diff --git a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef-scalable.ll
@@ -0,0 +1,407 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -vector-library=sleefgnuabi -replace-with-veclib -S < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+; NOTE: The existing TLI mappings are not used since the -replace-with-veclib pass is broken for scalable vectors.
+
+define <vscale x 2 x double> @llvm_ceil_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_ceil_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_ceil_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_ceil_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_copysign_vscale_f64(<vscale x 2 x double> %mag, <vscale x 2 x double> %sgn) {
+; CHECK-LABEL: @llvm_copysign_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> [[MAG:%.*]], <vscale x 2 x double> [[SGN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double> %mag, <vscale x 2 x double> %sgn)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_copysign_vscale_f32(<vscale x 4 x float> %mag, <vscale x 4 x float> %sgn) {
+; CHECK-LABEL: @llvm_copysign_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> [[MAG:%.*]], <vscale x 4 x float> [[SGN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float> %mag, <vscale x 4 x float> %sgn)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_cos_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_cos_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_cos_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_cos_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_exp_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_exp_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_exp_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_exp_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_exp2_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_exp2_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_exp2_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_exp2_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_fabs_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_fabs_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_fabs_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_fabs_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_floor_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_floor_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_floor_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_floor_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_fma_vscale_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c ) {
+; CHECK-LABEL: @llvm_fma_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.fma.nxv2f64(<vscale x 2 x double> [[A:%.*]], <vscale x 2 x double> [[B:%.*]], <vscale x 2 x double> [[C:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.fma.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_fma_vscale_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
+; CHECK-LABEL: @llvm_fma_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.fma.nxv4f32(<vscale x 4 x float> [[A:%.*]], <vscale x 4 x float> [[B:%.*]], <vscale x 4 x float> [[C:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.fma.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_log_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_log_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_log_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_log_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_log2_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_log2_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_log2_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_log2_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_log10_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_log10_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_log10_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_log10_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_maxnum_vscale_f64(<vscale x 2 x double> %in0, <vscale x 2 x double> %in1) {
+; CHECK-LABEL: @llvm_maxnum_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> [[IN0:%.*]], <vscale x 2 x double> [[IN1:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> %in0, <vscale x 2 x double> %in1)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_maxnum_vscale_f32(<vscale x 4 x float> %in0, <vscale x 4 x float> %in1) {
+; CHECK-LABEL: @llvm_maxnum_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> [[IN0:%.*]], <vscale x 4 x float> [[IN1:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> %in0, <vscale x 4 x float> %in1)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_minnum_vscale_f64(<vscale x 2 x double> %in0, <vscale x 2 x double> %in1) {
+; CHECK-LABEL: @llvm_minnum_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> [[IN0:%.*]], <vscale x 2 x double> [[IN1:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> %in0, <vscale x 2 x double> %in1)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_minnum_vscale_f32(<vscale x 4 x float> %in0, <vscale x 4 x float> %in1) {
+; CHECK-LABEL: @llvm_minnum_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> [[IN0:%.*]], <vscale x 4 x float> [[IN1:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> %in0, <vscale x 4 x float> %in1)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_nearbyint_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_nearbyint_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_nearbyint_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_nearbyint_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_pow_vscale_f64(<vscale x 2 x double> %in, <vscale x 2 x double> %pow) {
+; CHECK-LABEL: @llvm_pow_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> [[IN:%.*]], <vscale x 2 x double> [[POW:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double> %in, <vscale x 2 x double> %pow)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_pow_vscale_f32(<vscale x 4 x float> %in, <vscale x 4 x float> %pow) {
+; CHECK-LABEL: @llvm_pow_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> [[IN:%.*]], <vscale x 4 x float> [[POW:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %in, <vscale x 4 x float> %pow)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_rint_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_rint_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_rint_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_rint_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_round_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_round_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_round_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_round_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_sin_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_sin_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_sin_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_sin_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_sqrt_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_sqrt_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_sqrt_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_sqrt_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 2 x double> @llvm_trunc_vscale_f64(<vscale x 2 x double> %in) {
+; CHECK-LABEL: @llvm_trunc_vscale_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+;
+  %1 = call fast <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> %in)
+  ret <vscale x 2 x double> %1
+}
+
+define <vscale x 4 x float> @llvm_trunc_vscale_f32(<vscale x 4 x float> %in) {
+; CHECK-LABEL: @llvm_trunc_vscale_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+;
+  %1 = call fast <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> %in)
+  ret <vscale x 4 x float> %1
+}
+
