diff --git a/CMakeLists.txt b/CMakeLists.txt
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -244,6 +244,15 @@
 if(NOT DEFINED X86CPU_ARCH AND ARCH STREQUAL "x86")
   include(DetectArchitecture)
   detect_x86_cpu_architecture(X86CPU_ARCH)
+  detect_x86_feature(sse HAVE_X86_SSE_INSTRUCTIONS)
+  detect_x86_feature(sse2 HAVE_X86_SSE2_INSTRUCTIONS)
+  detect_x86_feature(avx HAVE_X86_AVX_INSTRUCTIONS)
+  detect_x86_feature(avx2 HAVE_X86_AVX2_INSTRUCTIONS)
+  detect_x86_feature(avx512f HAVE_X86_AVX512F_INSTRUCTIONS)
+endif()
+if(NOT HAVE_LIBMVEC_X86 AND ARCH STREQUAL "x86")
+  include(DetectVectorLibrary)
+  detect_libmvec_x86(HAVE_LIBMVEC_X86)
 endif()
 if(NOT DEFINED ENDIAN)
   include(TestBigEndian)
diff --git a/SingleSource/UnitTests/Vectorizer/CMakeLists.txt b/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
--- a/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
+++ b/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
@@ -1,2 +1,3 @@
+add_subdirectory(Veclib)
 llvm_singlesource()
 set_property(TARGET runtime-checks PROPERTY CXX_STANDARD 17)
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/CMakeLists.txt b/SingleSource/UnitTests/Vectorizer/Veclib/CMakeLists.txt
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/CMakeLists.txt
@@ -0,0 +1,30 @@
+set(FP_TOLERANCE 0.000002)
+
+function(llvm_singlesource_with_cflags_ldflags prefix additional_cflags additional_ldflags)
+    list(APPEND CFLAGS ${additional_cflags})
+    list(APPEND LDFLAGS ${additional_ldflags})
+    llvm_singlesource(PREFIX ${prefix})
+endfunction(llvm_singlesource_with_cflags_ldflags)
+
+if(HAVE_LIBMVEC_X86)
+    check_c_compiler_flag(-fveclib=libmvec COMPILER_HAS_FVECLIB_LIBMVEC_FLAG)
+    if(COMPILER_HAS_FVECLIB_LIBMVEC_FLAG)
+        llvm_singlesource_with_cflags_ldflags("libmvec-native-" "-fveclib=libmvec;-O2;-march=native" "-lm;-fveclib=libmvec")
+        if(HAVE_X86_SSE_INSTRUCTIONS)
+            llvm_singlesource_with_cflags_ldflags("libmvec-sse-" "-fveclib=libmvec;-O2;-msse" "-lm;-fveclib=libmvec")
+        endif()
+        if(HAVE_X86_SSE2_INSTRUCTIONS)
+            llvm_singlesource_with_cflags_ldflags("libmvec-sse2-" "-fveclib=libmvec;-O2;-msse2" "-lm;-fveclib=libmvec")
+        endif()
+        if(HAVE_X86_AVX_INSTRUCTIONS)
+            llvm_singlesource_with_cflags_ldflags("libmvec-avx-" "-fveclib=libmvec;-O2;-mavx" "-lm;-fveclib=libmvec")
+        endif()
+        if(HAVE_X86_AVX2_INSTRUCTIONS)
+            llvm_singlesource_with_cflags_ldflags("libmvec-avx2-" "-fveclib=libmvec;-O2;-mavx2" "-lm;-fveclib=libmvec")
+        endif()
+        if(HAVE_X86_AVX512F_INSTRUCTIONS)
+            llvm_singlesource_with_cflags_ldflags("libmvec-avx512f-" "-fveclib=libmvec;-O2;-mavx512f" "-lm;-fveclib=libmvec")
+        endif()
+    endif()
+endif()
+# Other vector math libraries may be added here...
