numpy
diff --git a/.github/workflows/linux-ppc64le.yml b/.github/workflows/linux-ppc64le.yml
@@ -1,4 +1,4 @@
-name: Native ppc64le Linux Test
+name: Linux IBM tests
 
 on:
   pull_request:
@@ -19,22 +19,42 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  native_ppc64le:
-    # This job runs only in the main NumPy repository.
-    # It requires a native ppc64le GHA runner, which is not available on forks.
+  native_ibm:
+    # These jobs runs only in the main NumPy repository.
+    # It requires a native ppc64le and s390x GHA runners, which are not available on forks.
     # For more details, see: https://github.com/numpy/numpy/issues/29125
     if: github.repository == 'numpy/numpy'
-    runs-on: ubuntu-24.04-ppc64le-p10
-  
+    runs-on: ${{ matrix.config.runner }}
+
     strategy:
       fail-fast: false
       matrix:
         config:
-          - name: "GCC"
+          - name: "ppc64le/gcc - baseline(default)"
             args: "-Dallow-noblas=false"
-          - name: "clang"
+            runner: ubuntu-24.04-ppc64le-p10
+            compiler: "gcc"
+          - name: "ppc64le/clang - baseline(default)"
             args: "-Dallow-noblas=false"
-
+            runner: ubuntu-24.04-ppc64le-p10
+            compiler: "clang"
+          - name: "s390x/gcc - baseline(default)"
+            args: "-Dallow-noblas=false"
+            runner: ubuntu-24.04-s390x
+            compiler: "gcc"
+          - name: "s390x/clang - baseline(default)"
+            args: "-Dallow-noblas=false"
+            runner: ubuntu-24.04-s390x
+            compiler: "clang"
+          - name: "s390x/gcc - baseline(Z15/VXE2)"
+            args: "-Dallow-noblas=false -Dcpu-baseline=vxe2"
+            runner: ubuntu-24.04-s390x
+            compiler: "gcc"
+          - name: "s390x/clang - baseline(Z15/VXE2)"
+            args: "-Dallow-noblas=false -Dcpu-baseline=vxe2"
+            runner: ubuntu-24.04-s390x
+            compiler: "clang"
+
     name: "${{ matrix.config.name }}"
     steps:
     - uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
@@ -52,11 +72,11 @@ jobs:
         echo "/home/runner/.local/bin" >> $GITHUB_PATH
 
     - name: Install clang
-      if: matrix.config.name == 'clang'
+      if: matrix.config.compiler == 'clang'
       run: |
-        sudo apt install -y clang
-        export CC=clang
-        export CXX=clang++
+        sudo apt install -y clang-20
+        echo CC=clang-20 >> $GITHUB_ENV
+        echo CXX=clang++-20 >> $GITHUB_ENV
 
     - name: Meson Build
       run: |

diff --git a/.github/workflows/linux_qemu.yml b/.github/workflows/linux_qemu.yml
@@ -42,41 +42,6 @@ jobs:
       fail-fast: false
       matrix:
         BUILD_PROP:
-          - [
-              "ppc64le",
-              "powerpc64le-linux-gnu",
-              "ppc64le/ubuntu:22.04",
-              "-Dallow-noblas=true",
-              "test_kind or test_multiarray or test_simd or test_umath or test_ufunc",
-              "ppc64le"
-            ]
-          - [
-              "ppc64le - baseline(Power9)",
-              "powerpc64le-linux-gnu",
-              "ppc64le/ubuntu:22.04",
-              "-Dallow-noblas=true -Dcpu-baseline=vsx3",
-              "test_kind or test_multiarray or test_simd or test_umath or test_ufunc",
-              "ppc64le"
-            ]
-          - [
-              "s390x",
-              "s390x-linux-gnu",
-              "s390x/ubuntu:22.04",
-              "-Dallow-noblas=true",
-              # Skipping TestRationalFunctions.test_gcd_overflow test
-              # because of a possible qemu bug that appears to be related to int64 overflow in absolute operation.
-              # TODO(@seiko2plus): Confirm the bug and provide a minimal reproducer, then report it to upstream.
-              "(test_kind or test_multiarray or test_simd or test_umath or test_ufunc) and not test_gcd_overflow",
-              "s390x"
-            ]
-          - [
-              "s390x - baseline(Z13)",
-              "s390x-linux-gnu",
-              "s390x/ubuntu:22.04",
-              "-Dallow-noblas=true -Dcpu-baseline=vx",
-              "(test_kind or test_multiarray or test_simd or test_umath or test_ufunc) and not test_gcd_overflow",
-              "s390x"
-            ]
           - [
               "riscv64",
               "riscv64-linux-gnu",

