.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.cos.f32(float undef)
@@ -71,6 +74,7 @@
   call <4 x float> @llvm.cos.v4f32(<4 x float> undef)
   call <8 x float> @llvm.cos.v8f32(<8 x float> undef)
   call <16 x float> @llvm.cos.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.cos.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.cos.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.cos.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.cos.nvx8f32(<vscale x 8 x float> undef)
@@ -94,19 +98,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.exp.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.exp.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.exp.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.exp.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.exp.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.exp.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.exp.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.exp.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.exp.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.exp.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.exp.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.exp.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.exp.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.exp.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.exp.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.exp.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.exp.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.exp.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.exp.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.exp.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.exp.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.exp.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.exp.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.exp.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.exp.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.exp.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.exp.f32(float undef)
@@ -114,6 +119,7 @@
   call <4 x float> @llvm.exp.v4f32(<4 x float> undef)
   call <8 x float> @llvm.exp.v8f32(<8 x float> undef)
   call <16 x float> @llvm.exp.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.exp.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.exp.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.exp.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.exp.nvx8f32(<vscale x 8 x float> undef)
@@ -137,19 +143,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.exp2.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.exp2.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.exp2.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.exp2.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.exp2.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.exp2.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.exp2.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.exp2.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.exp2.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.exp2.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.exp2.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.exp2.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.exp2.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.exp2.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.exp2.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.exp2.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.exp2.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.exp2.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.exp2.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.exp2.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.exp2.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.exp2.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.exp2.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.exp2.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.exp2.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.exp2.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.exp2.f32(float undef)
@@ -157,6 +164,7 @@
   call <4 x float> @llvm.exp2.v4f32(<4 x float> undef)
   call <8 x float> @llvm.exp2.v8f32(<8 x float> undef)
   call <16 x float> @llvm.exp2.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.exp2.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.exp2.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.exp2.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.exp2.nvx8f32(<vscale x 8 x float> undef)
@@ -180,19 +188,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.log.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.log.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.log.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.log.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.log.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.log.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.log.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.log.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.log.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.log.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.log.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.log.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.log.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.log.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.log.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.log.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.log.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.log.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.log.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.log.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.log.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.log.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.log.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.log.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.log.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.log.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.log.f32(float undef)
@@ -200,6 +209,7 @@
   call <4 x float> @llvm.log.v4f32(<4 x float> undef)
   call <8 x float> @llvm.log.v8f32(<8 x float> undef)
   call <16 x float> @llvm.log.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.log.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.log.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.log.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.log.nvx8f32(<vscale x 8 x float> undef)
@@ -223,19 +233,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.log10.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.log10.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.log10.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.log10.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.log10.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.log10.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.log10.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.log10.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.log10.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.log10.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.log10.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.log10.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.log10.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.log10.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.log10.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.log10.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.log10.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.log10.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.log10.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.log10.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.log10.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.log10.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.log10.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.log10.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.log10.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.log10.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.log10.f32(float undef)
@@ -243,6 +254,7 @@
   call <4 x float> @llvm.log10.v4f32(<4 x float> undef)
