[Bug c/42596] New: Integer/Floating point vector casts generate XMM register moves from and to the same register

[adam at consulting dot net dot nz]

/*
  GCC does not permit a vector of a union type.

  To dynamically store both integer and float data in an XMM register define an
  integer vector and cast to a float vector whenever a floating point operation
  is required upon the data (or use a union to perform the type conversion).

  Instead of treating these casts as a no-op GCC copies the register using a
  floating point XMM move instruction, performs the calculation, then copies
  the register back using an integer XMM move instruction.
*/

typedef double xmm_2f64_t __attribute__((vector_size (16)));
typedef long long xmm_2i64_t __attribute__((vector_size (16)));

register xmm_2f64_t xmm_a __asm__("xmm4");
register xmm_2f64_t xmm_b __asm__("xmm5");

register xmm_2i64_t xmm_c __asm__("xmm6");
register xmm_2i64_t xmm_d __asm__("xmm7");

typedef union {
  xmm_2f64_t xmm_2f64;
  xmm_2i64_t xmm_2i64;
} xmm_u;

//"data type of ‘xmm_e’ isn’t suitable for a register"
//register xmm_u xmm_e __asm__("xmm8");

typedef union {
  long long i64;
  double f64;
} r64_u;

//Note that the union above is suitable for a 64-bit register
register r64_u r64 __asm__("r15");


void test_fp_vectors_containing_fp_data() {
  xmm_a+=xmm_b;
}

void test_int_vectors_containing_fp_data() {
  xmm_c=(xmm_2i64_t) ((xmm_2f64_t) xmm_c + (xmm_2f64_t) xmm_d);
}

void test_int_vectors_containing_fp_data_using_a_union() {
  xmm_u u_c, u_d;
  u_c.xmm_2i64=xmm_c;
  u_d.xmm_2i64=xmm_d;
  u_c.xmm_2f64+=u_d.xmm_2f64;
  xmm_c=u_c.xmm_2i64;
}

int main() {
}


Relevant code generation:
$ gcc -O3 dynamic_vectors.c && objdump -d -m i386:x86-64:intel a.out |less

00000000004004a0 <test_fp_vectors_containing_fp_data>:
  4004a0:       66 0f 58 e5             addpd  xmm4,xmm5
  4004a4:       c3                      ret    
  4004a5:       66 66 2e 0f 1f 84 00    nop    WORD PTR cs:[rax+rax*1+0x0]
  4004ac:       00 00 00 00 

00000000004004b0 <test_int_vectors_containing_fp_data>:
  4004b0:       66 0f 28 c6             movapd xmm0,xmm6
  4004b4:       66 0f 58 c7             addpd  xmm0,xmm7
  4004b8:       66 0f 6f f0             movdqa xmm6,xmm0
  4004bc:       c3                      ret    
  4004bd:       0f 1f 00                nop    DWORD PTR [rax]

00000000004004c0 <test_int_vectors_containing_fp_data_using_a_union>:
  4004c0:       66 0f 28 c6             movapd xmm0,xmm6
  4004c4:       66 0f 58 c7             addpd  xmm0,xmm7
  4004c8:       66 0f 6f f0             movdqa xmm6,xmm0
  4004cc:       c3                      ret    
  4004cd:       0f 1f 00                nop    DWORD PTR [rax]


The last two functions should generate addpd xmm6,xmm7 instead of first copying
xmm6 to xmm0, performing the calculation, and then copying xmm6 back to xmm0.


-- 
           Summary: Integer/Floating point vector casts generate XMM
                    register moves from and to the same register
           Product: gcc
           Version: 4.4.2
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: adam at consulting dot net dot nz


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42596