+declare <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.copysign.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.copysign.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.cos.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.exp.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.exp2.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.fma.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.fma.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.log.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.log2.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.log10.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.pow.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.sin.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double>)
+declare <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float>)
diff --git a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef.ll b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sleef.ll
@@ -0,0 +1,405 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -vector-library=sleefgnuabi -replace-with-veclib -S < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+define <2 x double> @llvm_ceil_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_ceil_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.ceil.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.ceil.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_ceil_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_ceil_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.ceil.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.ceil.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_copysign_f64(<2 x double> %mag, <2 x double> %sgn) {
+; CHECK-LABEL: @llvm_copysign_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.copysign.v2f64(<2 x double> [[MAG:%.*]], <2 x double> [[SGN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.copysign.v2f64(<2 x double> %mag, <2 x double> %sgn)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_copysign_f32(<4 x float> %mag, <4 x float> %sgn) {
+; CHECK-LABEL: @llvm_copysign_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.copysign.v4f32(<4 x float> [[MAG:%.*]], <4 x float> [[SGN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.copysign.v4f32(<4 x float> %mag, <4 x float> %sgn)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_cos_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_cos_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_cos(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.cos.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_cos_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_cos_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_cosf(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.cos.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_exp_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_exp_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_exp(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.exp.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_exp_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_exp_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_expf(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.exp.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_exp2_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_exp2_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_exp2(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.exp2.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_exp2_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_exp2_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_exp2f(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.exp2.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_fabs_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_fabs_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.fabs.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.fabs.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_fabs_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_fabs_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_floor_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_floor_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.floor.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.floor.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_floor_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_floor_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.floor.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.floor.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_fma_f64(<2 x double> %a, <2 x double> %b, <2 x double> %c ) {
+; CHECK-LABEL: @llvm_fma_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.fma.v2f64(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_fma_f32(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
+; CHECK-LABEL: @llvm_fma_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fma.v4f32(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_log_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_log_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_log(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.log.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_log_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_log_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_logf(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.log.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_log2_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_log2_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_log2(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.log2.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_log2_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_log2_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_log2f(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.log2.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_log10_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_log10_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_log10(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.log10.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_log10_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_log10_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_log10f(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.log10.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_maxnum_f64(<2 x double> %in0, <2 x double> %in1) {
+; CHECK-LABEL: @llvm_maxnum_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.maxnum.v2f64(<2 x double> [[IN0:%.*]], <2 x double> [[IN1:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.maxnum.v2f64(<2 x double> %in0, <2 x double> %in1)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_maxnum_f32(<4 x float> %in0, <4 x float> %in1) {
+; CHECK-LABEL: @llvm_maxnum_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.maxnum.v4f32(<4 x float> [[IN0:%.*]], <4 x float> [[IN1:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.maxnum.v4f32(<4 x float> %in0, <4 x float> %in1)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_minnum_f64(<2 x double> %in0, <2 x double> %in1) {
+; CHECK-LABEL: @llvm_minnum_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.minnum.v2f64(<2 x double> [[IN0:%.*]], <2 x double> [[IN1:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.minnum.v2f64(<2 x double> %in0, <2 x double> %in1)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_minnum_f32(<4 x float> %in0, <4 x float> %in1) {
