[llvm-branch-commits] [llvm] PR for llvm/llvm-project#80296 (PR #80408)

via llvm-branch-commits llvm-branch-commits at lists.llvm.org
Fri Feb 2 01:00:03 PST 2024


https://github.com/llvmbot created https://github.com/llvm/llvm-project/pull/80408

resolves llvm/llvm-project#80296

>From 587074398c9a0e1d4932452261d9c26a57a62289 Mon Sep 17 00:00:00 2001
From: Maciej Gabka <maciej.gabka at arm.com>
Date: Fri, 2 Feb 2024 08:42:29 +0000
Subject: [PATCH] [TLI][AArch64] Adjust TLI mappings to vector functions taking
 linear pointers (#80296)

The masked symbols in SLEEF are incorrectly implemented as calls to non
masked variants, what only works fine for functions which do not modify
memory.
For vector variants which modify memory we can only use a non masked
symbols for now.
The SVE ArmPL mappings need to be removed for now as well.

(cherry picked from commit 0f26441cb83c1dea9aef12c748a79e3f38e3230a)
---
 llvm/include/llvm/Analysis/VecFuncs.def       |  18 +-
 .../AArch64/veclib-function-calls.ll          | 890 +++++++++++++++++-
 llvm/test/Transforms/Util/add-TLI-mappings.ll |  68 +-
 3 files changed, 905 insertions(+), 71 deletions(-)

diff --git a/llvm/include/llvm/Analysis/VecFuncs.def b/llvm/include/llvm/Analysis/VecFuncs.def
index f09e12f3038ca..07edf68c667a2 100644
--- a/llvm/include/llvm/Analysis/VecFuncs.def
+++ b/llvm/include/llvm/Analysis/VecFuncs.def
@@ -771,8 +771,8 @@ TLI_DEFINE_VECFUNC("log2f", "_ZGVsMxv_log2f", SCALABLE(4), MASKED, "_ZGVsMxv")
 TLI_DEFINE_VECFUNC("llvm.log2.f64", "_ZGVsMxv_log2", SCALABLE(2), MASKED, "_ZGVsMxv")
 TLI_DEFINE_VECFUNC("llvm.log2.f32", "_ZGVsMxv_log2f", SCALABLE(4), MASKED, "_ZGVsMxv")
 
-TLI_DEFINE_VECFUNC("modf", "_ZGVsMxvl8_modf", SCALABLE(2), MASKED, "_ZGVsMxvl8")
-TLI_DEFINE_VECFUNC("modff", "_ZGVsMxvl4_modff", SCALABLE(4), MASKED, "_ZGVsMxvl4")
+TLI_DEFINE_VECFUNC("modf", "_ZGVsNxvl8_modf", SCALABLE(2), NOMASK, "_ZGVsNxvl8")
+TLI_DEFINE_VECFUNC("modff", "_ZGVsNxvl4_modff", SCALABLE(4), NOMASK, "_ZGVsNxvl4")
 
 TLI_DEFINE_VECFUNC("nextafter", "_ZGVsMxvv_nextafter", SCALABLE(2), MASKED, "_ZGVsMxvv")
 TLI_DEFINE_VECFUNC("nextafterf", "_ZGVsMxvv_nextafterf", SCALABLE(4), MASKED, "_ZGVsMxvv")
@@ -787,11 +787,11 @@ TLI_DEFINE_VECFUNC("sinf", "_ZGVsMxv_sinf", SCALABLE(4), MASKED, "_ZGVsMxv")
 TLI_DEFINE_VECFUNC("llvm.sin.f64", "_ZGVsMxv_sin", SCALABLE(2), MASKED, "_ZGVsMxv")
 TLI_DEFINE_VECFUNC("llvm.sin.f32", "_ZGVsMxv_sinf", SCALABLE(4), MASKED, "_ZGVsMxv")
 
-TLI_DEFINE_VECFUNC("sincos", "_ZGVsMxvl8l8_sincos", SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincosf", "_ZGVsMxvl4l4_sincosf", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
+TLI_DEFINE_VECFUNC("sincos", "_ZGVsNxvl8l8_sincos", SCALABLE(2), NOMASK, "_ZGVsNxvl8l8")
+TLI_DEFINE_VECFUNC("sincosf", "_ZGVsNxvl4l4_sincosf", SCALABLE(4), NOMASK, "_ZGVsNxvl4l4")
 
-TLI_DEFINE_VECFUNC("sincospi", "_ZGVsMxvl8l8_sincospi", SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincospif", "_ZGVsMxvl4l4_sincospif", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
+TLI_DEFINE_VECFUNC("sincospi", "_ZGVsNxvl8l8_sincospi", SCALABLE(2), NOMASK, "_ZGVsNxvl8l8")
+TLI_DEFINE_VECFUNC("sincospif", "_ZGVsNxvl4l4_sincospif", SCALABLE(4), NOMASK, "_ZGVsNxvl4l4")
 
 TLI_DEFINE_VECFUNC("sinh", "_ZGVsMxv_sinh",  SCALABLE(2), MASKED, "_ZGVsMxv")
 TLI_DEFINE_VECFUNC("sinhf", "_ZGVsMxv_sinhf", SCALABLE(4), MASKED, "_ZGVsMxv")
@@ -1005,8 +1005,6 @@ TLI_DEFINE_VECFUNC("llvm.log2.f32", "armpl_svlog2_f32_x", SCALABLE(4), MASKED, "
 
 TLI_DEFINE_VECFUNC("modf", "armpl_vmodfq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8")
 TLI_DEFINE_VECFUNC("modff", "armpl_vmodfq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4")
-TLI_DEFINE_VECFUNC("modf", "armpl_svmodf_f64_x",  SCALABLE(2), MASKED, "_ZGVsMxvl8")
-TLI_DEFINE_VECFUNC("modff", "armpl_svmodf_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4")
 
 TLI_DEFINE_VECFUNC("nextafter", "armpl_vnextafterq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vv")
 TLI_DEFINE_VECFUNC("nextafterf", "armpl_vnextafterq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vv")
@@ -1035,13 +1033,9 @@ TLI_DEFINE_VECFUNC("llvm.sin.f32", "armpl_svsin_f32_x", SCALABLE(4), MASKED, "_Z
 
 TLI_DEFINE_VECFUNC("sincos", "armpl_vsincosq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8l8")
 TLI_DEFINE_VECFUNC("sincosf", "armpl_vsincosq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4l4")
-TLI_DEFINE_VECFUNC("sincos", "armpl_svsincos_f64_x",  SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincosf", "armpl_svsincos_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
 
 TLI_DEFINE_VECFUNC("sincospi", "armpl_vsincospiq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2vl8l8")
 TLI_DEFINE_VECFUNC("sincospif", "armpl_vsincospiq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4vl4l4")
-TLI_DEFINE_VECFUNC("sincospi", "armpl_svsincospi_f64_x", SCALABLE(2), MASKED, "_ZGVsMxvl8l8")
-TLI_DEFINE_VECFUNC("sincospif", "armpl_svsincospi_f32_x", SCALABLE(4), MASKED, "_ZGVsMxvl4l4")
 
