[enh] Add intel compiler support

.github/workflows/c-cpp.yml

@@ -179,3 +179,50 @@ jobs:
       run: |
         docker run -v $(pwd):/xss quay.io/pypa/manylinux2014_i686 \
         /bin/bash -xc "source /xss/.github/workflows/build-test-on-32bit.sh"
+
+  SPR-icpx:
+
+    runs-on: intel-ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Install dependencies
+      run: |
+        echo "deb https://apt.repos.intel.com/oneapi all main" | sudo tee /etc/apt/sources.list.d/oneAPI.list
+        sudo add-apt-repository -y "deb https://apt.repos.intel.com/oneapi all main"
+        sudo apt update --allow-insecure-repositories
+        sudo apt --allow-unauthenticated -y install intel-oneapi-compiler-dpcpp-cpp libgtest-dev curl git python3-pip
+        sudo pip3 install meson ninja
+
+    - name: Install Intel SDE
+      run: |
+        curl -o /tmp/sde.tar.xz https://downloadmirror.intel.com/784319/sde-external-9.24.0-2023-07-13-lin.tar.xz
+        mkdir /tmp/sde && tar -xvf /tmp/sde.tar.xz -C /tmp/sde/
+        sudo mv /tmp/sde/* /opt/sde && sudo ln -s /opt/sde/sde64 /usr/bin/sde
+
+    - name: Build examples
+      env:
+        CXX: icpx
+        CXXFLAGS: -fp-model=precise
+      run: |
+        source /opt/intel/oneapi/setvars.sh
+        cd examples
+        make all
+
+    - name: Build
+      env:
+        CXX: icpx
+        CXXFLAGS: -fp-model=precise
+      run: |
+        make clean
+        source /opt/intel/oneapi/setvars.sh
+        icpx --version
+        meson setup -Dbuild_tests=true --warnlevel 2 --werror --buildtype release builddir
+        cd builddir
+        ninja
+
+    - name: Run test suite on SPR
+      run: |
+        source /opt/intel/oneapi/setvars.sh
+        sde -spr -- ./builddir/testexe

examples/Makefile

@@ -1,5 +1,5 @@
 CXX ?= g++-12
-CFLAGS = -I../src -std=c++17 -O3
+CFLAGS = -I../src -std=c++17 -O3 $(if $(CXXFLAGS),$(CXXFLAGS),)
 EXE = qsort32avx2 argsort kvsort qsortfp16 qsort16 qsort32 qsort64
 
 default: all

lib/x86simdsort.cpp

@@ -10,7 +10,7 @@ static int check_cpu_feature_support(std::string_view cpufeature)
     const char *disable_avx512 = std::getenv("XSS_DISABLE_AVX512");
 
     if ((cpufeature == "avx512_spr") && (!disable_avx512))
-#ifdef __FLT16_MAX__
+#if defined(__FLT16_MAX__) && !defined(__INTEL_LLVM_COMPILER)
         return __builtin_cpu_supports("avx512f")
                 && __builtin_cpu_supports("avx512fp16")
                 && __builtin_cpu_supports("avx512vbmi2");

src/avx2-32bit-qsort.hpp

@@ -418,12 +418,10 @@ struct avx2_vector<float> {
     template <int type>
     static opmask_t fpclass(reg_t x)
     {
-        if constexpr (type == (0x01 | 0x80)) {
-            return _mm256_castps_si256(_mm256_cmp_ps(x, x, _CMP_UNORD_Q));
-        }
-        else {
+        if constexpr (type != (0x01 | 0x80)) {
             static_assert(type == (0x01 | 0x80), "should not reach here");
         }
+        return _mm256_castps_si256(_mm256_cmp_ps(x, x, _CMP_UNORD_Q));
     }
     template <int scale>
     static reg_t

src/avx2-64bit-qsort.hpp

@@ -433,12 +433,10 @@ struct avx2_vector<double> {
     template <int type>
     static opmask_t fpclass(reg_t x)
     {
-        if constexpr (type == (0x01 | 0x80)) {
-            return _mm256_castpd_si256(_mm256_cmp_pd(x, x, _CMP_UNORD_Q));
-        }
-        else {
+        if constexpr (type != (0x01 | 0x80)) {
             static_assert(type == (0x01 | 0x80), "should not reach here");
         }
+        return _mm256_castpd_si256(_mm256_cmp_pd(x, x, _CMP_UNORD_Q));
     }
     static ymmi_t seti(int v1, int v2, int v3, int v4)
     {

src/xss-common-includes.h

@@ -65,7 +65,9 @@
 #define UNLIKELY(x) (x)
 #endif
 
-#if __GNUC__ >= 8 and !defined(__SANITIZE_ADDRESS__)
+#if defined(__INTEL_COMPILER) and !defined(__SANITIZE_ADDRESS__)
+#define X86_SIMD_SORT_UNROLL_LOOP(num) PRAGMA(unroll(num))
+#elif __GNUC__ >= 8 and !defined(__SANITIZE_ADDRESS__)
 #define X86_SIMD_SORT_UNROLL_LOOP(num) PRAGMA(GCC unroll num)
 #else
 #define X86_SIMD_SORT_UNROLL_LOOP(num)