   call <8 x float> @llvm.log10.v8f32(<8 x float> undef)
   call <16 x float> @llvm.log10.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.log10.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.log10.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.log10.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.log10.nvx8f32(<vscale x 8 x float> undef)
@@ -266,19 +278,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.log2.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.log2.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.log2.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.log2.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.log2.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.log2.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.log2.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.log2.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.log2.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.log2.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.log2.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.log2.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.log2.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.log2.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.log2.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.log2.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.log2.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.log2.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.log2.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.log2.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.log2.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.log2.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.log2.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.log2.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.log2.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.log2.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.log2.f32(float undef)
@@ -286,6 +299,7 @@
   call <4 x float> @llvm.log2.v4f32(<4 x float> undef)
   call <8 x float> @llvm.log2.v8f32(<8 x float> undef)
   call <16 x float> @llvm.log2.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.log2.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.log2.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.log2.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.log2.nvx8f32(<vscale x 8 x float> undef)
@@ -307,6 +321,7 @@
 declare <4 x float> @llvm.sin.v4f32(<4 x float>)
 declare <8 x float> @llvm.sin.v8f32(<8 x float>)
 declare <16 x float> @llvm.sin.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.sin.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.sin.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.sin.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.sin.nvx8f32(<vscale x 8 x float>)
@@ -326,6 +341,7 @@
 declare <4 x float> @llvm.cos.v4f32(<4 x float>)
 declare <8 x float> @llvm.cos.v8f32(<8 x float>)
 declare <16 x float> @llvm.cos.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.cos.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.cos.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.cos.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.cos.nvx8f32(<vscale x 8 x float>)
@@ -345,6 +361,7 @@
 declare <4 x float> @llvm.exp.v4f32(<4 x float>)
 declare <8 x float> @llvm.exp.v8f32(<8 x float>)
 declare <16 x float> @llvm.exp.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.exp.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.exp.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.exp.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.exp.nvx8f32(<vscale x 8 x float>)
@@ -364,6 +381,7 @@
 declare <4 x float> @llvm.exp2.v4f32(<4 x float>)
 declare <8 x float> @llvm.exp2.v8f32(<8 x float>)
 declare <16 x float> @llvm.exp2.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.exp2.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.exp2.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.exp2.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.exp2.nvx8f32(<vscale x 8 x float>)
@@ -383,6 +401,7 @@
 declare <4 x float> @llvm.log.v4f32(<4 x float>)
 declare <8 x float> @llvm.log.v8f32(<8 x float>)
 declare <16 x float> @llvm.log.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.log.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.log.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.log.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.log.nvx8f32(<vscale x 8 x float>)
@@ -402,6 +421,7 @@
 declare <4 x float> @llvm.log10.v4f32(<4 x float>)
 declare <8 x float> @llvm.log10.v8f32(<8 x float>)
 declare <16 x float> @llvm.log10.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.log10.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.log10.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.log10.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.log10.nvx8f32(<vscale x 8 x float>)
@@ -421,6 +441,7 @@
 declare <4 x float> @llvm.log2.v4f32(<4 x float>)
 declare <8 x float> @llvm.log2.v8f32(<8 x float>)
 declare <16 x float> @llvm.log2.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.log2.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.log2.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.log2.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.log2.nvx8f32(<vscale x 8 x float>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/fround.ll b/llvm/test/Analysis/CostModel/RISCV/fround.ll
--- a/llvm/test/Analysis/CostModel/RISCV/fround.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fround.ll
@@ -8,19 +8,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.floor.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.floor.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.floor.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.floor.f32(float undef)
@@ -28,6 +29,7 @@
   call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
   call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
   call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.floor.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.floor.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.floor.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.floor.nvx8f32(<vscale x 8 x float> undef)
@@ -51,19 +53,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.ceil.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.ceil.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.ceil.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.ceil.f32(float undef)
@@ -71,6 +74,7 @@
   call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
   call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
   call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.ceil.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.ceil.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.ceil.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.ceil.nvx8f32(<vscale x 8 x float> undef)
@@ -94,19 +98,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %3 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %4 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %5 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.trunc.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %11 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %12 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %13 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %14 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 1 x float> @llvm.trunc.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.trunc.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.trunc.f32(float undef)
@@ -114,6 +119,7 @@
   call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
   call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
   call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.trunc.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.trunc.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.trunc.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.trunc.nvx8f32(<vscale x 8 x float> undef)