 TLI_DEFINE_VECFUNC("sinh", "armpl_vsinhq_f64", FIXED(2), NOMASK, "_ZGV_LLVM_N2v")
 TLI_DEFINE_VECFUNC("sinhf", "armpl_vsinhq_f32", FIXED(4), NOMASK, "_ZGV_LLVM_N4v")
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
index d07f72792e6b9..dd1495626eb98 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/veclib-function-calls.ll
@@ -1,8 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "call.*(cos|sin|tan|cbrt|erf|exp[^e]|gamma|log|sqrt|copysign|dim|min|mod|hypot|nextafter|pow|fma)" --version 2
-; RUN: opt -mattr=+neon -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=SLEEF-NEON
-; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s | FileCheck %s --check-prefix=SLEEF-SVE
-; RUN: opt -mattr=+neon -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s --check-prefix=ARMPL-NEON
-; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s | FileCheck %s --check-prefix=ARMPL-SVE
+; RUN: opt -mattr=+neon -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s -check-prefix=SLEEF-NEON
+; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s | FileCheck %s -check-prefix=SLEEF-SVE
+; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s -check-prefixes=SLEEF-SVE-NOPRED
+; RUN: opt -mattr=+neon -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s -check-prefix=ARMPL-NEON
+; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S < %s | FileCheck %s -check-prefix=ARMPL-SVE
+; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=inject-tli-mappings,loop-vectorize,simplifycfg -force-vector-interleave=1 -S < %s | FileCheck %s -check-prefixes=ARMPL-SVE-NOPRED
+
+
 
 target triple = "aarch64-unknown-linux-gnu"
 