diff --git a/numpy/_core/src/common/simd/vec/arithmetic.h b/numpy/_core/src/common/simd/vec/arithmetic.h
@@ -286,7 +286,7 @@ NPY_FINLINE npyv_u64 npyv_divc_u64(npyv_u64 a, const npyv_u64x3 divisor)
 // divide each signed 64-bit element by a precomputed divisor (round towards zero)
 NPY_FINLINE npyv_s64 npyv_divc_s64(npyv_s64 a, const npyv_s64x3 divisor)
 {
-    npyv_b64 overflow = npyv_and_b64(vec_cmpeq(a, npyv_setall_s64(-1LL << 63)), (npyv_b64)divisor.val[1]);
+    npyv_b64 overflow = npyv_and_b64(vec_cmpeq(a, npyv_setall_s64(0x8000000000000000LL)), (npyv_b64)divisor.val[1]);
     npyv_s64 d = vec_sel(divisor.val[0], npyv_setall_s64(1), overflow);
     return vec_div(a, d);
 }

diff --git a/numpy/_core/src/multiarray/compiled_base.c b/numpy/_core/src/multiarray/compiled_base.c
@@ -1628,9 +1628,29 @@ pack_inner(const char *inptr,
             #else
                 npy_uint64 arr[4] = {bb[0], bb[1], bb[2], bb[3]};
             #endif
+
+            #if NPY_BYTE_ORDER == NPY_BIG_ENDIAN
+                #if NPY_SIMD_WIDTH == 16
+                arr[0] = npy_bswap8(arr[0]);
+                #elif NPY_SIMD_WIDTH == 32
+                arr[0] = npy_bswap8(arr[0]);
+                arr[1] = npy_bswap8(arr[1]);
+                #else
+                arr[0] = npy_bswap8(arr[0]);
+                arr[1] = npy_bswap8(arr[1]);
+                arr[2] = npy_bswap8(arr[2]);
+                arr[3] = npy_bswap8(arr[3]);
+                #endif
+            #endif
                 memcpy(outptr, arr, sizeof(arr));
                 outptr += vstepx4;
             } else {
+                #if NPY_BYTE_ORDER == NPY_BIG_ENDIAN
+                bb[0] = npy_bswap8(bb[0]);
+                bb[1] = npy_bswap8(bb[1]);
+                bb[2] = npy_bswap8(bb[2]);
+                bb[3] = npy_bswap8(bb[3]);
+                #endif
                 for(int i = 0; i < 4; i++) {
                     for (int j = 0; j < vstep; j++) {
                         memcpy(outptr, (char*)&bb[i] + j, 1);
@@ -1645,6 +1665,11 @@ pack_inner(const char *inptr,
                 va = npyv_rev64_u8(va);
             }
             npy_uint64 bb = npyv_tobits_b8(npyv_cmpneq_u8(va, v_zero));
+
+            #if NPY_BYTE_ORDER == NPY_BIG_ENDIAN
+            bb = npy_bswap8(bb);
+            #endif
+
             for (int i = 0; i < vstep; ++i) {
                 memcpy(outptr, (char*)&bb + i, 1);
                 outptr += out_stride;

diff --git a/numpy/_core/tests/test_cpu_features.py b/numpy/_core/tests/test_cpu_features.py
@@ -423,7 +423,7 @@ class Test_ZARCH_Features(AbstractTest):
     features = ["VX", "VXE", "VXE2"]
 
     def load_flags(self):
-        self.load_flags_auxv()
+        self.load_flags_cpuinfo("features")
 
 
 is_arm = re.match(r"^(arm|aarch64)", machine, re.IGNORECASE)

diff --git a/numpy/f2py/_backends/meson.build.template b/numpy/f2py/_backends/meson.build.template
@@ -7,6 +7,11 @@ project('${modulename}',
                             'buildtype=${buildtype}'
                           ])
 fc = meson.get_compiler('fortran')
+cc = meson.get_compiler('c')
+
+add_project_arguments(
+  cc.get_supported_arguments( '-fno-strict-aliasing'), language : 'c'
+)
 
 py = import('python').find_installation('''${python}''', pure: false)
 py_dep = py.dependency()