@@ -137,19 +143,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.rint.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.rint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.rint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.rint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.rint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.rint.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.rint.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.rint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.rint.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.rint.f32(float undef)
@@ -157,6 +164,7 @@
   call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
   call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
   call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.rint.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.rint.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.rint.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.rint.nvx8f32(<vscale x 8 x float> undef)
@@ -180,19 +188,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %3 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %4 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %5 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.nearbyint.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %11 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %12 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %13 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %14 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %15 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %6 = call <vscale x 1 x float> @llvm.nearbyint.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.nearbyint.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %12 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %13 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 95 for instruction: %14 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 191 for instruction: %15 = call <16 x double> @llvm.nearbyint.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %16 = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %18 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.nearbyint.f32(float undef)
@@ -200,6 +209,7 @@
   call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
   call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
   call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.nearbyint.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.nearbyint.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.nearbyint.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.nearbyint.nvx8f32(<vscale x 8 x float> undef)
@@ -223,19 +233,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.round.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.round.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.round.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.round.f32(float undef)
@@ -243,6 +254,7 @@
   call <4 x float> @llvm.round.v4f32(<4 x float> undef)
   call <8 x float> @llvm.round.v8f32(<8 x float> undef)
   call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.round.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.round.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.round.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.round.nvx8f32(<vscale x 8 x float> undef)
@@ -266,19 +278,20 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %3 = call <4 x float> @llvm.roundeven.v4f32(<4 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %4 = call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %5 = call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.roundeven.f64(double undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %11 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = call <vscale x 1 x float> @llvm.roundeven.nxv1f32(<vscale x 1 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %7 = call <vscale x 2 x float> @llvm.roundeven.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %8 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %9 = call <vscale x 8 x float> @llvm.roundeven.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %10 = call <vscale x 16 x float> @llvm.roundeven.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call double @llvm.roundeven.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %13 = call <4 x double> @llvm.roundeven.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %14 = call <8 x double> @llvm.roundeven.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = call <16 x double> @llvm.roundeven.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = call <vscale x 1 x double> @llvm.roundeven.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %17 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %18 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %19 = call <vscale x 8 x double> @llvm.roundeven.nxv8f64(<vscale x 8 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call float @llvm.roundeven.f32(float undef)
@@ -286,6 +299,7 @@
   call <4 x float> @llvm.roundeven.v4f32(<4 x float> undef)
   call <8 x float> @llvm.roundeven.v8f32(<8 x float> undef)
   call <16 x float> @llvm.roundeven.v16f32(<16 x float> undef)
+  call <vscale x 1 x float> @llvm.roundeven.nvx1f32(<vscale x 1 x float> undef)
   call <vscale x 2 x float> @llvm.roundeven.nvx2f32(<vscale x 2 x float> undef)
   call <vscale x 4 x float> @llvm.roundeven.nvx4f32(<vscale x 4 x float> undef)
   call <vscale x 8 x float> @llvm.roundeven.nvx8f32(<vscale x 8 x float> undef)
@@ -307,6 +321,7 @@
 declare <4 x float> @llvm.floor.v4f32(<4 x float>)
 declare <8 x float> @llvm.floor.v8f32(<8 x float>)
 declare <16 x float> @llvm.floor.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.floor.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.floor.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.floor.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.floor.nvx8f32(<vscale x 8 x float>)
@@ -326,6 +341,7 @@
 declare <4 x float> @llvm.ceil.v4f32(<4 x float>)
 declare <8 x float> @llvm.ceil.v8f32(<8 x float>)
 declare <16 x float> @llvm.ceil.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.ceil.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.ceil.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.ceil.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.ceil.nvx8f32(<vscale x 8 x float>)
@@ -345,6 +361,7 @@
 declare <4 x float> @llvm.trunc.v4f32(<4 x float>)
 declare <8 x float> @llvm.trunc.v8f32(<8 x float>)
 declare <16 x float> @llvm.trunc.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.trunc.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.trunc.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.trunc.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.trunc.nvx8f32(<vscale x 8 x float>)
@@ -364,6 +381,7 @@
 declare <4 x float> @llvm.rint.v4f32(<4 x float>)
 declare <8 x float> @llvm.rint.v8f32(<8 x float>)
 declare <16 x float> @llvm.rint.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.rint.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.rint.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.rint.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.rint.nvx8f32(<vscale x 8 x float>)
@@ -383,6 +401,7 @@
 declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>)
 declare <8 x float> @llvm.nearbyint.v8f32(<8 x float>)
 declare <16 x float> @llvm.nearbyint.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.nearbyint.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.nearbyint.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.nearbyint.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.nearbyint.nvx8f32(<vscale x 8 x float>)
@@ -402,6 +421,7 @@
 declare <4 x float> @llvm.round.v4f32(<4 x float>)
 declare <8 x float> @llvm.round.v8f32(<8 x float>)
 declare <16 x float> @llvm.round.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.round.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.round.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.round.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.round.nvx8f32(<vscale x 8 x float>)
@@ -421,6 +441,7 @@
 declare <4 x float> @llvm.roundeven.v4f32(<4 x float>)
 declare <8 x float> @llvm.roundeven.v8f32(<8 x float>)
 declare <16 x float> @llvm.roundeven.v16f32(<16 x float>)
+declare <vscale x 1 x float> @llvm.roundeven.nvx1f32(<vscale x 1 x float>)
 declare <vscale x 2 x float> @llvm.roundeven.nvx2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.roundeven.nvx4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.roundeven.nvx8f32(<vscale x 8 x float>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