@@ -23,6 +27,11 @@ define void @acos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @acos_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @acos(double [[IN:%.*]]) #[[ATTR2:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @acos_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vacosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -30,6 +39,11 @@ define void @acos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @acos_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @acos_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svacos_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @acos(double [[IN:%.*]]) #[[ATTR2:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -58,6 +72,11 @@ define void @acos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @acos_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @acosf(float [[IN:%.*]]) #[[ATTR3:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @acos_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vacosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -65,6 +84,11 @@ define void @acos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @acos_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @acos_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svacos_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @acosf(float [[IN:%.*]]) #[[ATTR3:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -96,6 +120,11 @@ define void @acosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @acosh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_acosh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @acosh(double [[IN:%.*]]) #[[ATTR4:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @acosh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vacoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -103,6 +132,11 @@ define void @acosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @acosh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @acosh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svacosh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @acosh(double [[IN:%.*]]) #[[ATTR4:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -131,6 +165,11 @@ define void @acosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @acosh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_acoshf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @acoshf(float [[IN:%.*]]) #[[ATTR5:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @acosh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vacoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -138,6 +177,11 @@ define void @acosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @acosh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @acosh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svacosh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @acoshf(float [[IN:%.*]]) #[[ATTR5:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -169,6 +213,11 @@ define void @asin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @asin_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asin(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @asin(double [[IN:%.*]]) #[[ATTR6:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @asin_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vasinq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -176,6 +225,11 @@ define void @asin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @asin_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @asin_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svasin_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @asin(double [[IN:%.*]]) #[[ATTR6:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -204,6 +258,11 @@ define void @asin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @asin_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @asinf(float [[IN:%.*]]) #[[ATTR7:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @asin_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vasinq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -211,6 +270,11 @@ define void @asin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @asin_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @asin_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svasin_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @asinf(float [[IN:%.*]]) #[[ATTR7:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -242,6 +306,11 @@ define void @asinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @asinh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_asinh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @asinh(double [[IN:%.*]]) #[[ATTR8:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @asinh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vasinhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -249,6 +318,11 @@ define void @asinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @asinh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svasinh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @asinh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svasinh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @asinh(double [[IN:%.*]]) #[[ATTR8:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -277,6 +351,11 @@ define void @asinh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinhf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @asinh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_asinhf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @asinhf(float [[IN:%.*]]) #[[ATTR9:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @asinh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vasinhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -284,6 +363,11 @@ define void @asinh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @asinh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svasinh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @asinh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svasinh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @asinhf(float [[IN:%.*]]) #[[ATTR9:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -315,6 +399,11 @@ define void @atan_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atan(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atan_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atan(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atan(double [[IN:%.*]]) #[[ATTR10:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atan_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vatanq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -322,6 +411,11 @@ define void @atan_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atan_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svatan_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atan_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svatan_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atan(double [[IN:%.*]]) #[[ATTR10:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -350,6 +444,11 @@ define void @atan_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atan_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atanf(float [[IN:%.*]]) #[[ATTR11:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atan_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vatanq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -357,6 +456,11 @@ define void @atan_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atan_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svatan_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atan_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svatan_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atanf(float [[IN:%.*]]) #[[ATTR11:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -388,6 +492,11 @@ define void @atan2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_atan2(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atan2_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_atan2(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atan2(double [[IN:%.*]], double [[IN]]) #[[ATTR12:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atan2_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vatan2q_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -395,6 +504,11 @@ define void @atan2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atan2_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svatan2_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atan2_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svatan2_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atan2(double [[IN:%.*]], double [[IN]]) #[[ATTR12:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -423,6 +537,11 @@ define void @atan2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_atan2f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atan2_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_atan2f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atan2f(float [[IN:%.*]], float [[IN]]) #[[ATTR13:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atan2_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vatan2q_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -430,6 +549,11 @@ define void @atan2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atan2_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svatan2_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atan2_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svatan2_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atan2f(float [[IN:%.*]], float [[IN]]) #[[ATTR13:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -461,6 +585,11 @@ define void @atanh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atanh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atanh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_atanh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atanh(double [[IN:%.*]]) #[[ATTR14:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atanh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vatanhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -468,6 +597,11 @@ define void @atanh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atanh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svatanh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atanh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svatanh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @atanh(double [[IN:%.*]]) #[[ATTR14:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -496,6 +630,11 @@ define void @atanh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanhf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @atanh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_atanhf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atanhf(float [[IN:%.*]]) #[[ATTR15:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @atanh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vatanhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -503,6 +642,11 @@ define void @atanh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @atanh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svatanh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @atanh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svatanh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @atanhf(float [[IN:%.*]]) #[[ATTR15:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -534,6 +678,11 @@ define void @cbrt_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cbrt(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cbrt_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cbrt(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cbrt(double [[IN:%.*]]) #[[ATTR16:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cbrt_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vcbrtq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -541,6 +690,11 @@ define void @cbrt_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cbrt_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcbrt_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cbrt_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svcbrt_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cbrt(double [[IN:%.*]]) #[[ATTR16:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -569,6 +723,11 @@ define void @cbrt_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cbrtf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cbrt_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cbrtf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cbrtf(float [[IN:%.*]]) #[[ATTR17:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cbrt_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vcbrtq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -576,6 +735,11 @@ define void @cbrt_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cbrt_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcbrt_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cbrt_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svcbrt_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cbrtf(float [[IN:%.*]]) #[[ATTR17:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -607,6 +771,11 @@ define void @copysign_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_copysign(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @copysign_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_copysign(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @copysign(double [[IN:%.*]], double [[IN]]) #[[ATTR18:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @copysign_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vcopysignq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -614,6 +783,11 @@ define void @copysign_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @copysign_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcopysign_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @copysign_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svcopysign_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @copysign(double [[IN:%.*]], double [[IN]]) #[[ATTR18:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -642,6 +816,11 @@ define void @copysign_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_copysignf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @copysign_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_copysignf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @copysignf(float [[IN:%.*]], float [[IN]]) #[[ATTR19:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @copysign_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vcopysignq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -649,6 +828,11 @@ define void @copysign_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @copysign_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcopysign_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @copysign_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svcopysign_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @copysignf(float [[IN:%.*]], float [[IN]]) #[[ATTR19:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -680,6 +864,11 @@ define void @cos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cos(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cos_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cos(double [[IN:%.*]]) #[[ATTR20:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cos_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vcosq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -687,6 +876,11 @@ define void @cos_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cos_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cos_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svcos_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cos(double [[IN:%.*]]) #[[ATTR20:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -715,6 +909,11 @@ define void @cos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cosf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cos_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cosf(float [[IN:%.*]]) #[[ATTR21:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cos_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vcosq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -722,6 +921,11 @@ define void @cos_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cos_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cos_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svcos_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cosf(float [[IN:%.*]]) #[[ATTR21:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -753,6 +957,11 @@ define void @cosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cosh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cosh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cosh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cosh(double [[IN:%.*]]) #[[ATTR22:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cosh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vcoshq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -760,6 +969,11 @@ define void @cosh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cosh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcosh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cosh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svcosh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cosh(double [[IN:%.*]]) #[[ATTR22:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -788,6 +1002,11 @@ define void @cosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_coshf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cosh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_coshf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @coshf(float [[IN:%.*]]) #[[ATTR23:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cosh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vcoshq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -795,6 +1014,11 @@ define void @cosh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cosh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcosh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cosh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svcosh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @coshf(float [[IN:%.*]]) #[[ATTR23:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -826,6 +1050,11 @@ define void @cospi_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cospi(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cospi_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_cospi(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cospi(double [[IN:%.*]]) #[[ATTR24:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cospi_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vcospiq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -833,6 +1062,11 @@ define void @cospi_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cospi_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svcospi_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cospi_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svcospi_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @cospi(double [[IN:%.*]]) #[[ATTR24:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -861,6 +1095,11 @@ define void @cospi_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cospif(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @cospi_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_cospif(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cospif(float [[IN:%.*]]) #[[ATTR25:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @cospi_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vcospiq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -868,6 +1107,11 @@ define void @cospi_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @cospi_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svcospi_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @cospi_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svcospi_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @cospif(float [[IN:%.*]]) #[[ATTR25:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -899,6 +1143,11 @@ define void @erf_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_erf(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @erf_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_erf(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @erf(double [[IN:%.*]]) #[[ATTR26:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @erf_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_verfq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -906,6 +1155,11 @@ define void @erf_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @erf_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_sverf_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @erf_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_sverf_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @erf(double [[IN:%.*]]) #[[ATTR26:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -934,6 +1188,11 @@ define void @erf_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_erff(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @erf_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_erff(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @erff(float [[IN:%.*]]) #[[ATTR27:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @erf_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_verfq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -941,6 +1200,11 @@ define void @erf_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @erf_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_sverf_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @erf_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_sverf_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @erff(float [[IN:%.*]]) #[[ATTR27:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -972,6 +1236,11 @@ define void @erfc_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_erfc(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @erfc_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_erfc(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @erfc(double [[IN:%.*]]) #[[ATTR28:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @erfc_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_verfcq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -979,6 +1248,11 @@ define void @erfc_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @erfc_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_sverfc_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @erfc_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_sverfc_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @erfc(double [[IN:%.*]]) #[[ATTR28:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1007,6 +1281,11 @@ define void @erfc_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_erfcf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @erfc_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_erfcf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @erfcf(float [[IN:%.*]]) #[[ATTR29:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @erfc_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_verfcq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1014,6 +1293,11 @@ define void @erfc_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @erfc_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_sverfc_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @erfc_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_sverfc_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @erfcf(float [[IN:%.*]]) #[[ATTR29:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1045,6 +1329,11 @@ define void @exp_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp(double [[IN:%.*]]) #[[ATTR30:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vexpq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1052,6 +1341,11 @@ define void @exp_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svexp_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svexp_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp(double [[IN:%.*]]) #[[ATTR30:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1080,6 +1374,11 @@ define void @exp_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @expf(float [[IN:%.*]]) #[[ATTR31:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vexpq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1087,6 +1386,11 @@ define void @exp_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svexp_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svexp_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @expf(float [[IN:%.*]]) #[[ATTR31:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1118,6 +1422,11 @@ define void @exp10_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp10(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp10_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp10(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp10(double [[IN:%.*]]) #[[ATTR32:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp10_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vexp10q_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1125,6 +1434,11 @@ define void @exp10_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp10_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svexp10_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp10_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svexp10_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp10(double [[IN:%.*]]) #[[ATTR32:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1153,6 +1467,11 @@ define void @exp10_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_exp10f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp10_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_exp10f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @exp10f(float [[IN:%.*]]) #[[ATTR33:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp10_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vexp10q_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1160,6 +1479,11 @@ define void @exp10_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp10_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svexp10_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp10_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svexp10_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @exp10f(float [[IN:%.*]]) #[[ATTR33:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1191,6 +1515,11 @@ define void @exp2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp2(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp2_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_exp2(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp2(double [[IN:%.*]]) #[[ATTR34:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp2_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vexp2q_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1198,6 +1527,11 @@ define void @exp2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp2_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svexp2_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp2_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svexp2_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @exp2(double [[IN:%.*]]) #[[ATTR34:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1226,6 +1560,11 @@ define void @exp2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_exp2f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @exp2_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_exp2f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @exp2f(float [[IN:%.