__builtin_prefetch(const void*)

void foo(double *d, unsigned len) {
  for (unsigned i = 0; i < len; ++i) {
    __builtin_prefetch(&d[i]);
    d[i] = d[i] * d[i];
  }
}

void foo(double *d, unsigned len) {
  for (unsigned i = 0; i < len; ++i) {
    asm("prefetcht0 (%0)"
        : /**/
        : "g"(&d[i])
        : /**/
    );
    d[i] = d[i] * d[i];
  }
}

.file   "test1.c"                                       |          .file   "test2.c"
        .text                                                              .text
        .p2align 4,,15                                                     .p2align 4,,15
        .globl  foo                                                        .globl  foo
        .type   foo, @function                                             .type   foo, @function
foo:                                                               foo:
.LFB0:                                                             .LFB0:
        .cfi_startproc                                                     .cfi_startproc
        testl   %esi, %esi      # len                                      testl   %esi, %esi      # len
        je      .L1     #,                                                 je      .L1     #,
        leal    -1(%rsi), %eax  #, D.1749                       |          leal    -1(%rsi), %eax  #, D.1745
        leaq    8(%rdi,%rax,8), %rax    #, D.1749               |          leaq    8(%rdi,%rax,8), %rax    #, D.1745
        .p2align 4,,10                                                     .p2align 4,,10
        .p2align 3                                                         .p2align 3
.L4:                                                               .L4:
        movsd   (%rdi), %xmm0   # MEM[base: _8, offset: 0B], D. |  #APP
        prefetcht0      (%rdi)  # ivtmp.6                       |  # 3 "test2.c" 1
                                                                >          prefetcht0 (%rdi)       # ivtmp.6
                                                                >  # 0 "" 2
                                                                >  #NO_APP
                                                                >          movsd   (%rdi), %xmm0   # MEM[base: _8, offset: 0B], D.
        addq    $8, %rdi        #, ivtmp.6                                 addq    $8, %rdi        #, ivtmp.6
        mulsd   %xmm0, %xmm0    # D.1748, D.1748                |          mulsd   %xmm0, %xmm0    # D.1747, D.1747
        movsd   %xmm0, -8(%rdi) # D.1748, MEM[base: _8, offset: |          movsd   %xmm0, -8(%rdi) # D.1747, MEM[base: _8, offset:
        cmpq    %rax, %rdi      # D.1749, ivtmp.6               |          cmpq    %rax, %rdi      # D.1745, ivtmp.6
        jne     .L4     #,                                                 jne     .L4     #,
.L1:                                                               .L1:
        rep ret                                                            rep ret
        .cfi_endproc                                                       .cfi_endproc
.LFE0:                                                             .LFE0:
        .size   foo, .-foo                                                 .size   foo, .-foo
        .ident  "GCC: (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4"               .ident  "GCC: (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4"
        .section        .note.GNU-stack,"",@progbits                       .section        .note.GNU-stack,"",@progbits

asm volatile (
        "prefetcht0 (%rax)              ;"