--- a/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-bit-manip.ll
@@ -8,28 +8,31 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %3 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %4 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %5 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 2 x i16> @llvm.bswap.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 4 x i16> @llvm.bswap.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 16 x i16> @llvm.bswap.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call i32 @llvm.bswap.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %11 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %12 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %13 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %14 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %15 = call <vscale x 2 x i32> @llvm.bswap.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 8 x i32> @llvm.bswap.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 16 x i32> @llvm.bswap.nxv16i32(<vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %19 = call i64 @llvm.bswap.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %20 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %21 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %22 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %23 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %24 = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %25 = call <vscale x 4 x i64> @llvm.bswap.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 8 x i64> @llvm.bswap.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %27 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %6 = call <vscale x 1 x i16> @llvm.bswap.nxv1i16(<vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %7 = call <vscale x 2 x i16> @llvm.bswap.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %8 = call <vscale x 4 x i16> @llvm.bswap.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %9 = call <vscale x 8 x i16> @llvm.bswap.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %10 = call <vscale x 16 x i16> @llvm.bswap.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call i32 @llvm.bswap.i32(i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %12 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %13 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %14 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %15 = call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %16 = call <vscale x 1 x i32> @llvm.bswap.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %17 = call <vscale x 2 x i32> @llvm.bswap.nxv2i32(<vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %18 = call <vscale x 4 x i32> @llvm.bswap.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = call <vscale x 8 x i32> @llvm.bswap.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %20 = call <vscale x 16 x i32> @llvm.bswap.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %21 = call i64 @llvm.bswap.i64(i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %22 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %23 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %24 = call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %25 = call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %26 = call <vscale x 1 x i64> @llvm.bswap.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %27 = call <vscale x 2 x i64> @llvm.bswap.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %28 = call <vscale x 4 x i64> @llvm.bswap.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %29 = call <vscale x 8 x i64> @llvm.bswap.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %30 = call <vscale x 16 x i64> @llvm.bswap.nxv16i64(<vscale x 16 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i16 @llvm.bswap.i16(i16 undef)
@@ -37,6 +40,7 @@
   call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.bswap.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.bswap.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.bswap.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.bswap.nvx8i16(<vscale x 8 x i16> undef)
@@ -46,6 +50,7 @@
   call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.bswap.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.bswap.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.bswap.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.bswap.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.bswap.nvx8i32(<vscale x 8 x i32> undef)
@@ -55,6 +60,7 @@
   call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.bswap.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.bswap.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.bswap.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.bswap.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.bswap.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.bswap.nvx8i64(<vscale x 8 x i64> undef)
@@ -69,37 +75,41 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %3 = call <4 x i8> @llvm.bitreverse.v4i8(<4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %4 = call <8 x i8> @llvm.bitreverse.v8i8(<8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %5 = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %6 = call <vscale x 2 x i8> @llvm.bitreverse.nxv2i8(<vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %7 = call <vscale x 4 x i8> @llvm.bitreverse.nxv4i8(<vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %8 = call <vscale x 8 x i8> @llvm.bitreverse.nxv8i8(<vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %9 = call <vscale x 16 x i8> @llvm.bitreverse.nxv16i8(<vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %10 = call i16 @llvm.bitreverse.i16(i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %11 = call <2 x i16> @llvm.bitreverse.v2i16(<2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %12 = call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %13 = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %14 = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %15 = call <vscale x 2 x i16> @llvm.bitreverse.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %16 = call <vscale x 4 x i16> @llvm.bitreverse.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %17 = call <vscale x 8 x i16> @llvm.bitreverse.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %18 = call <vscale x 16 x i16> @llvm.bitreverse.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %19 = call i32 @llvm.bitreverse.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %20 = call <2 x i32> @llvm.bitreverse.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %21 = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %22 = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %23 = call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %24 = call <vscale x 2 x i32> @llvm.bitreverse.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %25 = call <vscale x 4 x i32> @llvm.bitreverse.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %26 = call <vscale x 8 x i32> @llvm.bitreverse.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %27 = call <vscale x 16 x i32> @llvm.bitreverse.nxv16i32(<vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %28 = call i64 @llvm.bitreverse.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %29 = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %30 = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %31 = call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %32 = call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %33 = call <vscale x 2 x i64> @llvm.bitreverse.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %34 = call <vscale x 4 x i64> @llvm.bitreverse.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %35 = call <vscale x 8 x i64> @llvm.bitreverse.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %36 = call <vscale x 16 x i64> @llvm.bitreverse.