*]]) #[[ATTR35:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @exp2_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vexp2q_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1233,6 +1572,11 @@ define void @exp2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @exp2_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svexp2_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @exp2_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svexp2_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @exp2f(float [[IN:%.*]]) #[[ATTR35:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1264,6 +1608,11 @@ define void @expm1_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_expm1(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @expm1_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_expm1(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @expm1(double [[IN:%.*]]) #[[ATTR36:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @expm1_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vexpm1q_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1271,6 +1620,11 @@ define void @expm1_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @expm1_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svexpm1_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @expm1_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svexpm1_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @expm1(double [[IN:%.*]]) #[[ATTR36:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1299,6 +1653,11 @@ define void @expm1_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expm1f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @expm1_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_expm1f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @expm1f(float [[IN:%.*]]) #[[ATTR37:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @expm1_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vexpm1q_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1306,6 +1665,11 @@ define void @expm1_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @expm1_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svexpm1_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @expm1_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svexpm1_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @expm1f(float [[IN:%.*]]) #[[ATTR37:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1337,6 +1701,11 @@ define void @fdim_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fdim(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fdim_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fdim(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fdim(double [[IN:%.*]], double [[IN]]) #[[ATTR38:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fdim_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vfdimq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -1344,6 +1713,11 @@ define void @fdim_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fdim_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svfdim_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fdim_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svfdim_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fdim(double [[IN:%.*]], double [[IN]]) #[[ATTR38:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1372,6 +1746,11 @@ define void @fdim_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fdimf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fdim_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fdimf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fdimf(float [[IN:%.*]], float [[IN]]) #[[ATTR39:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fdim_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vfdimq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -1379,6 +1758,11 @@ define void @fdim_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fdim_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svfdim_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fdim_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svfdim_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fdimf(float [[IN:%.*]], float [[IN]]) #[[ATTR39:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1410,6 +1794,11 @@ define void @fma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvvv_fma(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fma_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvvv_fma(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fma(double [[IN:%.*]], double [[IN]], double [[IN]]) #[[ATTR40:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fma_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vfmaq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]], <2 x double> [[WIDE_LOAD]])
@@ -1417,6 +1806,11 @@ define void @fma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fma_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svfma_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fma_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svfma_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fma(double [[IN:%.*]], double [[IN]], double [[IN]]) #[[ATTR40:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1445,6 +1839,11 @@ define void @fma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvvv_fmaf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fma_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvvv_fmaf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmaf(float [[IN:%.*]], float [[IN]], float [[IN]]) #[[ATTR41:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fma_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vfmaq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]], <4 x float> [[WIDE_LOAD]])
@@ -1452,6 +1851,11 @@ define void @fma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fma_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svfma_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fma_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svfma_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmaf(float [[IN:%.*]], float [[IN]], float [[IN]]) #[[ATTR41:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1483,6 +1887,11 @@ define void @fmax_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmax(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmax_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmax(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmax(double [[IN:%.*]], double [[IN]]) #[[ATTR42:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmax_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vfmaxq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -1490,6 +1899,11 @@ define void @fmax_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmax_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svfmax_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmax_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svfmax_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmax(double [[IN:%.*]], double [[IN]]) #[[ATTR42:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1518,6 +1932,11 @@ define void @fmax_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fmaxf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmax_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fmaxf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmaxf(float [[IN:%.*]], float [[IN]]) #[[ATTR43:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmax_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vfmaxq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -1525,6 +1944,11 @@ define void @fmax_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmax_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svfmax_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmax_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svfmax_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmaxf(float [[IN:%.*]], float [[IN]]) #[[ATTR43:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1556,6 +1980,11 @@ define void @fmin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmin(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmin_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmin(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmin(double [[IN:%.*]], double [[IN]]) #[[ATTR44:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmin_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vfminq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -1563,6 +1992,11 @@ define void @fmin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmin_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svfmin_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmin_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svfmin_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmin(double [[IN:%.*]], double [[IN]]) #[[ATTR44:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1591,6 +2025,11 @@ define void @fmin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fminf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmin_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fminf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fminf(float [[IN:%.*]], float [[IN]]) #[[ATTR45:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmin_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vfminq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -1598,6 +2037,11 @@ define void @fmin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmin_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svfmin_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmin_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svfmin_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fminf(float [[IN:%.*]], float [[IN]]) #[[ATTR45:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1629,6 +2073,11 @@ define void @fmod_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmod(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmod_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_fmod(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmod(double [[IN:%.*]], double [[IN]]) #[[ATTR46:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmod_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vfmodq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -1636,6 +2085,11 @@ define void @fmod_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmod_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svfmod_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmod_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svfmod_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @fmod(double [[IN:%.*]], double [[IN]]) #[[ATTR46:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1664,6 +2118,11 @@ define void @fmod_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fmodf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @fmod_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_fmodf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmodf(float [[IN:%.*]], float [[IN]]) #[[ATTR47:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @fmod_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vfmodq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -1671,6 +2130,11 @@ define void @fmod_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @fmod_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svfmod_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @fmod_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svfmod_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @fmodf(float [[IN:%.*]], float [[IN]]) #[[ATTR47:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1702,6 +2166,11 @@ define void @hypot_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_hypot(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @hypot_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_hypot(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @hypot(double [[IN:%.*]], double [[IN]]) #[[ATTR48:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @hypot_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vhypotq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -1709,6 +2178,11 @@ define void @hypot_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @hypot_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svhypot_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @hypot_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svhypot_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @hypot(double [[IN:%.*]], double [[IN]]) #[[ATTR48:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1737,6 +2211,11 @@ define void @hypot_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_hypotf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @hypot_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_hypotf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @hypotf(float [[IN:%.*]], float [[IN]]) #[[ATTR49:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @hypot_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vhypotq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -1744,6 +2223,11 @@ define void @hypot_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @hypot_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svhypot_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @hypot_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svhypot_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @hypotf(float [[IN:%.*]], float [[IN]]) #[[ATTR49:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1775,6 +2259,11 @@ define void @ilogb_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x i32> @_ZGVsMxv_ilogb(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @ilogb_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x i32> @_ZGVsMxv_ilogb(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call i32 @ilogb(double [[IN:%.*]]) #[[ATTR50:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @ilogb_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x i32> @armpl_vilogbq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1782,6 +2271,11 @@ define void @ilogb_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @ilogb_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x i32> @armpl_svilogb_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @ilogb_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x i32> @armpl_svilogb_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call i32 @ilogb(double [[IN:%.*]]) #[[ATTR50:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1810,6 +2304,11 @@ define void @ilogb_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x i32> @_ZGVsMxv_ilogbf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @ilogb_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x i32> @_ZGVsMxv_ilogbf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call i32 @ilogbf(float [[IN:%.*]]) #[[ATTR51:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @ilogb_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x i32> @armpl_vilogbq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1817,6 +2316,11 @@ define void @ilogb_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @ilogb_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x i32> @armpl_svilogb_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @ilogb_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x i32> @armpl_svilogb_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call i32 @ilogbf(float [[IN:%.*]]) #[[ATTR51:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1848,6 +2352,11 @@ define void @ldexp_f64(ptr noalias %in1.ptr, ptr noalias %in2.ptr, ptr noalias %
 ; SLEEF-SVE-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP17:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_ldexp(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i32> [[WIDE_MASKED_LOAD1:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @ldexp_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP11:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_ldexp(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i32> [[WIDE_LOAD1:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @ldexp(double [[IN1:%.*]], i32 [[IN2:%.*]]) #[[ATTR52:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @ldexp_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP5:%.*]] = call <2 x double> @armpl_vldexpq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x i32> [[WIDE_LOAD1:%.*]])
@@ -1855,6 +2364,11 @@ define void @ldexp_f64(ptr noalias %in1.ptr, ptr noalias %in2.ptr, ptr noalias %
 ; ARMPL-SVE-LABEL: define void @ldexp_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP17:%.*]] = call <vscale x 2 x double> @armpl_svldexp_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i32> [[WIDE_MASKED_LOAD1:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @ldexp_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP11:%.*]] = call <vscale x 2 x double> @armpl_svldexp_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i32> [[WIDE_LOAD1:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @ldexp(double [[IN1:%.*]], i32 [[IN2:%.*]]) #[[ATTR52:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1885,6 +2399,11 @@ define void @ldexp_f32(ptr noalias %in1.ptr, ptr noalias %in2.ptr, ptr noalias %
 ; SLEEF-SVE-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP17:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_ldexpf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD1:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @ldexp_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP11:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_ldexpf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i32> [[WIDE_LOAD1:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @ldexpf(float [[IN1:%.*]], i32 [[IN2:%.*]]) #[[ATTR53:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @ldexp_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP5:%.*]] = call <4 x float> @armpl_vldexpq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x i32> [[WIDE_LOAD1:%.*]])
@@ -1892,6 +2411,11 @@ define void @ldexp_f32(ptr noalias %in1.ptr, ptr noalias %in2.ptr, ptr noalias %
 ; ARMPL-SVE-LABEL: define void @ldexp_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP17:%.*]] = call <vscale x 4 x float> @armpl_svldexp_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD1:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @ldexp_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN1_PTR:%.*]], ptr noalias [[IN2_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP11:%.*]] = call <vscale x 4 x float> @armpl_svldexp_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i32> [[WIDE_LOAD1:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @ldexpf(float [[IN1:%.*]], i32 [[IN2:%.*]]) #[[ATTR53:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1925,6 +2449,11 @@ define void @lgamma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_lgamma(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @lgamma_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_lgamma(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @lgamma(double [[IN:%.*]]) #[[ATTR54:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @lgamma_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vlgammaq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -1932,6 +2461,11 @@ define void @lgamma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @lgamma_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svlgamma_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @lgamma_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svlgamma_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @lgamma(double [[IN:%.*]]) #[[ATTR54:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1960,6 +2494,11 @@ define void @lgamma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_lgammaf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @lgamma_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_lgammaf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @lgammaf(float [[IN:%.*]]) #[[ATTR55:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @lgamma_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vlgammaq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -1967,6 +2506,11 @@ define void @lgamma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @lgamma_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svlgamma_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @lgamma_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svlgamma_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @lgammaf(float [[IN:%.*]]) #[[ATTR55:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -1998,6 +2542,11 @@ define void @log_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log(double [[IN:%.*]]) #[[ATTR56:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vlogq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2005,6 +2554,11 @@ define void @log_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svlog_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svlog_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log(double [[IN:%.*]]) #[[ATTR56:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2033,6 +2587,11 @@ define void @log_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_logf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_logf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @logf(float [[IN:%.*]]) #[[ATTR57:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vlogq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2040,6 +2599,11 @@ define void @log_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svlog_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svlog_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @logf(float [[IN:%.*]]) #[[ATTR57:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2071,6 +2635,11 @@ define void @log10_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log10(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log10_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log10(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log10(double [[IN:%.*]]) #[[ATTR58:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log10_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vlog10q_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2078,6 +2647,11 @@ define void @log10_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log10_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svlog10_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log10_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svlog10_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log10(double [[IN:%.*]]) #[[ATTR58:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2106,6 +2680,11 @@ define void @log10_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log10f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log10_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log10f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log10f(float [[IN:%.*]]) #[[ATTR59:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log10_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vlog10q_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2113,6 +2692,11 @@ define void @log10_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log10_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svlog10_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log10_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svlog10_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log10f(float [[IN:%.*]]) #[[ATTR59:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2144,6 +2728,11 @@ define void @log1p_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log1p(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log1p_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log1p(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log1p(double [[IN:%.*]]) #[[ATTR60:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log1p_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vlog1pq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2151,6 +2740,11 @@ define void @log1p_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log1p_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svlog1p_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log1p_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svlog1p_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log1p(double [[IN:%.*]]) #[[ATTR60:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2179,6 +2773,11 @@ define void @log1p_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log1pf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log1p_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log1pf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log1pf(float [[IN:%.*]]) #[[ATTR61:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log1p_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vlog1pq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2186,6 +2785,11 @@ define void @log1p_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log1p_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svlog1p_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log1p_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svlog1p_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log1pf(float [[IN:%.*]]) #[[ATTR61:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2217,6 +2821,11 @@ define void @log2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log2(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log2_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_log2(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log2(double [[IN:%.*]]) #[[ATTR62:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log2_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vlog2q_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2224,6 +2833,11 @@ define void @log2_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log2_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svlog2_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log2_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svlog2_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @log2(double [[IN:%.*]]) #[[ATTR62:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2252,6 +2866,11 @@ define void @log2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log2f(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @log2_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_log2f(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log2f(float [[IN:%.*]]) #[[ATTR63:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @log2_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vlog2q_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2259,6 +2878,11 @@ define void @log2_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @log2_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svlog2_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @log2_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svlog2_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @log2f(float [[IN:%.*]]) #[[ATTR63:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2288,7 +2912,12 @@ define void @modf_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @modf_f64
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    [[TMP23:%.*]] = call <vscale x 2 x double> @_ZGVsMxvl8_modf(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR4:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @modf_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP17:%.*]] = call <vscale x 2 x double> @_ZGVsNxvl8_modf(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]])