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/sincos.h b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.h
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.h
@@ -0,0 +1,145 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <math.h>
+
+// inner loop vectorization with linear access
+void sincos_arr(REAL* sines, REAL* cosines, REAL* phases, int size) {
+    for (int i=0; i<size; i++) {
+        SINCOS(phases[i], sines+i, cosines+i);
+    }
+}
+
+// outer loop vectorization with linear access
+void sincos_arr_nested(REAL* sines, REAL* cosines, REAL* phases, int size, int nests) {
+    for (int i=0; i<size; i++) {
+        SINCOS(phases[i], sines+i, cosines+i);
+        for (int k=0; k<nests; k++) {
+            SINCOS(cosines[i]-sines[i], sines+i, cosines+i);
+        }
+    }
+}
+
+// outer loop vectorization with linear access, inner loop prevented from being unrolled
+void sincos_arr_nested_nounroll(REAL* sines, REAL* cosines, REAL* phases, int size, int nests) {
+    for (int i=0; i<size; i++) {
+        SINCOS(phases[i], sines+i, cosines+i);
+#pragma unroll 1
+        for (int k=0; k<nests; k++) {
+            SINCOS(cosines[i]-sines[i], sines+i, cosines+i);
+        }
+    }
+}
+
+// inner loop vectorization with nonlinear access
+void sincos_arr_scrambled(REAL* sines, REAL* cosines, REAL* phases, int* indices, int size) {
+    for (int i=0; i<size; i++) {
+        int j = indices[i];
+        SINCOS(phases[j], sines+j, cosines+j);
+    }
+}
+
+// outer loop vectorization with nonlinear access
+void sincos_arr_scrambled_nested(REAL* sines, REAL* cosines, REAL* phases, int* indices, int size, int nests) {
+    for (int i=0; i<size; i++) {
+        int j = indices[i];
+        SINCOS(phases[j], sines+j, cosines+j);
+        for (int k=0; k<nests; k++) {
+            SINCOS(cosines[j]-sines[j], sines+j, cosines+j);
+        }
+    }
+}
+
+// outer loop vectorization with nonlinear access, inner loop prevented from being unrolled
+void sincos_arr_scrambled_nested_nounroll(REAL* sines, REAL* cosines, REAL* phases, int* indices, int size, int nests) {
+    for (int i=0; i<size; i++) {
+        int j = indices[i];
+        SINCOS(phases[j], sines+j, cosines+j);
+#pragma unroll 1
+        for (int k=0; k<nests; k++) {
+            SINCOS(cosines[j]-sines[j], sines+j, cosines+j);
+        }
+    }
+}
+
+// returns true (=failure) iff ULP error is larger than max_ulp_err, with a simplified definition of ULP
+int check_ULP(REAL arg, REAL val, REAL ref, REAL max_ulp_err, int index, const char* msg1, const char* msg2, int verbose)
+{
+    REAL ulp = 0.5 * (NEXTAFTER(ref, INFINITY) - NEXTAFTER(ref, -INFINITY));
+    if (fabs(val - ref) > max_ulp_err * ulp) {
+        printf("%s.%s FAILED at %d: argument %g, value %g, reference %g, difference %g, (%g ULP).\n",
+               msg1, msg2, index, arg, val, ref, (val-ref), fabs(val-ref)/ulp);
+        return 1;
+    } else if (verbose) {
+        printf("%s.%s at %2d: argument %2g, value %10.7f, reference %10.7f.\n",
+               msg1, msg2, index, arg, val, ref);
+    }
+    return 0;
+}
+
+int check_arr(REAL* sines, REAL* coses, REAL* phases, int* indices, int size, int nests, REAL max_ulp_err, const char* msg)
+{
+    int fail = 0;
+
+    for (int i = 0; i < size; i++) {
+        int j = indices ? indices[i] : i;
+        long double ref_sin = sinl(phases[j]);
+        long double ref_cos = cosl(phases[j]);
+        for (int k=0; k<nests; k++) {
+                REAL arg = ref_cos - ref_sin;
+                ref_sin = sinl(arg);
+                ref_cos = cosl(arg);
+            }
+        fail |= check_ULP(phases[j], sines[j], (REAL)ref_sin, max_ulp_err, i, msg, "sin", i%8 == 0);
+        fail |= check_ULP(phases[j], coses[j], (REAL)ref_cos, max_ulp_err, i, msg, "cos", i%8 == 0);
+    }
+    return fail;
+}
+
+int main(int argc, char *argv[])
+{
+    argc |= 1; // ensure argc is odd for better test coverage
+    const int loops = argc;
+    const int N = 26 + argc;
+    const int nests = 34 + argc;
+    int indices[N];