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %6 = call <vscale x 1 x i8> @llvm.bitreverse.nxv1i8(<vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %7 = call <vscale x 2 x i8> @llvm.bitreverse.nxv2i8(<vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %8 = call <vscale x 4 x i8> @llvm.bitreverse.nxv4i8(<vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %9 = call <vscale x 8 x i8> @llvm.bitreverse.nxv8i8(<vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %10 = call <vscale x 16 x i8> @llvm.bitreverse.nxv16i8(<vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %11 = call i16 @llvm.bitreverse.i16(i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %12 = call <2 x i16> @llvm.bitreverse.v2i16(<2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %13 = call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %14 = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %15 = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %16 = call <vscale x 1 x i16> @llvm.bitreverse.nxv1i16(<vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %17 = call <vscale x 2 x i16> @llvm.bitreverse.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %18 = call <vscale x 4 x i16> @llvm.bitreverse.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %19 = call <vscale x 8 x i16> @llvm.bitreverse.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %20 = call <vscale x 16 x i16> @llvm.bitreverse.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %21 = call i32 @llvm.bitreverse.i32(i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %22 = call <2 x i32> @llvm.bitreverse.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %23 = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %24 = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %25 = call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %26 = call <vscale x 1 x i32> @llvm.bitreverse.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %27 = call <vscale x 2 x i32> @llvm.bitreverse.nxv2i32(<vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %28 = call <vscale x 4 x i32> @llvm.bitreverse.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %29 = call <vscale x 8 x i32> @llvm.bitreverse.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %30 = call <vscale x 16 x i32> @llvm.bitreverse.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %31 = call i64 @llvm.bitreverse.i64(i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %32 = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %33 = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %34 = call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %35 = call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %36 = call <vscale x 1 x i64> @llvm.bitreverse.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %37 = call <vscale x 2 x i64> @llvm.bitreverse.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %38 = call <vscale x 4 x i64> @llvm.bitreverse.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %39 = call <vscale x 8 x i64> @llvm.bitreverse.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %40 = call <vscale x 16 x i64> @llvm.bitreverse.nxv16i64(<vscale x 16 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.bitreverse.i8(i8 undef)
@@ -107,6 +117,7 @@
   call <4 x i8> @llvm.bitreverse.v4i8(<4 x i8> undef)
   call <8 x i8> @llvm.bitreverse.v8i8(<8 x i8> undef)
   call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.bitreverse.nvx1i8(<vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.bitreverse.nvx2i8(<vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.bitreverse.nvx4i8(<vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.bitreverse.nvx8i8(<vscale x 8 x i8> undef)
@@ -116,6 +127,7 @@
   call <4 x i16> @llvm.bitreverse.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.bitreverse.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.bitreverse.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.bitreverse.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.bitreverse.nvx8i16(<vscale x 8 x i16> undef)
@@ -125,6 +137,7 @@
   call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.bitreverse.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.bitreverse.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.bitreverse.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.bitreverse.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.bitreverse.nvx8i32(<vscale x 8 x i32> undef)
@@ -134,6 +147,7 @@
   call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.bitreverse.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.bitreverse.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.bitreverse.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.bitreverse.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.bitreverse.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.bitreverse.nvx8i64(<vscale x 8 x i64> undef)
@@ -148,37 +162,41 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %3 = call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %4 = call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %5 = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %6 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %8 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call i16 @llvm.ctpop.i16(i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %11 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %19 = call i32 @llvm.ctpop.i32(i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %20 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %21 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %28 = call i64 @llvm.ctpop.i64(i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %29 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %30 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %31 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %36 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %6 = call <vscale x 1 x i8> @llvm.ctpop.nxv1i8(<vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %7 = call <vscale x 2 x i8> @llvm.ctpop.nxv2i8(<vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %8 = call <vscale x 4 x i8> @llvm.ctpop.nxv4i8(<vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call <vscale x 8 x i8> @llvm.ctpop.nxv8i8(<vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %10 = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = call i16 @llvm.ctpop.i16(i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %12 = call <2 x i16> @llvm.ctpop.v2i16(<2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %13 = call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %14 = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %15 = call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %16 = call <vscale x 1 x i16> @llvm.ctpop.nxv1i16(<vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %17 = call <vscale x 2 x i16> @llvm.ctpop.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = call <vscale x 4 x i16> @llvm.ctpop.nxv4i16(<vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %19 = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %20 = call <vscale x 16 x i16> @llvm.ctpop.nxv16i16(<vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = call i32 @llvm.ctpop.i32(i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %22 = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %24 = call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %25 = call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %26 = call <vscale x 1 x i32> @llvm.ctpop.nxv1i32(<vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %27 = call <vscale x 2 x i32> @llvm.ctpop.nxv2i32(<vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %28 = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %29 = call <vscale x 8 x i32> @llvm.ctpop.nxv8i32(<vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %30 = call <vscale x 16 x i32> @llvm.ctpop.nxv16i32(<vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call i64 @llvm.ctpop.i64(i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %32 = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %33 = call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %34 = call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %35 = call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %36 = call <vscale x 1 x i64> @llvm.ctpop.nxv1i64(<vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %37 = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %38 = call <vscale x 4 x i64> @llvm.ctpop.nxv4i64(<vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %39 = call <vscale x 8 x i64> @llvm.ctpop.nxv8i64(<vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %40 = call <vscale x 16 x i64> @llvm.ctpop.nxv16i64(<vscale x 16 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.ctpop.i8(i8 undef)
@@ -186,6 +204,7 @@