+; SLEEF-SVE-NOPRED:    [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR64:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @modf_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2296,7 +2925,11 @@ define void @modf_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @modf_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    [[TMP23:%.*]] = call <vscale x 2 x double> @armpl_svmodf_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    [[DATA:%.*]] = call double @modf(double [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR4:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @modf_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP5:%.*]] = call <2 x double> @armpl_vmodfq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
 ;
 entry:
   br label %for.body
@@ -2324,7 +2957,12 @@ define void @modf_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @modf_f32
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    [[TMP23:%.*]] = call <vscale x 4 x float> @_ZGVsMxvl4_modff(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR5:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @modf_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP17:%.*]] = call <vscale x 4 x float> @_ZGVsNxvl4_modff(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP16:%.*]])
+; SLEEF-SVE-NOPRED:    [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR65:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @modf_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2332,7 +2970,11 @@ define void @modf_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @modf_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    [[TMP23:%.*]] = call <vscale x 4 x float> @armpl_svmodf_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP22:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    [[DATA:%.*]] = call float @modff(float [[NUM:%.*]], ptr [[GEPB:%.*]]) #[[ATTR5:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @modf_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP5:%.*]] = call <4 x float> @armpl_vmodfq_f32(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP4:%.*]])
 ;
 entry:
   br label %for.body
@@ -2365,6 +3007,11 @@ define void @nextafter_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_nextafter(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @nextafter_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_nextafter(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @nextafter(double [[IN:%.*]], double [[IN]]) #[[ATTR66:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @nextafter_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vnextafterq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -2372,6 +3019,11 @@ define void @nextafter_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @nextafter_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svnextafter_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @nextafter_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svnextafter_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @nextafter(double [[IN:%.*]], double [[IN]]) #[[ATTR64:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2400,6 +3052,11 @@ define void @nextafter_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_nextafterf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @nextafter_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_nextafterf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @nextafterf(float [[IN:%.*]], float [[IN]]) #[[ATTR67:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @nextafter_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vnextafterq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -2407,6 +3064,11 @@ define void @nextafter_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @nextafter_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svnextafter_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @nextafter_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svnextafter_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @nextafterf(float [[IN:%.*]], float [[IN]]) #[[ATTR65:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2438,6 +3100,11 @@ define void @pow_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_pow(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @pow_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxvv_pow(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @pow(double [[IN:%.*]], double [[IN]]) #[[ATTR68:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @pow_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vpowq_f64(<2 x double> [[WIDE_LOAD:%.*]], <2 x double> [[WIDE_LOAD]])
@@ -2445,6 +3112,11 @@ define void @pow_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @pow_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svpow_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x double> [[WIDE_MASKED_LOAD]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @pow_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svpow_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x double> [[WIDE_LOAD]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @pow(double [[IN:%.*]], double [[IN]]) #[[ATTR66:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2473,6 +3145,11 @@ define void @pow_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_powf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @pow_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxvv_powf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @powf(float [[IN:%.*]], float [[IN]]) #[[ATTR69:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @pow_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vpowq_f32(<4 x float> [[WIDE_LOAD:%.*]], <4 x float> [[WIDE_LOAD]])
@@ -2480,6 +3157,11 @@ define void @pow_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @pow_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svpow_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @pow_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svpow_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x float> [[WIDE_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @powf(float [[IN:%.*]], float [[IN]]) #[[ATTR67:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2511,6 +3193,11 @@ define void @sin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sin(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sin_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sin(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sin(double [[IN:%.*]]) #[[ATTR70:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sin_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vsinq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2518,6 +3205,11 @@ define void @sin_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sin_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svsin_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sin_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svsin_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sin(double [[IN:%.*]]) #[[ATTR68:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2546,6 +3238,11 @@ define void @sin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sin_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinf(float [[IN:%.*]]) #[[ATTR71:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sin_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vsinq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2553,6 +3250,11 @@ define void @sin_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sin_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svsin_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sin_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svsin_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinf(float [[IN:%.*]]) #[[ATTR69:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2582,7 +3284,12 @@ define void @sincos_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @sincos_f64
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    call void @_ZGVsMxvl8l8_sincos(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR6:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @sincos_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    call void @_ZGVsNxvl8l8_sincos(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
+; SLEEF-SVE-NOPRED:    call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR72:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @sincos_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2590,7 +3297,11 @@ define void @sincos_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @sincos_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    call void @armpl_svsincos_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    call void @sincos(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR6:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sincos_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    call void @armpl_vsincosq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
 ;
 entry:
   br label %for.body
@@ -2617,7 +3328,12 @@ define void @sincos_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @sincos_f32
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    call void @_ZGVsMxvl4l4_sincosf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR7:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @sincos_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    call void @_ZGVsNxvl4l4_sincosf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
+; SLEEF-SVE-NOPRED:    call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR73:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @sincos_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2625,7 +3341,11 @@ define void @sincos_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @sincos_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    call void @armpl_svsincos_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    call void @sincosf(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR7:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sincos_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    call void @armpl_vsincosq_f32(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
 ;
 entry:
   br label %for.body
@@ -2655,7 +3375,12 @@ define void @sincospi_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @sincospi_f64
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    call void @_ZGVsMxvl8l8_sincospi(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR8:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @sincospi_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    call void @_ZGVsNxvl8l8_sincospi(<vscale x 2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
+; SLEEF-SVE-NOPRED:    call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR74:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @sincospi_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2663,7 +3388,11 @@ define void @sincospi_f64(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @sincospi_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    call void @armpl_svsincospi_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    call void @sincospi(double [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR8:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sincospi_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    call void @armpl_vsincospiq_f64(<2 x double> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
 ;
 entry:
   br label %for.body
@@ -2690,7 +3419,12 @@ define void @sincospi_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; SLEEF-SVE-LABEL: define void @sincospi_f32
 ; SLEEF-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; SLEEF-SVE:    call void @_ZGVsMxvl4l4_sincospif(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; SLEEF-SVE:    call void @sincospif(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR9:[0-9]+]]
+;
+; SLEEF-SVE-NOPRED-LABEL: define void @sincospi_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    call void @_ZGVsNxvl4l4_sincospif(<vscale x 4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP17:%.*]], ptr [[TMP18:%.*]])
+; SLEEF-SVE-NOPRED:    call void @sincospif(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR75:[0-9]+]]
 ;
 ; ARMPL-NEON-LABEL: define void @sincospi_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
@@ -2698,7 +3432,11 @@ define void @sincospi_f32(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
 ;
 ; ARMPL-SVE-LABEL: define void @sincospi_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
-; ARMPL-SVE:    call void @armpl_svsincospi_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], ptr [[TMP23:%.*]], ptr [[TMP24:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+; ARMPL-SVE:    call void @sincospif(float [[NUM:%.*]], ptr [[GEPB:%.*]], ptr [[GEPC:%.*]]) #[[ATTR9:[0-9]+]]
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sincospi_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    call void @armpl_vsincospiq_f32(<4 x float> [[WIDE_LOAD:%.*]], ptr [[TMP5:%.*]], ptr [[TMP6:%.*]])
 ;
 entry:
   br label %for.body
@@ -2730,6 +3468,11 @@ define void @sinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sinh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sinh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sinh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sinh(double [[IN:%.*]]) #[[ATTR76:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sinh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vsinhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2737,6 +3480,11 @@ define void @sinh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sinh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svsinh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sinh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svsinh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sinh(double [[IN:%.*]]) #[[ATTR70:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2765,6 +3513,11 @@ define void @sinh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinhf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sinh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinhf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinhf(float [[IN:%.*]]) #[[ATTR77:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sinh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vsinhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2772,6 +3525,11 @@ define void @sinh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sinh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svsinh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sinh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svsinh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinhf(float [[IN:%.*]]) #[[ATTR71:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2803,6 +3561,11 @@ define void @sinpi_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sinpi(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sinpi_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sinpi(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sinpi(double [[IN:%.*]]) #[[ATTR78:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sinpi_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vsinpiq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2810,6 +3573,11 @@ define void @sinpi_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sinpi_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svsinpi_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sinpi_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svsinpi_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sinpi(double [[IN:%.*]]) #[[ATTR72:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2838,6 +3606,11 @@ define void @sinpi_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinpif(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sinpi_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sinpif(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinpif(float [[IN:%.*]]) #[[ATTR79:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sinpi_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vsinpiq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2845,6 +3618,11 @@ define void @sinpi_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sinpi_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svsinpi_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sinpi_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svsinpi_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sinpif(float [[IN:%.*]]) #[[ATTR73:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2876,6 +3654,11 @@ define void @sqrt_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sqrt(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sqrt_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_sqrt(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sqrt(double [[IN:%.*]]) #[[ATTR80:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sqrt_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vsqrtq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2883,6 +3666,11 @@ define void @sqrt_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sqrt_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svsqrt_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sqrt_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svsqrt_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @sqrt(double [[IN:%.*]]) #[[ATTR74:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2911,6 +3699,11 @@ define void @sqrt_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sqrtf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @sqrt_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_sqrtf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sqrtf(float [[IN:%.*]]) #[[ATTR81:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @sqrt_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vsqrtq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2918,6 +3711,11 @@ define void @sqrt_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @sqrt_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svsqrt_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @sqrt_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svsqrt_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @sqrtf(float [[IN:%.*]]) #[[ATTR75:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2949,6 +3747,11 @@ define void @tan_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tan(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tan_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tan(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tan(double [[IN:%.*]]) #[[ATTR82:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tan_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vtanq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -2956,6 +3759,11 @@ define void @tan_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tan_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svtan_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tan_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svtan_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tan(double [[IN:%.*]]) #[[ATTR76:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -2984,6 +3792,11 @@ define void @tan_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tanf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tan_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tanf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tanf(float [[IN:%.*]]) #[[ATTR83:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tan_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vtanq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -2991,6 +3804,11 @@ define void @tan_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tan_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svtan_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tan_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svtan_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tanf(float [[IN:%.*]]) #[[ATTR77:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -3022,6 +3840,11 @@ define void @tanh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tanh(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tanh_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tanh(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tanh(double [[IN:%.*]]) #[[ATTR84:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tanh_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vtanhq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -3029,6 +3852,11 @@ define void @tanh_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tanh_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svtanh_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tanh_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svtanh_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tanh(double [[IN:%.*]]) #[[ATTR78:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -3057,6 +3885,11 @@ define void @tanh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tanhf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tanh_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tanhf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tanhf(float [[IN:%.*]]) #[[ATTR85:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tanh_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vtanhq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -3064,6 +3897,11 @@ define void @tanh_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tanh_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svtanh_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tanh_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svtanh_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tanhf(float [[IN:%.*]]) #[[ATTR79:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -3095,6 +3933,11 @@ define void @tgamma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tgamma(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tgamma_f64
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @_ZGVsMxv_tgamma(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tgamma(double [[IN:%.*]]) #[[ATTR86:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tgamma_f64
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <2 x double> @armpl_vtgammaq_f64(<2 x double> [[WIDE_LOAD:%.*]])
@@ -3102,6 +3945,11 @@ define void @tgamma_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tgamma_f64
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 2 x double> @armpl_svtgamma_f64_x(<vscale x 2 x double> [[WIDE_MASKED_LOAD:%.*]], <vscale x 2 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tgamma_f64
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 2 x double> @armpl_svtgamma_f64_x(<vscale x 2 x double> [[WIDE_LOAD:%.*]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call double @tgamma(double [[IN:%.*]]) #[[ATTR80:[0-9]+]]
 ;
   entry:
   br label %for.body
@@ -3130,6 +3978,11 @@ define void @tgamma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; SLEEF-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; SLEEF-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tgammaf(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
 ;
+; SLEEF-SVE-NOPRED-LABEL: define void @tgamma_f32
+; SLEEF-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; SLEEF-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @_ZGVsMxv_tgammaf(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; SLEEF-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tgammaf(float [[IN:%.*]]) #[[ATTR87:[0-9]+]]
+;
 ; ARMPL-NEON-LABEL: define void @tgamma_f32
 ; ARMPL-NEON-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-NEON:    [[TMP3:%.*]] = call <4 x float> @armpl_vtgammaq_f32(<4 x float> [[WIDE_LOAD:%.*]])
@@ -3137,6 +3990,11 @@ define void @tgamma_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
 ; ARMPL-SVE-LABEL: define void @tgamma_f32
 ; ARMPL-SVE-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
 ; ARMPL-SVE:    [[TMP15:%.*]] = call <vscale x 4 x float> @armpl_svtgamma_f32_x(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
+;
+; ARMPL-SVE-NOPRED-LABEL: define void @tgamma_f32
+; ARMPL-SVE-NOPRED-SAME: (ptr noalias [[IN_PTR:%.*]], ptr noalias [[OUT_PTR:%.*]]) #[[ATTR0]] {
+; ARMPL-SVE-NOPRED:    [[TMP9:%.*]] = call <vscale x 4 x float> @armpl_svtgamma_f32_x(<vscale x 4 x float> [[WIDE_LOAD:%.*]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; ARMPL-SVE-NOPRED:    [[CALL:%.*]] = tail call float @tgammaf(float [[IN:%.*]]) #[[ATTR81:[0-9]+]]
 ;
   entry:
   br label %for.body
diff --git a/llvm/test/Transforms/Util/add-TLI-mappings.ll b/llvm/test/Transforms/Util/add-TLI-mappings.ll
index 8ccd27030afae..7b12de9031901 100644
--- a/llvm/test/Transforms/Util/add-TLI-mappings.ll
+++ b/llvm/test/Transforms/Util/add-TLI-mappings.ll
@@ -23,36 +23,30 @@
 ; LIBMVEC-X86-SAME:   ptr @_ZGVdN4v_sin
 ; SLEEFGNUABI-SAME: [16 x ptr] [
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN2vl8_modf,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl8_modf,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl8_modf,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN4vl4_modff,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl4_modff,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl4_modff,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN2v_sin,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVsMxv_sin,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN2vl8l8_sincos,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl8l8_sincos,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl8l8_sincos,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN4vl4l4_sincosf,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl4l4_sincosf,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl4l4_sincosf,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN2vl8l8_sincospi,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl8l8_sincospi,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl8l8_sincospi,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVnN4vl4l4_sincospif,
-; SLEEFGNUABI-SAME:   ptr @_ZGVsMxvl4l4_sincospif,
+; SLEEFGNUABI-SAME:   ptr @_ZGVsNxvl4l4_sincospif,
 ; SLEEFGNUABI_SAME;   ptr @_ZGVnN4v_log10f,
 ; SLEEFGNUABI-SAME:   ptr @_ZGVsMxv_log10f
-; ARMPL-SAME:       [16 x ptr] [
+; ARMPL-SAME:       [10 x ptr] [
 ; ARMPL-SAME:         ptr @armpl_vmodfq_f64,
-; ARMPL-SAME:         ptr @armpl_svmodf_f64_x,
 ; ARMPL-SAME:         ptr @armpl_vmodfq_f32,
-; ARMPL-SAME:         ptr @armpl_svmodf_f32_x,
 ; ARMPL-SAME:         ptr @armpl_vsinq_f64,
 ; ARMPL-SAME:         ptr @armpl_svsin_f64_x,
 ; ARMPL-SAME:         ptr @armpl_vsincosq_f64,
-; ARMPL-SAME:         ptr @armpl_svsincos_f64_x,
 ; ARMPL-SAME:         ptr @armpl_vsincosq_f32,
-; ARMPL-SAME:         ptr @armpl_svsincos_f32_x,
 ; ARMPL-SAME:         ptr @armpl_vsincospiq_f64,
-; ARMPL-SAME:         ptr @armpl_svsincospi_f64_x,
 ; ARMPL-SAME:         ptr @armpl_vsincospiq_f32,
-; ARMPL-SAME:         ptr @armpl_svsincospi_f32_x,
 ; ARMPL-SAME:         ptr @armpl_vlog10q_f32,
 ; ARMPL-SAME:         ptr @armpl_svlog10_f32_x
 ; COMMON-SAME:      ], section "llvm.metadata"
@@ -166,36 +160,30 @@ declare float @llvm.log10.f32(float) #0
 ; ACCELERATE: declare <4 x float> @vlog10f(<4 x float>)
 