+    REAL phases[N], sines[N], coses[N];
+    int fail = 0;
+    const REAL MAX_ULP_ERR_NESTED = 64;
+    const REAL MAX_ULP_ERR = 16;
+
+    for (int l=0; l<loops; l++) {
+        // test with linear access:
+        for (int i = 0; i < N; i++) {
+            phases[i] = i;
+            indices[i] = i;
+            sines[i] = 0.0 / 0.0;
+            coses[i] = 0.0 / 0.0;
+        }
+        sincos_arr(sines, coses, phases, N);
+        fail |= check_arr(sines, coses, phases, NULL, N, 0, MAX_ULP_ERR, "sincos_arr");
+        sincos_arr_nested(sines, coses, phases, N, nests);
+        fail |= check_arr(sines, coses, phases, NULL, N, nests, MAX_ULP_ERR_NESTED, "sincos_arr_nested");
+        sincos_arr_nested_nounroll(sines, coses, phases, N, nests);
+        fail |= check_arr(sines, coses, phases, NULL, N, nests, MAX_ULP_ERR_NESTED, "sincos_arr_nested_nounroll");
+
+        // test with nonlinear access:
+        for (int i = 0; i < N; i++) {
+            indices[i] = (i < 2) ? 1 : (indices[i - 2] + indices[i - 1]) % N;
+            sines[i] = 0.0 / 0.0;
+            coses[i] = 0.0 / 0.0;
+        }
+        sincos_arr_scrambled(sines, coses, phases, indices, N);
+        fail |= check_arr(sines, coses, phases, indices, N, 0, MAX_ULP_ERR, "sincos_arr_scrambled");
+        sincos_arr_scrambled_nested(sines, coses, phases, indices, N, nests);
+        fail |= check_arr(sines, coses, phases, indices, N, nests, MAX_ULP_ERR_NESTED, "sincos_arr_scrambled_nested");
+        sincos_arr_scrambled_nested_nounroll(sines, coses, phases, indices, N, nests);
+        fail |= check_arr(sines, coses, phases, indices, N, nests, MAX_ULP_ERR_NESTED, "sincos_arr_scrambled_nested_nounroll");
+    }
+    if (fail) {
+        printf("FAILED!\n");
+    } else {
+        printf("Passed.\n");
+    }
+    return fail;
+}
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/sincos.c b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.c
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.c
@@ -0,0 +1,5 @@
+#define REAL double
+#define SINCOS sincos
+#define NEXTAFTER nextafter
+
+#include "sincos.h"
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/sincos.reference_output b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.reference_output
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/sincos.reference_output
@@ -0,0 +1,50 @@
+sincos_arr.sin at  0: argument  0, value  0.0000000, reference  0.0000000.
+sincos_arr.cos at  0: argument  0, value  1.0000000, reference  1.0000000.
+sincos_arr.sin at  8: argument  8, value  0.9893582, reference  0.9893582.
+sincos_arr.cos at  8: argument  8, value -0.1455000, reference -0.1455000.
+sincos_arr.sin at 16: argument 16, value -0.2879033, reference -0.2879033.
+sincos_arr.cos at 16: argument 16, value -0.9576595, reference -0.9576595.
+sincos_arr.sin at 24: argument 24, value -0.9055784, reference -0.9055784.
+sincos_arr.cos at 24: argument 24, value  0.4241790, reference  0.4241790.
+sincos_arr_nested.sin at  0: argument  0, value  0.9875437, reference  0.9875437.
+sincos_arr_nested.cos at  0: argument  0, value  0.1573452, reference  0.1573452.
+sincos_arr_nested.sin at  8: argument  8, value -0.7380653, reference -0.7380653.
+sincos_arr_nested.cos at  8: argument  8, value  0.6747293, reference  0.6747293.
+sincos_arr_nested.sin at 16: argument 16, value -0.7380653, reference -0.7380653.
+sincos_arr_nested.cos at 16: argument 16, value  0.6747293, reference  0.6747293.
+sincos_arr_nested.sin at 24: argument 24, value  0.9875437, reference  0.9875437.
+sincos_arr_nested.cos at 24: argument 24, value  0.1573452, reference  0.1573452.
+sincos_arr_nested_nounroll.sin at  0: argument  0, value  0.9875437, reference  0.9875437.
+sincos_arr_nested_nounroll.cos at  0: argument  0, value  0.1573452, reference  0.1573452.
+sincos_arr_nested_nounroll.sin at  8: argument  8, value -0.7380653, reference -0.7380653.
+sincos_arr_nested_nounroll.cos at  8: argument  8, value  0.6747293, reference  0.6747293.
+sincos_arr_nested_nounroll.sin at 16: argument 16, value -0.7380653, reference -0.7380653.
