[Bug rtl-optimization/50107] [IRA, i386] allocates registers in very non-optimal way

[hjl.tools at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50107

--- Comment #12 from H.J. Lu <hjl.tools at gmail dot com> 2011-08-19 01:12:56 
UTC ---
I changed MULX to

(define_insn "bmi2_umul<mode><dwi>3_1"
  [(set (match_operand:<DWI> 0 "register_operand" "=r") 
        (mult:<DWI>
          (zero_extend:<DWI>
            (match_operand:DWIH 1 "register_operand" "d")) 
          (zero_extend:<DWI>
            (match_operand:DWIH 2 "nonimmediate_operand" "rm"))))]
  "TARGET_BMI2"
{
  if (<MODE>mode == DImode)
    return "mulx\t{%2, %q0, %N0|%N0, %q0, %2}";
  else
    return "mulx\t{%2, %k0, %K0|%K0, %k0, %2}";
}
  [(set_attr "type" "imul")
   (set_attr "prefix" "vex")
   (set_attr "mode" "<MODE>")])

Now I got

[hjl@gnu-6 pr50107]$ cat udi-2.i
unsigned long long test_mul_64 (unsigned long a, unsigned long b)
{
  return (unsigned long long) a * b;
}
[hjl@gnu-6 pr50107]$ /export/build/gnu/gcc-hsw/build-x86_64-linux/gcc/xgcc
-B/export/build/gnu/gcc-hsw/build-x86_64-linux/gcc/ -S  -O2 -mbmi2 -dp -m32
udi-2.i
[hjl@gnu-6 pr50107]$ cat udi-2.s
    .file    "udi-2.i"
    .text
    .p2align 4,,15
    .globl    test_mul_64
    .type    test_mul_64, @function
test_mul_64:
.LFB0:
    .cfi_startproc
    movl    8(%esp), %edx    # 20    *movsi_internal/1    [length = 4]
    mulx    4(%esp), %eax, %edx    # 9    bmi2_umulsidi3_1    [length = 7]
    ret    # 25    return_internal    [length = 1]
    .cfi_endproc
.LFE0:
    .size    test_mul_64, .-test_mul_64
    .ident    "GCC: (GNU) 4.7.0 20110818 (experimental)"
    .section    .note.GNU-stack,"",@progbits
[hjl@gnu-6 pr50107]$ cat uti-2.i
unsigned __int128 test_mul_64 (unsigned long long a, unsigned long long b)
{
  return (unsigned __int128) a*b;
}
[hjl@gnu-6 pr50107]$ /export/build/gnu/gcc-hsw/build-x86_64-linux/gcc/xgcc
-B/export/build/gnu/gcc-hsw/build-x86_64-linux/gcc/ -S  -O2 -mbmi2 -dp uti-2.i
[hjl@gnu-6 pr50107]$ cat uti-2.s
    .file    "uti-2.i"
    .text
    .p2align 4,,15
    .globl    test_mul_64
    .type    test_mul_64, @function
test_mul_64:
.LFB0:
    .cfi_startproc
    movq    %rsi, %rdx    # 24    *movdi_internal_rex64/2    [length = 3]
    mulx    %rdi, %rsi, %rdi    # 11    bmi2_umulditi3_1    [length = 5]
    movq    %rsi, %rax    # 25    *movdi_internal_rex64/2    [length = 3]
    movq    %rdi, %rdx    # 26    *movdi_internal_rex64/2    [length = 3]
    ret    # 29    return_internal    [length = 1]
    .cfi_endproc
.LFE0:
    .size    test_mul_64, .-test_mul_64
    .ident    "GCC: (GNU) 4.7.0 20110818 (experimental)"
    .section    .note.GNU-stack,"",@progbits
[hjl@gnu-6 pr50107]$ 

Why don't we generate

mulx    %rdi, %rax, %rdx

for 64bit?