   call <4 x i8> @llvm.ctpop.v4i8(<4 x i8> undef)
   call <8 x i8> @llvm.ctpop.v8i8(<8 x i8> undef)
   call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.ctpop.nvx1i8(<vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.ctpop.nvx2i8(<vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.ctpop.nvx4i8(<vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.ctpop.nvx8i8(<vscale x 8 x i8> undef)
@@ -195,6 +214,7 @@
   call <4 x i16> @llvm.ctpop.v4i16(<4 x i16> undef)
   call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> undef)
   call <16 x i16> @llvm.ctpop.v16i16(<16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.ctpop.nvx1i16(<vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.ctpop.nvx2i16(<vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.ctpop.nvx4i16(<vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.ctpop.nvx8i16(<vscale x 8 x i16> undef)
@@ -204,6 +224,7 @@
   call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> undef)
   call <8 x i32> @llvm.ctpop.v8i32(<8 x i32> undef)
   call <16 x i32> @llvm.ctpop.v16i32(<16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.ctpop.nvx1i32(<vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.ctpop.nvx2i32(<vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.ctpop.nvx4i32(<vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.ctpop.nvx8i32(<vscale x 8 x i32> undef)
@@ -213,6 +234,7 @@
   call <4 x i64> @llvm.ctpop.v4i64(<4 x i64> undef)
   call <8 x i64> @llvm.ctpop.v8i64(<8 x i64> undef)
   call <16 x i64> @llvm.ctpop.v16i64(<16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.ctpop.nvx1i64(<vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.ctpop.nvx2i64(<vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.ctpop.nvx4i64(<vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.ctpop.nvx8i64(<vscale x 8 x i64> undef)
@@ -226,6 +248,7 @@
 declare <4 x i16> @llvm.bswap.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.bswap.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.bswap.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.bswap.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.bswap.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.bswap.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.bswap.nvx8i16(<vscale x 8 x i16>)
@@ -235,6 +258,7 @@
 declare <4 x i32> @llvm.bswap.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.bswap.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.bswap.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.bswap.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.bswap.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.bswap.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.bswap.nvx8i32(<vscale x 8 x i32>)
@@ -244,6 +268,7 @@
 declare <4 x i64> @llvm.bswap.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.bswap.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.bswap.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.bswap.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.bswap.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.bswap.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.bswap.nvx8i64(<vscale x 8 x i64>)
@@ -254,6 +279,7 @@
 declare <4 x i8> @llvm.bitreverse.v4i8(<4 x i8>)
 declare <8 x i8> @llvm.bitreverse.v8i8(<8 x i8>)
 declare <16 x i8> @llvm.bitreverse.v16i8(<16 x i8>)
+declare <vscale x 1 x i8> @llvm.bitreverse.nvx1i8(<vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.bitreverse.nvx2i8(<vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.bitreverse.nvx4i8(<vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.bitreverse.nvx8i8(<vscale x 8 x i8>)
@@ -263,6 +289,7 @@
 declare <4 x i16> @llvm.bitreverse.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.bitreverse.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.bitreverse.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.bitreverse.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.bitreverse.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.bitreverse.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.bitreverse.nvx8i16(<vscale x 8 x i16>)
@@ -272,6 +299,7 @@
 declare <4 x i32> @llvm.bitreverse.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.bitreverse.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.bitreverse.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.bitreverse.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.bitreverse.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.bitreverse.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.bitreverse.nvx8i32(<vscale x 8 x i32>)
@@ -281,6 +309,7 @@
 declare <4 x i64> @llvm.bitreverse.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.bitreverse.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.bitreverse.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.bitreverse.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.bitreverse.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.bitreverse.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.bitreverse.nvx8i64(<vscale x 8 x i64>)
@@ -291,6 +320,7 @@
 declare <4 x i8> @llvm.ctpop.v4i8(<4 x i8>)
 declare <8 x i8> @llvm.ctpop.v8i8(<8 x i8>)
 declare <16 x i8> @llvm.ctpop.v16i8(<16 x i8>)
+declare <vscale x 1 x i8> @llvm.ctpop.nvx1i8(<vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.ctpop.nvx2i8(<vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.ctpop.nvx4i8(<vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.ctpop.nvx8i8(<vscale x 8 x i8>)
@@ -300,6 +330,7 @@
 declare <4 x i16> @llvm.ctpop.v4i16(<4 x i16>)
 declare <8 x i16> @llvm.ctpop.v8i16(<8 x i16>)
 declare <16 x i16> @llvm.ctpop.v16i16(<16 x i16>)
+declare <vscale x 1 x i16> @llvm.ctpop.nvx1i16(<vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.ctpop.nvx2i16(<vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.ctpop.nvx4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.ctpop.nvx8i16(<vscale x 8 x i16>)
@@ -309,6 +340,7 @@
 declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>)
 declare <8 x i32> @llvm.ctpop.v8i32(<8 x i32>)
 declare <16 x i32> @llvm.ctpop.v16i32(<16 x i32>)
+declare <vscale x 1 x i32> @llvm.ctpop.nvx1i32(<vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.ctpop.nvx2i32(<vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.ctpop.nvx4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.ctpop.nvx8i32(<vscale x 8 x i32>)
@@ -318,6 +350,7 @@
 declare <4 x i64> @llvm.ctpop.v4i64(<4 x i64>)
 declare <8 x i64> @llvm.ctpop.v8i64(<8 x i64>)
 declare <16 x i64> @llvm.ctpop.v16i64(<16 x i64>)
+declare <vscale x 1 x i64> @llvm.ctpop.nvx1i64(<vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.ctpop.nvx2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.ctpop.nvx4i64(<vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.ctpop.nvx8i64(<vscale x 8 x i64>)
diff --git a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
--- a/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/int-min-max.ll
@@ -8,36 +8,40 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i8> @llvm.smax.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.smax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.smax.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.smax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.smax.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.smax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.smax.i8(i8 undef, i8 undef)
@@ -45,6 +49,7 @@
   call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
   call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
   call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.smax.nvx1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.smax.nvx2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.smax.nvx4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.smax.nvx8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
@@ -54,6 +59,7 @@
   call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
   call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
   call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.smax.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.smax.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.smax.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.smax.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
@@ -63,6 +69,7 @@