+sincos_arr_nested_nounroll.cos at 16: argument 16, value  0.6747293, reference  0.6747293.
+sincos_arr_nested_nounroll.sin at 24: argument 24, value  0.9875437, reference  0.9875437.
+sincos_arr_nested_nounroll.cos at 24: argument 24, value  0.1573452, reference  0.1573452.
+sincos_arr_scrambled.sin at  0: argument  1, value  0.8414710, reference  0.8414710.
+sincos_arr_scrambled.cos at  0: argument  1, value  0.5403023, reference  0.5403023.
+sincos_arr_scrambled.sin at  8: argument  7, value  0.6569866, reference  0.6569866.
+sincos_arr_scrambled.cos at  8: argument  7, value  0.7539023, reference  0.7539023.
+sincos_arr_scrambled.sin at 16: argument  4, value -0.7568025, reference -0.7568025.
+sincos_arr_scrambled.cos at 16: argument  4, value -0.6536436, reference -0.6536436.
+sincos_arr_scrambled.sin at 24: argument 19, value  0.1498772, reference  0.1498772.
+sincos_arr_scrambled.cos at 24: argument 19, value  0.9887046, reference  0.9887046.
+sincos_arr_scrambled_nested.sin at  0: argument  1, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested.cos at  0: argument  1, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested.sin at  8: argument  7, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested.cos at  8: argument  7, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested.sin at 16: argument  4, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested.cos at 16: argument  4, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested.sin at 24: argument 19, value  0.9875437, reference  0.9875437.
+sincos_arr_scrambled_nested.cos at 24: argument 19, value  0.1573452, reference  0.1573452.
+sincos_arr_scrambled_nested_nounroll.sin at  0: argument  1, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested_nounroll.cos at  0: argument  1, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested_nounroll.sin at  8: argument  7, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested_nounroll.cos at  8: argument  7, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested_nounroll.sin at 16: argument  4, value -0.7380653, reference -0.7380653.
+sincos_arr_scrambled_nested_nounroll.cos at 16: argument  4, value  0.6747293, reference  0.6747293.
+sincos_arr_scrambled_nested_nounroll.sin at 24: argument 19, value  0.9875437, reference  0.9875437.
+sincos_arr_scrambled_nested_nounroll.cos at 24: argument 19, value  0.1573452, reference  0.1573452.
+Passed.
+exit 0
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.c b/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.c
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.c
@@ -0,0 +1,5 @@
+#define REAL float
+#define SINCOS sincosf
+#define NEXTAFTER nextafterf
+
+#include "sincos.h"
diff --git a/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.reference_output b/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.reference_output
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/Veclib/sincosf.reference_output
@@ -0,0 +1,50 @@
+sincos_arr.sin at  0: argument  0, value  0.0000000, reference  0.0000000.
+sincos_arr.cos at  0: argument  0, value  1.0000000, reference  1.0000000.
+sincos_arr.sin at  8: argument  8, value  0.9893582, reference  0.9893582.
+sincos_arr.cos at  8: argument  8, value -0.1455000, reference -0.1455000.
+sincos_arr.sin at 16: argument 16, value -0.2879033, reference -0.2879033.
+sincos_arr.cos at 16: argument 16, value -0.9576595, reference -0.9576595.
+sincos_arr.sin at 24: argument 24, value -0.9055784, reference -0.9055784.
+sincos_arr.cos at 24: argument 24, value  0.4241790, reference  0.4241790.
+sincos_arr_nested.sin at  0: argument  0, value  0.9875436, reference  0.9875436.
+sincos_arr_nested.cos at  0: argument  0, value  0.1573451, reference  0.1573451.
+sincos_arr_nested.sin at  8: argument  8, value -0.7380654, reference -0.7380654.
+sincos_arr_nested.cos at  8: argument  8, value  0.6747292, reference  0.6747292.
+sincos_arr_nested.sin at 16: argument 16, value -0.7380654, reference -0.7380654.
+sincos_arr_nested.cos at 16: argument 16, value  0.6747292, reference  0.6747292.
+sincos_arr_nested.sin at 24: argument 24, value  0.9875436, reference  0.9875436.
+sincos_arr_nested.cos at 24: argument 24, value  0.1573451, reference  0.1573451.
+sincos_arr_nested_nounroll.sin at  0: argument  0, value  0.9875436, reference  0.9875436.
+sincos_arr_nested_nounroll.cos at  0: argument  0, value  0.1573451, reference  0.1573451.