 ; SLEEFGNUABI: declare <2 x double> @_ZGVnN2vl8_modf(<2 x double>, ptr)
-; SLEEFGNUABI: declare <vscale x 2 x double> @_ZGVsMxvl8_modf(<vscale x 2 x double>, ptr, <vscale x 2 x i1>)
+; SLEEFGNUABI: declare <vscale x 2 x double> @_ZGVsNxvl8_modf(<vscale x 2 x double>, ptr)
 ; SLEEFGNUABI: declare <4 x float> @_ZGVnN4vl4_modff(<4 x float>, ptr)
-; SLEEFGNUABI: declare <vscale x 4 x float> @_ZGVsMxvl4_modff(<vscale x 4 x float>, ptr, <vscale x 4 x i1>)
+; SLEEFGNUABI: declare <vscale x 4 x float> @_ZGVsNxvl4_modff(<vscale x 4 x float>, ptr)
 ; SLEEFGNUABI: declare <2 x double> @_ZGVnN2v_sin(<2 x double>)
 ; SLEEFGNUABI: declare <vscale x 2 x double> @_ZGVsMxv_sin(<vscale x 2 x double>, <vscale x 2 x i1>)
 ; SLEEFGNUABI: declare void @_ZGVnN2vl8l8_sincos(<2 x double>, ptr, ptr)
-; SLEEFGNUABI: declare void @_ZGVsMxvl8l8_sincos(<vscale x 2 x double>, ptr, ptr, <vscale x 2 x i1>)
+; SLEEFGNUABI: declare void @_ZGVsNxvl8l8_sincos(<vscale x 2 x double>, ptr, ptr)
 ; SLEEFGNUABI: declare void @_ZGVnN4vl4l4_sincosf(<4 x float>, ptr, ptr)
-; SLEEFGNUABI: declare void @_ZGVsMxvl4l4_sincosf(<vscale x 4 x float>, ptr, ptr, <vscale x 4 x i1>)
+; SLEEFGNUABI: declare void @_ZGVsNxvl4l4_sincosf(<vscale x 4 x float>, ptr, ptr)
 ; SLEEFGNUABI: declare void @_ZGVnN2vl8l8_sincospi(<2 x double>, ptr, ptr)
-; SLEEFGNUABI: declare void @_ZGVsMxvl8l8_sincospi(<vscale x 2 x double>, ptr, ptr, <vscale x 2 x i1>)
+; SLEEFGNUABI: declare void @_ZGVsNxvl8l8_sincospi(<vscale x 2 x double>, ptr, ptr)
 ; SLEEFGNUABI: declare void @_ZGVnN4vl4l4_sincospif(<4 x float>, ptr, ptr)
-; SLEEFGNUABI: declare void @_ZGVsMxvl4l4_sincospif(<vscale x 4 x float>, ptr, ptr, <vscale x 4 x i1>)
+; SLEEFGNUABI: declare void @_ZGVsNxvl4l4_sincospif(<vscale x 4 x float>, ptr, ptr)
 ; SLEEFGNUABI: declare <4 x float> @_ZGVnN4v_log10f(<4 x float>)
 ; SLEEFGNUABI: declare <vscale x 4 x float> @_ZGVsMxv_log10f(<vscale x 4 x float>, <vscale x 4 x i1>)
 
