[llvm-dev] Comparing Clang and GCC: only clang stores updated value in each iteration.

[Jonas Paulsson via llvm-dev]

Hi,

I have a benchmark (mcf) that is currently slower when compiled with 
clang compared to gcc 8 (~10%). It seems that a hot loop has a few 
differences, where one interesting one is that while clang stores an 
incremented value in each iteration, gcc waits and just stores the final 
value just once after the loop. The value is a global variable.

I wonder if this is something clang does not do per default but can be 
activated, similarly to the fp-contract situation?

If not, is this a deficiency in clang? What pass should handle this? 
IndVarSimplify?

I have made a reduced test case which shows the same difference between 
the compilers: clang adds 1 and stores it back to 'a' in each iteration, 
while gcc instead figures out the value a has after the loop (0) and 
stores it then once to 'a'.

/Jonas


int a = 1;
void b() {
   do
     if (a)
       a++;
   while (a != 0);
}

bin/clang -O3 -march=z13 -mllvm -unroll-count=1

         .text
         .file   "testfun.i"
         .globl  b                       # -- Begin function b
         .p2align        4
         .type   b, at function
b:                                      # @b
# %bb.0:                                # %entry
         lrl     %r0, a
.LBB0_1:                                # %do.body
                                         # =>This Inner Loop Header: Depth=1
         cije    %r0, 0, .LBB0_3
# %bb.2:                                # %if.then
                                         #   in Loop: Header=BB0_1 Depth=1
         ahi     %r0, 1
         strl    %r0, a
.LBB0_3:                                # %do.cond
                                         #   in Loop: Header=BB0_1 Depth=1
         cijlh   %r0, 0, .LBB0_1
# %bb.4:                                # %do.end
         br      %r14
.Lfunc_end0:
         .size   b, .Lfunc_end0-b
                                         # -- End function
         .type   a, at object               # @a
         .data
         .globl  a
         .p2align        2
a:
         .long   1                       # 0x1
         .size   a, 4


gcc -O3 -march=z13:

         .file   "testfun.i"
         .machinemode zarch
         .machine "z13"
.text
         .align  8
.globl b
         .type   b, @function
b:
.LFB0:
         .cfi_startproc
         larl    %r1,a
         lt      %r1,0(%r1)
         je      .L1
         larl    %r1,a
         mvhi    0(%r1),0
.L1:
         br      %r14
         .cfi_endproc
.LFE0:
         .size   b, .-b
.globl a
.data
         .align  4
         .type   a, @object
         .size   a, 4
a:
         .long   1
         .ident  "GCC: (GNU) 8.0.1 20180324 (Red Hat 8.0.1-0.20)"
         .section        .note.GNU-stack,"", at progbits