+sincos_arr_nested_nounroll.sin at  8: argument  8, value -0.7380654, reference -0.7380654.
+sincos_arr_nested_nounroll.cos at  8: argument  8, value  0.6747292, reference  0.6747292.
+sincos_arr_nested_nounroll.sin at 16: argument 16, value -0.7380654, reference -0.7380654.
+sincos_arr_nested_nounroll.cos at 16: argument 16, value  0.6747292, reference  0.6747292.
+sincos_arr_nested_nounroll.sin at 24: argument 24, value  0.9875436, reference  0.9875436.
+sincos_arr_nested_nounroll.cos at 24: argument 24, value  0.1573451, reference  0.1573451.
+sincos_arr_scrambled.sin at  0: argument  1, value  0.8414710, reference  0.8414710.
+sincos_arr_scrambled.cos at  0: argument  1, value  0.5403023, reference  0.5403023.
+sincos_arr_scrambled.sin at  8: argument  7, value  0.6569866, reference  0.6569866.
+sincos_arr_scrambled.cos at  8: argument  7, value  0.7539023, reference  0.7539023.
+sincos_arr_scrambled.sin at 16: argument  4, value -0.7568025, reference -0.7568025.
+sincos_arr_scrambled.cos at 16: argument  4, value -0.6536436, reference -0.6536436.
+sincos_arr_scrambled.sin at 24: argument 19, value  0.1498772, reference  0.1498772.
+sincos_arr_scrambled.cos at 24: argument 19, value  0.9887046, reference  0.9887046.
+sincos_arr_scrambled_nested.sin at  0: argument  1, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested.cos at  0: argument  1, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested.sin at  8: argument  7, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested.cos at  8: argument  7, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested.sin at 16: argument  4, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested.cos at 16: argument  4, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested.sin at 24: argument 19, value  0.9875436, reference  0.9875436.
+sincos_arr_scrambled_nested.cos at 24: argument 19, value  0.1573451, reference  0.1573451.
+sincos_arr_scrambled_nested_nounroll.sin at  0: argument  1, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested_nounroll.cos at  0: argument  1, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested_nounroll.sin at  8: argument  7, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested_nounroll.cos at  8: argument  7, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested_nounroll.sin at 16: argument  4, value -0.7380654, reference -0.7380654.
+sincos_arr_scrambled_nested_nounroll.cos at 16: argument  4, value  0.6747292, reference  0.6747292.
+sincos_arr_scrambled_nested_nounroll.sin at 24: argument 19, value  0.9875436, reference  0.9875436.
+sincos_arr_scrambled_nested_nounroll.cos at 24: argument 19, value  0.1573451, reference  0.1573451.
+Passed.
+exit 0
diff --git a/cmake/modules/DetectArchitecture.cmake b/cmake/modules/DetectArchitecture.cmake
--- a/cmake/modules/DetectArchitecture.cmake
+++ b/cmake/modules/DetectArchitecture.cmake
@@ -60,3 +60,33 @@
   endif()
 
 endfunction(detect_x86_cpu_architecture)
+
+#
+# Performs a try_run to check cpu feature flag of target
+#
+
+function(detect_x86_feature feature variable)
+  try_run(HAVE_RUN_CPU_FEATURE_${variable} HAVE_COMPILE_CPU_FEATURE_${variable}
+          ${CMAKE_BINARY_DIR}
+          ${CMAKE_SOURCE_DIR}/cmake/modules/DetectX86FeatureFlag.c
+          COMPILE_DEFINITIONS -DFEATURE_FLAG=${feature}
+          COMPILE_OUTPUT_VARIABLE COMP_OUTPUT
+          RUN_OUTPUT_VARIABLE RUN_OUTPUT)
+
+  if(HAVE_COMPILE_CPU_FEATURE_${variable} AND NOT (HAVE_RUN_CPU_FEATURE_${variable} STREQUAL  FAILED_TO_RUN))
+    if(RUN_OUTPUT MATCHES "^(YES|NO)$")
+      message(STATUS "Check target cpu feature ${feature}: ${RUN_OUTPUT}")
+      set(${variable} ${RUN_OUTPUT} PARENT_SCOPE)
+    else()
+      message(SEND_ERROR "Could not detect target cpu feature ${feature}!")