   call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
   call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
   call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.smax.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.smax.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.smax.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.smax.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -72,6 +79,7 @@
   call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
   call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
   call <16 x i64> @llvm.smax.v16i64(<16 x i64> undef, <16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.smax.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.smax.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.smax.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.smax.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
@@ -85,36 +93,40 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i8> @llvm.smin.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.smin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.smin.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.smin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.smin.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.smin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.smin.i8(i8 undef, i8 undef)
@@ -122,6 +134,7 @@
   call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
   call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
   call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.smin.nvx1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.smin.nvx2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.smin.nvx4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.smin.nvx8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
@@ -131,6 +144,7 @@
   call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
   call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
   call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.smin.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.smin.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.smin.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.smin.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
@@ -140,6 +154,7 @@
   call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
   call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
   call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.smin.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.smin.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.smin.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.smin.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -149,6 +164,7 @@
   call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
   call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
   call <16 x i64> @llvm.smin.v16i64(<16 x i64> undef, <16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.smin.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.smin.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.smin.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.smin.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
@@ -162,36 +178,40 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i8> @llvm.umax.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.umax.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.umax.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.umax.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.umax.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.umax.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.umax.i8(i8 undef, i8 undef)
@@ -199,6 +219,7 @@
   call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
   call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
   call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.umax.nvx1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.umax.nvx2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.umax.nvx4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.umax.nvx8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
@@ -208,6 +229,7 @@
   call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
   call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
   call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.umax.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.umax.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.umax.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.umax.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
@@ -217,6 +239,7 @@
   call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
   call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
   call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.umax.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.umax.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.umax.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.umax.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -226,6 +249,7 @@
   call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
   call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
   call <16 x i64> @llvm.umax.v16i64(<16 x i64> undef, <16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.umax.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.umax.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.umax.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.umax.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
@@ -239,36 +263,40 @@
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 1 x i8> @llvm.umin.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 2 x i8> @llvm.umin.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x i16> @llvm.umin.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 16 x i32> @llvm.umin.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %31 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %33 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %34 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %35 = call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 1 x i64> @llvm.umin.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %39 = call <vscale x 8 x i64> @llvm.umin.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   call i8 @llvm.umin.i8(i8 undef, i8 undef)
@@ -276,6 +304,7 @@
   call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
   call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
   call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+  call <vscale x 1 x i8> @llvm.umin.nvx1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef)
   call <vscale x 2 x i8> @llvm.umin.nvx2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef)
   call <vscale x 4 x i8> @llvm.umin.nvx4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
   call <vscale x 8 x i8> @llvm.umin.nvx8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
@@ -285,6 +314,7 @@
   call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
   call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
   call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+  call <vscale x 1 x i16> @llvm.umin.nvx1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef)
   call <vscale x 2 x i16> @llvm.umin.nvx2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
   call <vscale x 4 x i16> @llvm.umin.nvx4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
   call <vscale x 8 x i16> @llvm.umin.nvx8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
@@ -294,6 +324,7 @@
   call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
   call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
   call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+  call <vscale x 1 x i32> @llvm.umin.nvx1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
   call <vscale x 2 x i32> @llvm.umin.nvx2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
   call <vscale x 4 x i32> @llvm.umin.nvx4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
   call <vscale x 8 x i32> @llvm.umin.nvx8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
@@ -303,6 +334,7 @@
   call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
   call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
   call <16 x i64> @llvm.umin.v16i64(<16 x i64> undef, <16 x i64> undef)
+  call <vscale x 1 x i64> @llvm.umin.nvx1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef)
