https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106069
--- Comment #4 from luoxhu at gcc dot gnu.org --- Reduced to: #include <stdio.h> extern "C" void *memcpy(void *, const void *, unsigned long); typedef __attribute__((altivec(vector__))) unsigned native_simd_type; union { native_simd_type V; int R[4]; } store_le_vec; struct S { S() = default; S(unsigned B0) { native_simd_type val{B0}; m_simd = val; } void store_le(unsigned char out[]) { store_le_vec.V = m_simd; unsigned int x0 = store_le_vec.R[0]; memcpy(out, &x0, 1); } static void transpose(S &B0, S B1, S B2, S B3) { native_simd_type T0 = __builtin_vec_mergeh(B0.m_simd, B2.m_simd); native_simd_type T1 = __builtin_vec_mergeh(B1.m_simd, B3.m_simd); native_simd_type T2 = __builtin_vec_mergel(B0.m_simd, B2.m_simd); native_simd_type T3 = __builtin_vec_mergel(B1.m_simd, B3.m_simd); B0 = __builtin_vec_mergeh(T0, T1); B3 = __builtin_vec_mergel(T2, T3); printf ("B0: %x, %x,%x,%x\n", B0.m_simd[0], B0.m_simd[1], B0.m_simd[2], B0.m_simd[3]); } S(native_simd_type x) : m_simd(x) {} native_simd_type m_simd; }; void foo (unsigned char output[], unsigned state[], native_simd_type R0, native_simd_type R1, native_simd_type R2, native_simd_type R3) { S R00; R00.m_simd = R0; S R01; R01.m_simd = R1; S R02; R02.m_simd = R2; S R03; R03.m_simd = R3; S::transpose(R00, R01, R02, R03); R00.store_le(output); } unsigned char res[1]; unsigned main_state[]{1634760805, 60878, 2036477234, 6, 0, 825562964, 1471091955, 1346092787, 506976774, 4197066702, 518848283, 118491664, 0, 0, 0, 0}; int main () { native_simd_type R0 = native_simd_type {0x41fcef98, 0,0,0}; native_simd_type R1 = native_simd_type {0x91648e8b, 0,0,0}; native_simd_type R2 = native_simd_type {0x7dca18c6, 0,0,0}; native_simd_type R3 = native_simd_type {0x61707865, 0,0,0}; foo (res, main_state, R0, R1, R2, R3); if (res[0] != 152) __builtin_abort(); }