 ; ARMPL: declare <2 x double> @armpl_vmodfq_f64(<2 x double>, ptr)
-; ARMPL: declare <vscale x 2 x double> @armpl_svmodf_f64_x(<vscale x 2 x double>, ptr, <vscale x 2 x i1>)
 ; ARMPL: declare <4 x float> @armpl_vmodfq_f32(<4 x float>, ptr)
-; ARMPL: declare <vscale x 4 x float> @armpl_svmodf_f32_x(<vscale x 4 x float>, ptr, <vscale x 4 x i1>)
 ; ARMPL: declare <2 x double> @armpl_vsinq_f64(<2 x double>)
 ; ARMPL: declare <vscale x 2 x double> @armpl_svsin_f64_x(<vscale x 2 x double>, <vscale x 2 x i1>)
 ; ARMPL: declare void @armpl_vsincosq_f64(<2 x double>, ptr, ptr)
-; ARMPL: declare void @armpl_svsincos_f64_x(<vscale x 2 x double>, ptr, ptr, <vscale x 2 x i1>)
 ; ARMPL: declare void @armpl_vsincosq_f32(<4 x float>, ptr, ptr)
-; ARMPL: declare void @armpl_svsincos_f32_x(<vscale x 4 x float>, ptr, ptr, <vscale x 4 x i1>)
 ; ARMPL: declare void @armpl_vsincospiq_f64(<2 x double>, ptr, ptr)
-; ARMPL: declare void @armpl_svsincospi_f64_x(<vscale x 2 x double>, ptr, ptr, <vscale x 2 x i1>)
 ; ARMPL: declare void @armpl_vsincospiq_f32(<4 x float>, ptr, ptr)
-; ARMPL: declare void @armpl_svsincospi_f32_x(<vscale x 4 x float>, ptr, ptr, <vscale x 4 x i1>)
 ; ARMPL: declare <4 x float> @armpl_vlog10q_f32(<4 x float>)
 ; ARMPL: declare <vscale x 4 x float> @armpl_svlog10_f32_x(<vscale x 4 x float>, <vscale x 4 x i1>)
 