   call <vscale x 2 x i64> @llvm.umin.nvx2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
   call <vscale x 4 x i64> @llvm.umin.nvx4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
   call <vscale x 8 x i64> @llvm.umin.nvx8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef)
@@ -314,6 +346,7 @@
 declare <4 x i8> @llvm.smax.v4i8(<4 x i8>, <4 x i8>)
 declare <8 x i8> @llvm.smax.v8i8(<8 x i8>, <8 x i8>)
 declare <16 x i8> @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
+declare <vscale x 1 x i8> @llvm.smax.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.smax.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.smax.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.smax.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
@@ -323,6 +356,7 @@
 declare <4 x i16> @llvm.smax.v4i16(<4 x i16>, <4 x i16>)
 declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
 declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
+declare <vscale x 1 x i16> @llvm.smax.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.smax.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.smax.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.smax.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
@@ -332,6 +366,7 @@
 declare <4 x i32> @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
 declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
 declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
+declare <vscale x 1 x i32> @llvm.smax.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.smax.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.smax.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.smax.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
@@ -341,6 +376,7 @@
 declare <4 x i64> @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
 declare <8 x i64> @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
 declare <16 x i64> @llvm.smax.v16i64(<16 x i64>, <16 x i64>)
+declare <vscale x 1 x i64> @llvm.smax.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.smax.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.smax.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.smax.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i64>)
@@ -350,6 +386,7 @@
 declare <4 x i8> @llvm.smin.v4i8(<4 x i8>, <4 x i8>)
 declare <8 x i8> @llvm.smin.v8i8(<8 x i8>, <8 x i8>)
 declare <16 x i8> @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
+declare <vscale x 1 x i8> @llvm.smin.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.smin.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.smin.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.smin.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
@@ -359,6 +396,7 @@
 declare <4 x i16> @llvm.smin.v4i16(<4 x i16>, <4 x i16>)
 declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
 declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
+declare <vscale x 1 x i16> @llvm.smin.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.smin.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.smin.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.smin.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
@@ -368,6 +406,7 @@
 declare <4 x i32> @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
 declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
 declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
+declare <vscale x 1 x i32> @llvm.smin.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.smin.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.smin.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.smin.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
@@ -377,6 +416,7 @@
 declare <4 x i64> @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
 declare <8 x i64> @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
 declare <16 x i64> @llvm.smin.v16i64(<16 x i64>, <16 x i64>)
+declare <vscale x 1 x i64> @llvm.smin.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.smin.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.smin.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.smin.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i64>)
@@ -386,6 +426,7 @@
 declare <4 x i8> @llvm.umax.v4i8(<4 x i8>, <4 x i8>)
 declare <8 x i8> @llvm.umax.v8i8(<8 x i8>, <8 x i8>)
 declare <16 x i8> @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
+declare <vscale x 1 x i8> @llvm.umax.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.umax.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.umax.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.umax.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
@@ -395,6 +436,7 @@
 declare <4 x i16> @llvm.umax.v4i16(<4 x i16>, <4 x i16>)
 declare <8 x i16> @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
 declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
+declare <vscale x 1 x i16> @llvm.umax.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.umax.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.umax.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.umax.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
@@ -404,6 +446,7 @@
 declare <4 x i32> @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
 declare <8 x i32> @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
 declare <16 x i32> @llvm.umax.v16i32(<16 x i32>, <16 x i32>)
+declare <vscale x 1 x i32> @llvm.umax.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.umax.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.umax.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.umax.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
@@ -413,6 +456,7 @@
 declare <4 x i64> @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
 declare <8 x i64> @llvm.umax.v8i64(<8 x i64>, <8 x i64>)
 declare <16 x i64> @llvm.umax.v16i64(<16 x i64>, <16 x i64>)
+declare <vscale x 1 x i64> @llvm.umax.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.umax.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.umax.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.umax.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i64>)
@@ -422,6 +466,7 @@
 declare <4 x i8> @llvm.umin.v4i8(<4 x i8>, <4 x i8>)
 declare <8 x i8> @llvm.umin.v8i8(<8 x i8>, <8 x i8>)
 declare <16 x i8> @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
+declare <vscale x 1 x i8> @llvm.umin.nvx1i8(<vscale x 1 x i8>, <vscale x 1 x i8>)
 declare <vscale x 2 x i8> @llvm.umin.nvx2i8(<vscale x 2 x i8>, <vscale x 2 x i8>)
 declare <vscale x 4 x i8> @llvm.umin.nvx4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
 declare <vscale x 8 x i8> @llvm.umin.nvx8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
@@ -431,6 +476,7 @@
 declare <4 x i16> @llvm.umin.v4i16(<4 x i16>, <4 x i16>)
 declare <8 x i16> @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
 declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
+declare <vscale x 1 x i16> @llvm.umin.nvx1i16(<vscale x 1 x i16>, <vscale x 1 x i16>)
 declare <vscale x 2 x i16> @llvm.umin.nvx2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
 declare <vscale x 4 x i16> @llvm.umin.nvx4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.umin.nvx8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
@@ -440,6 +486,7 @@
 declare <4 x i32> @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
 declare <8 x i32> @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
 declare <16 x i32> @llvm.umin.v16i32(<16 x i32>, <16 x i32>)
+declare <vscale x 1 x i32> @llvm.umin.nvx1i32(<vscale x 1 x i32>, <vscale x 1 x i32>)
 declare <vscale x 2 x i32> @llvm.umin.nvx2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
 declare <vscale x 4 x i32> @llvm.umin.nvx4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.umin.nvx8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
@@ -449,6 +496,7 @@
 declare <4 x i64> @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
 declare <8 x i64> @llvm.umin.v8i64(<8 x i64>, <8 x i64>)
 declare <16 x i64> @llvm.umin.v16i64(<16 x i64>, <16 x i64>)
+declare <vscale x 1 x i64> @llvm.umin.nvx1i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
 declare <vscale x 2 x i64> @llvm.umin.nvx2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.umin.nvx4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
 declare <vscale x 8 x i64> @llvm.umin.nvx8i64(<vscale x 8 x i64>, <vscale x 8 x i64>)