+; CHECK-LABEL: @llvm_minnum_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.minnum.v4f32(<4 x float> [[IN0:%.*]], <4 x float> [[IN1:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.minnum.v4f32(<4 x float> %in0, <4 x float> %in1)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_nearbyint_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_nearbyint_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.nearbyint.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.nearbyint.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_nearbyint_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_nearbyint_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.nearbyint.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.nearbyint.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_pow_f64(<2 x double> %in, <2 x double> %pow) {
+; CHECK-LABEL: @llvm_pow_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.pow.v2f64(<2 x double> [[IN:%.*]], <2 x double> [[POW:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %in, <2 x double> %pow)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_pow_f32(<4 x float> %in, <4 x float> %pow) {
+; CHECK-LABEL: @llvm_pow_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.pow.v4f32(<4 x float> [[IN:%.*]], <4 x float> [[POW:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %in, <4 x float> %pow)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_rint_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_rint_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.rint.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.rint.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_rint_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_rint_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.rint.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.rint.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_round_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_round_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.round.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.round.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_round_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_round_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.round.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.round.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_sin_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_sin_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @_ZGVnN2v_sin(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.sin.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_sin_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_sin_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @_ZGVnN4v_sinf(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.sin.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_sqrt_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_sqrt_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_sqrt_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_sqrt_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+define <2 x double> @llvm_trunc_f64(<2 x double> %in) {
+; CHECK-LABEL: @llvm_trunc_f64(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.trunc.v2f64(<2 x double> [[IN:%.*]])
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
+;
+  %1 = call fast <2 x double> @llvm.trunc.v2f64(<2 x double> %in)
+  ret <2 x double> %1
+}
+
+define <4 x float> @llvm_trunc_f32(<4 x float> %in) {
+; CHECK-LABEL: @llvm_trunc_f32(
+; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.trunc.v4f32(<4 x float> [[IN:%.*]])
+; CHECK-NEXT:    ret <4 x float> [[TMP1]]
+;
+  %1 = call fast <4 x float> @llvm.trunc.v4f32(<4 x float> %in)
+  ret <4 x float> %1
+}
+
+declare <2 x double> @llvm.ceil.v2f64(<2 x double>)
+declare <4 x float> @llvm.ceil.v4f32(<4 x float>)
+declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
+declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
+declare <2 x double> @llvm.cos.v2f64(<2 x double>)
+declare <4 x float> @llvm.cos.v4f32(<4 x float>)
+declare <2 x double> @llvm.exp.v2f64(<2 x double>)
+declare <4 x float> @llvm.exp.v4f32(<4 x float>)
+declare <2 x double> @llvm.exp2.v2f64(<2 x double>)
+declare <4 x float> @llvm.exp2.v4f32(<4 x float>)
+declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
+declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
+declare <2 x double> @llvm.floor.v2f64(<2 x double>)
+declare <4 x float> @llvm.floor.v4f32(<4 x float>)
+declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
+declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
+declare <2 x double> @llvm.log.v2f64(<2 x double>)
+declare <4 x float> @llvm.log.v4f32(<4 x float>)
+declare <2 x double> @llvm.log2.v2f64(<2 x double>)
+declare <4 x float> @llvm.log2.v4f32(<4 x float>)
+declare <2 x double> @llvm.log10.v2f64(<2 x double>)
+declare <4 x float> @llvm.log10.v4f32(<4 x float>)
+declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
+declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
+declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
+declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
+declare <2 x double> @llvm.nearbyint.v2f64(<2 x double>)
+declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>)
+declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>)
+declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>)
+declare <2 x double> @llvm.rint.v2f64(<2 x double>)
+declare <4 x float> @llvm.rint.v4f32(<4 x float>)
+declare <2 x double> @llvm.round.v2f64(<2 x double>)
+declare <4 x float> @llvm.round.v4f32(<4 x float>)
+declare <2 x double> @llvm.sin.v2f64(<2 x double>)
+declare <4 x float> @llvm.sin.v4f32(<4 x float>)
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
+declare <2 x double> @llvm.trunc.v2f64(<2 x double>)
+declare <4 x float> @llvm.trunc.v4f32(<4 x float>)
diff --git a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sqrt.ll b/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sqrt.ll
deleted file mode 100644
--- a/llvm/test/CodeGen/AArch64/replace-intrinsics-with-veclib-sqrt.ll
+++ /dev/null
@@ -1,50 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -vector-library=sleefgnuabi -replace-with-veclib -S < %s | FileCheck %s
-
-target triple = "aarch64-unknown-linux-gnu"
-
-define <2 x double> @llvm_sqrt_f64(<2 x double> %in) {
-; CHECK-LABEL: define {{[^@]+}}@llvm_sqrt_f64
-; CHECK-SAME: (<2 x double> [[IN:%.*]]) {
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> [[IN]])
-; CHECK-NEXT:    ret <2 x double> [[TMP1]]
-;
-  %1 = call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %in)
-  ret <2 x double> %1
-}
-
-define <4 x float> @llvm_sqrt_f32(<4 x float> %in) {
-; CHECK-LABEL: define {{[^@]+}}@llvm_sqrt_f32
-; CHECK-SAME: (<4 x float> [[IN:%.*]]) {
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> [[IN]])
-; CHECK-NEXT:    ret <4 x float> [[TMP1]]
-;
-  %1 = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %in)
-  ret <4 x float> %1
-}
-
-define <vscale x 2 x double> @llvm_sqrt_vscale_f64(<vscale x 2 x double> %in) {
-; CHECK-LABEL: define {{[^@]+}}@llvm_sqrt_vscale_f64
-; CHECK-SAME: (<vscale x 2 x double> [[IN:%.*]]) {
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> [[IN]])
-; CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
-;
-  %1 = call fast <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> %in)
-  ret <vscale x 2 x double> %1
-}
-
-define <vscale x 4 x float> @llvm_sqrt_vscale_f32(<vscale x 4 x float> %in) {
-; CHECK-LABEL: define {{[^@]+}}@llvm_sqrt_vscale_f32
-; CHECK-SAME: (<vscale x 4 x float> [[IN:%.*]]) {
-; CHECK-NEXT:    [[TMP1:%.*]] = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> [[IN]])
-; CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
-;
-  %1 = call fast <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> %in)
-  ret <vscale x 4 x float> %1
-}
-
-
-declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
-declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
-declare <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double>)
-declare <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float>)