https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108707
Bug ID: 108707 Summary: suboptimal allocation with same memory op for many different instructions. Product: gcc Version: 13.0 Status: UNCONFIRMED Severity: normal Priority: P3 Component: rtl-optimization Assignee: unassigned at gcc dot gnu.org Reporter: crazylht at gmail dot com Target Milestone: --- #include<immintrin.h> void foo (__m512* pv, float* __restrict ps, int n, __m512* pdest, __m512* p1, __m512* p2, __m512* p3) { __m512 a = _mm512_setzero_ps (); __m512 b = a; __m512 c = a; for (int i = 0; i != n ;i++) { a = _mm512_fmadd_ps (p1[i], pv[i], a); b = _mm512_fmadd_ps (p2[i], pv[i], b); c = _mm512_fmadd_ps (p3[i], pv[i], c); } pdest[0] = a; pdest[1] = b; pdest[2] = c; } g++ -O2 -mavx512f -S got .L3: vmovaps (%r8,%rax), %zmm3 vmovaps (%r9,%rax), %zmm4 vmovaps (%rsi,%rax), %zmm5 vfmadd231ps (%rdi,%rax), %zmm3, %zmm2 vfmadd231ps (%rdi,%rax), %zmm4, %zmm1 vfmadd231ps (%rdi,%rax), %zmm5, %zmm0 addq $64, %rax cmpq %rax, %rdx jne .L3 It would be better to load (%rdi, %rax) into a zmm then .L3: vmovaps (%rdi,%rax), %zmm0 vfmadd231ps (%r8,%rax), %zmm0, %zmm3 vfmadd231ps (%r9,%rax), %zmm0, %zmm2 vfmadd231ps (%rsi,%rax), %zmm0, %zmm1 addq $64, %rax cmpq %rax, %rdx jne .L3