Merge pull request #91 from r-devulap/reorg

Reorganize code and add examples to build

Author: Raghuveer Devulapalli

.github/workflows/c-cpp.yml

@@ -17,7 +17,7 @@ jobs:
     - name: Install dependencies
       run: |
         sudo apt update
-        sudo apt -y install g++-9 libgtest-dev meson curl git cmake
+        sudo apt -y install g++-9 libgtest-dev meson curl git
 
     - name: Install Intel SDE
       run: |
@@ -47,7 +47,7 @@ jobs:
     - name: Install dependencies
       run: |
         sudo apt update
-        sudo apt -y install g++-10 libgtest-dev meson curl git cmake
+        sudo apt -y install g++-10 libgtest-dev meson curl git
 
     - name: Install Intel SDE
       run: |
@@ -77,7 +77,7 @@ jobs:
     - name: Install dependencies
       run: |
         sudo apt update
-        sudo apt -y install g++-11 libgtest-dev meson curl git cmake
+        sudo apt -y install g++-11 libgtest-dev meson curl git
 
     - name: Install Intel SDE
       run: |
@@ -106,14 +106,21 @@ jobs:
     - name: Install dependencies
       run: |
         sudo apt update
-        sudo apt -y install g++-13 libgtest-dev meson curl git cmake
+        sudo apt -y install g++-13 libgtest-dev meson curl git
 
     - 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: g++-13
+      run: |
+        cd examples
+        make all
+
     - name: Build
       env:
         CXX: g++-13
@@ -136,7 +143,7 @@ jobs:
     - name: Install dependencies
       run: |
         sudo apt update
-        sudo apt -y install g++-13 libgtest-dev meson curl git cmake
+        sudo apt -y install g++-13 libgtest-dev meson curl git
 
     - name: Install Intel SDE
       run: |

examples/Makefile

@@ -0,0 +1,27 @@
+CXX ?= g++-12
+CFLAGS = -I../src -std=c++17 -O3
+EXE = argsort kvsort qsortfp16 qsort16 qsort32 qsort64
+
+default: all
+all : $(EXE)
+
+qsortfp16: avx512fp-16bit-qsort.cpp
+	     $(CXX) -o qsortfp16 -march=sapphirerapids $(CFLAGS) avx512fp-16bit-qsort.cpp
+
+qsort16: avx512-16bit-qsort.cpp
+	     $(CXX) -o qsort16 -march=icelake-client $(CFLAGS) avx512-16bit-qsort.cpp
+
+qsort32: avx512-32bit-qsort.cpp
+	     $(CXX) -o qsort32 -march=skylake-avx512 $(CFLAGS) avx512-32bit-qsort.cpp
+
+qsort64: avx512-64bit-qsort.cpp
+	     $(CXX) -o qsort64 -march=skylake-avx512 $(CFLAGS) avx512-64bit-qsort.cpp
+
+argsort: avx512-argsort.cpp
+	     $(CXX) -o argsort -march=skylake-avx512 $(CFLAGS) avx512-argsort.cpp
+
+kvsort: avx512-kv.cpp
+	     $(CXX) -o kvsort -march=skylake-avx512 $(CFLAGS) avx512-kv.cpp
+
+clean:
+	$(RM) $(EXE)

examples/avx512-16bit-qsort.cpp

@@ -0,0 +1,10 @@
+#include "avx512-16bit-qsort.hpp"
+
+int main() {
+    const int size = 1000;
+    short arr[size];
+    avx512_qsort(arr, size);
+    avx512_qselect(arr, 10, size);
+    avx512_partial_qsort(arr, 10, size);
+    return 0;
+}

examples/avx512-32bit-qsort.cpp

@@ -0,0 +1,10 @@
+#include "avx512-32bit-qsort.hpp"
+
+int main() {
+    const int size = 1000;
+    float arr[size];
+    avx512_qsort(arr, size);
+    avx512_qselect(arr, 10, size);
+    avx512_partial_qsort(arr, 10, size);
+    return 0;
+}

examples/avx512-64bit-qsort.cpp

@@ -0,0 +1,10 @@
+#include "avx512-64bit-qsort.hpp"
+
+int main() {
+    const int size = 1000;
+    double arr[size];
+    avx512_qsort(arr, size);
+    avx512_qselect(arr, 10, size);
+    avx512_partial_qsort(arr, 10, size);
+    return 0;
+}

examples/avx512-argsort.cpp

@@ -0,0 +1,9 @@
+#include "avx512-64bit-argsort.hpp"
+
+int main() {
+    const int size = 1000;
+    float arr[size];
+    std::vector<size_t> arg1 = avx512_argsort(arr, size);
+    std::vector<size_t> arg2 = avx512_argselect(arr, 10, size);
+    return 0;
+}

examples/avx512-kv.cpp

@@ -0,0 +1,18 @@
+#include "avx512-64bit-keyvaluesort.hpp"
+
+int main() {
+    const int size = 1000;
+    int64_t arr1[size];
+    uint64_t arr2[size];
+    double arr3[size];
+    avx512_qsort_kv(arr1, arr1, size);
+    avx512_qsort_kv(arr1, arr2, size);
+    avx512_qsort_kv(arr1, arr3, size);
+    avx512_qsort_kv(arr2, arr1, size);
+    avx512_qsort_kv(arr2, arr2, size);
+    avx512_qsort_kv(arr2, arr3, size);
+    avx512_qsort_kv(arr3, arr1, size);
+    avx512_qsort_kv(arr3, arr2, size);
+    avx512_qsort_kv(arr3, arr3, size);
+    return 0;
+}

examples/avx512fp-16bit-qsort.cpp

@@ -0,0 +1,10 @@
+#include "avx512fp16-16bit-qsort.hpp"
+
+int main() {
+    const int size = 1000;
+    _Float16 arr[size];
+    avx512_qsort(arr, size);
+    avx512_qselect(arr, 10, size);
+    avx512_partial_qsort(arr, 10, size);
+    return 0;
+}