@@ -220,50 +208,44 @@ attributes #0 = { nounwind readnone }
 
 ; SLEEFGNUABI:      attributes #[[MODF]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N2vl8_modf(_ZGVnN2vl8_modf),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl8_modf(_ZGVsMxvl8_modf)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl8_modf(_ZGVsNxvl8_modf)" }
 ; SLEEFGNUABI:      attributes #[[MODFF]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N4vl4_modff(_ZGVnN4vl4_modff),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl4_modff(_ZGVsMxvl4_modff)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl4_modff(_ZGVsNxvl4_modff)" }
 ; SLEEFGNUABI:      attributes #[[SIN]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N2v_sin(_ZGVnN2v_sin),
 ; SLEEFGNUABI-SAME:   _ZGVsMxv_sin(_ZGVsMxv_sin)" }
 ; SLEEFGNUABI:      attributes #[[SINCOS]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N2vl8l8_sincos(_ZGVnN2vl8l8_sincos),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl8l8_sincos(_ZGVsMxvl8l8_sincos)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl8l8_sincos(_ZGVsNxvl8l8_sincos)" }
 ; SLEEFGNUABI:      attributes #[[SINCOSF]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N4vl4l4_sincosf(_ZGVnN4vl4l4_sincosf),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl4l4_sincosf(_ZGVsMxvl4l4_sincosf)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl4l4_sincosf(_ZGVsNxvl4l4_sincosf)" }
 ; SLEEFGNUABI:      attributes #[[SINCOSPI]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N2vl8l8_sincospi(_ZGVnN2vl8l8_sincospi),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl8l8_sincospi(_ZGVsMxvl8l8_sincospi)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl8l8_sincospi(_ZGVsNxvl8l8_sincospi)" }
 ; SLEEFGNUABI:      attributes #[[SINCOSPIF]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N4vl4l4_sincospif(_ZGVnN4vl4l4_sincospif),
-; SLEEFGNUABI-SAME:   _ZGVsMxvl4l4_sincospif(_ZGVsMxvl4l4_sincospif)" }
+; SLEEFGNUABI-SAME:   _ZGVsNxvl4l4_sincospif(_ZGVsNxvl4l4_sincospif)" }
 ; SLEEFGNUABI:      attributes #[[LOG10]] = { "vector-function-abi-variant"=
 ; SLEEFGNUABI-SAME:   "_ZGV_LLVM_N4v_llvm.log10.f32(_ZGVnN4v_log10f),
 ; SLEEFGNUABI-SAME:   _ZGVsMxv_llvm.log10.f32(_ZGVsMxv_log10f)" }
 
 ; ARMPL:      attributes #[[MODF]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N2vl8_modf(armpl_vmodfq_f64),
-; ARMPL-SAME:    _ZGVsMxvl8_modf(armpl_svmodf_f64_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N2vl8_modf(armpl_vmodfq_f64)" }
 ; ARMPL:      attributes #[[MODFF]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N4vl4_modff(armpl_vmodfq_f32),
-; ARMPL-SAME:    _ZGVsMxvl4_modff(armpl_svmodf_f32_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N4vl4_modff(armpl_vmodfq_f32)" }
 ; ARMPL:      attributes #[[SIN]] = { "vector-function-abi-variant"=
 ; ARMPL-SAME:    "_ZGV_LLVM_N2v_sin(armpl_vsinq_f64),
 ; ARMPL-SAME     _ZGVsMxv_sin(armpl_svsin_f64_x)" }
 ; ARMPL:      attributes #[[SINCOS]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N2vl8l8_sincos(armpl_vsincosq_f64),
-; ARMPL-SAME:   _ZGVsMxvl8l8_sincos(armpl_svsincos_f64_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N2vl8l8_sincos(armpl_vsincosq_f64)" }
 ; ARMPL:      attributes #[[SINCOSF]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N4vl4l4_sincosf(armpl_vsincosq_f32),
-; ARMPL-SAME:    _ZGVsMxvl4l4_sincosf(armpl_svsincos_f32_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N4vl4l4_sincosf(armpl_vsincosq_f32)" }
 ; ARMPL:      attributes #[[SINCOSPI]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N2vl8l8_sincospi(armpl_vsincospiq_f64),
-; ARMPL-SAME:   _ZGVsMxvl8l8_sincospi(armpl_svsincospi_f64_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N2vl8l8_sincospi(armpl_vsincospiq_f64)" }
 ; ARMPL:      attributes #[[SINCOSPIF]] = { "vector-function-abi-variant"=
-; ARMPL-SAME:    "_ZGV_LLVM_N4vl4l4_sincospif(armpl_vsincospiq_f32),
-; ARMPL-SAME:    _ZGVsMxvl4l4_sincospif(armpl_svsincospi_f32_x)" }
+; ARMPL-SAME:    "_ZGV_LLVM_N4vl4l4_sincospif(armpl_vsincospiq_f32)" }
 ; ARMPL:      attributes #[[LOG10]] = { "vector-function-abi-variant"=
 ; ARMPL-SAME:    "_ZGV_LLVM_N4v_llvm.log10.f32(armpl_vlog10q_f32),
 ; ARMPL-SAME     _ZGVsMxv_llvm.log10.f32(armpl_svlog10_f32_x)" }



More information about the llvm-branch-commits mailing list