+      file(APPEND ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeError.log
+              "Determining the system cpu feature failed with the following output:\n${COMP_OUTPUT}\n${RUN_OUTPUT}")
+    endif()
+  else()
+    message(STATUS "Check target system for feature ${feature} - failed")
+    file(APPEND ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeError.log
+            "Determining the system cpu feature failed with the following output:\n${COMP_OUTPUT}\n${RUN_OUTPUT}")
+    set(${variable} PARENT_SCOPE)
+  endif()
+
+endfunction(detect_x86_feature)
diff --git a/cmake/modules/DetectLibmvecX86.c b/cmake/modules/DetectLibmvecX86.c
new file mode 100644
--- /dev/null
+++ b/cmake/modules/DetectLibmvecX86.c
@@ -0,0 +1,33 @@
+#define _GNU_SOURCE
+
+#include <bits/wordsize.h>
+
+typedef float __m128 __attribute__((__vector_size__(16), __aligned__(16)));
+
+#if __WORDSIZE==32
+void _ZGVbN4vvv_sincosf(__m128 x, __m128 sinptr, __m128 cosptr);
+#else
+void _ZGVbN4vvv_sincosf(__m128 x, __m128 sinptrlo, __m128 sinptrhi, __m128 cosptrlo, __m128 cosptrhi);
+#endif
+
+int main(void) {
+    union {__m128 vec; float arr[4];} x, sines, coses;
+    union {__m128 vec[2]; float* arr[4];} sinptr, cosptr;
+    for (int i=0; i<4; i++) {
+        x.arr[i] = 0.1f * i;
+        sinptr.arr[i] = &sines.arr[i];
+        cosptr.arr[i] = &coses.arr[i];
+    }
+    // use function from libmvec (the one we have a test for):
+#if __WORDSIZE==32
+    _ZGVbN4vvv_sincosf(x.vec, sinptr.vec[0], cosptr.vec[0]);
+#else
+    _ZGVbN4vvv_sincosf(x.vec, sinptr.vec[0], sinptr.vec[1], cosptr.vec[0], cosptr.vec[1]);
+#endif
+    // ensure the call cannot get optimized out:
+    int sin_is_less_than_cos = 1;
+    for (int i=0; i<4; i++) {
+        sin_is_less_than_cos &= (sines.arr[i] < coses.arr[i]);
+    }
+    return !sin_is_less_than_cos;
+}
diff --git a/cmake/modules/DetectVectorLibrary.cmake b/cmake/modules/DetectVectorLibrary.cmake
new file mode 100644
--- /dev/null
+++ b/cmake/modules/DetectVectorLibrary.cmake
@@ -0,0 +1,28 @@
+##===- DetectVectorLibrary.cmake ------------------------------------------===##
+#
+# Performs a try_run to determine if a vector library is available.
+#
+##===----------------------------------------------------------------------===##
+
+#
+# Performs a try_run to determine if libmvec-x86 is available
+#
+
+function(detect_libmvec_x86 variable)
+  set(CMAKE_C_FLAGS -msse)
+  try_run(HAVE_RUN_${variable} HAVE_COMPILE_${variable}
+    ${CMAKE_BINARY_DIR}
+    ${CMAKE_SOURCE_DIR}/cmake/modules/DetectLibmvecX86.c
+    LINK_LIBRARIES -lmvec)
+
+  if(HAVE_COMPILE_${variable} AND NOT (HAVE_RUN_${variable} STREQUAL  FAILED_TO_RUN))
+    set(HAVE_LIBMVEC_X86 YES)
+  else()
+    set(HAVE_LIBMVEC_X86 NO)
+  endif()
+  set(${variable} ${HAVE_LIBMVEC_X86} PARENT_SCOPE)
+  message(STATUS "Check libmvec X86 vector math library available: ${HAVE_LIBMVEC_X86}")
+
+endfunction(detect_libmvec_x86)
+
+# Add other vector libraries here...
diff --git a/cmake/modules/DetectX86FeatureFlag.c b/cmake/modules/DetectX86FeatureFlag.c
new file mode 100644
--- /dev/null
+++ b/cmake/modules/DetectX86FeatureFlag.c
@@ -0,0 +1,14 @@
+#include <stdio.h>
+
+#define xstr(s) str(s)
+#define str(s) #s
+
+int main(void) {
+  __builtin_cpu_init();
+  if (__builtin_cpu_supports(xstr(FEATURE_FLAG))) {
+      printf("YES");
+  } else {
+      printf("NO");
+  }
+  return 0;
+}