On Jun 1, 2018, at 10:11 AM, Will Schmidt <[email protected]> wrote:
>
> On Fri, 2018-06-01 at 08:53 +0200, Richard Biener wrote:
>> On Thu, May 31, 2018 at 9:59 PM Will Schmidt <[email protected]>
>> wrote:
>>>
>>> Hi,
>>> Add support for gimple folding for unaligned vector loads and stores.
>>> testcases posted separately in this thread.
>>>
>>> Regtest completed across variety of systems, P6,P7,P8,P9.
>>>
>>> OK for trunk?
>>> Thanks,
>>> -Will
>>>
>>> [gcc]
>>>
>>> 2018-05-31 Will Schmidt <[email protected]>
>>>
>>> * config/rs6000/rs6000.c: (rs6000_builtin_valid_without_lhs) Add
>>> vec_xst
>>> variants to the list. (rs6000_gimple_fold_builtin) Add support for
>>> folding unaligned vector loads and stores.
>>>
>>> diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
>>> index d62abdf..54b7de2 100644
>>> --- a/gcc/config/rs6000/rs6000.c
>>> +++ b/gcc/config/rs6000/rs6000.c
>>> @@ -15360,10 +15360,16 @@ rs6000_builtin_valid_without_lhs (enum
>>> rs6000_builtins fn_code)
>>> case ALTIVEC_BUILTIN_STVX_V8HI:
>>> case ALTIVEC_BUILTIN_STVX_V4SI:
>>> case ALTIVEC_BUILTIN_STVX_V4SF:
>>> case ALTIVEC_BUILTIN_STVX_V2DI:
>>> case ALTIVEC_BUILTIN_STVX_V2DF:
>>> + case VSX_BUILTIN_STXVW4X_V16QI:
>>> + case VSX_BUILTIN_STXVW4X_V8HI:
>>> + case VSX_BUILTIN_STXVW4X_V4SF:
>>> + case VSX_BUILTIN_STXVW4X_V4SI:
>>> + case VSX_BUILTIN_STXVD2X_V2DF:
>>> + case VSX_BUILTIN_STXVD2X_V2DI:
>>> return true;
>>> default:
>>> return false;
>>> }
>>> }
>>> @@ -15869,10 +15875,77 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator
>>> *gsi)
>>> gimple_set_location (g, loc);
>>> gsi_replace (gsi, g, true);
>>> return true;
>>> }
>>>
>>> + /* unaligned Vector loads. */
>>> + case VSX_BUILTIN_LXVW4X_V16QI:
>>> + case VSX_BUILTIN_LXVW4X_V8HI:
>>> + case VSX_BUILTIN_LXVW4X_V4SF:
>>> + case VSX_BUILTIN_LXVW4X_V4SI:
>>> + case VSX_BUILTIN_LXVD2X_V2DF:
>>> + case VSX_BUILTIN_LXVD2X_V2DI:
>>> + {
>>> + arg0 = gimple_call_arg (stmt, 0); // offset
>>> + arg1 = gimple_call_arg (stmt, 1); // address
>>> + lhs = gimple_call_lhs (stmt);
>>> + location_t loc = gimple_location (stmt);
>>> + /* Since arg1 may be cast to a different type, just use
>>> ptr_type_node
>>> + here instead of trying to enforce TBAA on pointer types. */
>>> + tree arg1_type = ptr_type_node;
>>> + tree lhs_type = TREE_TYPE (lhs);
>>> + /* POINTER_PLUS_EXPR wants the offset to be of type 'sizetype'.
>>> Create
>>> + the tree using the value from arg0. The resulting type will
>>> match
>>> + the type of arg1. */
>>> + gimple_seq stmts = NULL;
>>> + tree temp_offset = gimple_convert (&stmts, loc, sizetype, arg0);
>>> + tree temp_addr = gimple_build (&stmts, loc, POINTER_PLUS_EXPR,
>>> + arg1_type, arg1, temp_offset);
>>> + gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
>>> + /* Use the build2 helper to set up the mem_ref. The MEM_REF could
>>> also
>>> + take an offset, but since we've already incorporated the offset
>>> + above, here we just pass in a zero. */
>>> + gimple *g;
>>> + g = gimple_build_assign (lhs, build2 (MEM_REF, lhs_type, temp_addr,
>>> + build_int_cst (arg1_type,
>>> 0)));
>>
>> So in GIMPLE the type of the MEM_REF specifies the alignment so my question
>> is what type does the lhs usually have here? I'd simply guess V4SF, etc.?
>> In
>
> yes. (double-checking). my reference for the intrinsic signatures
> shows the lhs is a vector of type. The rhs can be either *type or
> *vector of type.
>
> vector double vec_vsx_ld (int, const vector double *);
> vector double vec_vsx_ld (int, const double *);
> With similar/same for the assorted other types.
>
> These are also on my list as 'unaligned' vector loads. I'm not certain
> if that adds a twist to how I should answer the below..
>
> Bill?
'unaligned' means not necessarily aligned on a vector boundary.
They are guaranteed to be aligned on an element boundary.
>
>> this case you are missing a
>> tree ltype = build_aligned_type (lhs_type, desired-alignment);
>>
>> and use that ltype for building the MEM_REF. I suppose in this case the
>> known
>> alignment is either BITS_PER_UNIT or element alignment (thus
>> TYPE_ALIGN (TREE_TYPE (lhs_type)))?
>
> I'd think element alignment. but no longer certain. :-)
Yep, element alignment.
Thanks,
Bill
>
>> Or is the type of the load the element types?
>
>
> So, In any case.. I'll build up / modify some tests to look at data
> being loaded, and see if I can see alignment issues here.
>
> Thanks,
> -Will
>
>
>
>> Richard.
>>
>>> + gimple_set_location (g, loc);
>>> + gsi_replace (gsi, g, true);
>>> + return true;
>>> + }
>>> +
>>> + /* unaligned Vector stores. */
>>> + case VSX_BUILTIN_STXVW4X_V16QI:
>>> + case VSX_BUILTIN_STXVW4X_V8HI:
>>> + case VSX_BUILTIN_STXVW4X_V4SF:
>>> + case VSX_BUILTIN_STXVW4X_V4SI:
>>> + case VSX_BUILTIN_STXVD2X_V2DF:
>>> + case VSX_BUILTIN_STXVD2X_V2DI:
>>> + {
>>> + arg0 = gimple_call_arg (stmt, 0); /* Value to be stored. */
>>> + arg1 = gimple_call_arg (stmt, 1); /* Offset. */
>>> + tree arg2 = gimple_call_arg (stmt, 2); /* Store-to address. */
>>> + location_t loc = gimple_location (stmt);
>>> + tree arg0_type = TREE_TYPE (arg0);
>>> + /* Use ptr_type_node (no TBAA) for the arg2_type. */
>>> + tree arg2_type = ptr_type_node;
>>> + /* POINTER_PLUS_EXPR wants the offset to be of type 'sizetype'.
>>> Create
>>> + the tree using the value from arg0. The resulting type will
>>> match
>>> + the type of arg2. */
>>> + gimple_seq stmts = NULL;
>>> + tree temp_offset = gimple_convert (&stmts, loc, sizetype, arg1);
>>> + tree temp_addr = gimple_build (&stmts, loc, POINTER_PLUS_EXPR,
>>> + arg2_type, arg2, temp_offset);
>>> + /* Mask off any lower bits from the address. */
>>> + gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
>>> + gimple *g;
>>> + g = gimple_build_assign (build2 (MEM_REF, arg0_type, temp_addr,
>>> + build_int_cst (arg2_type, 0)),
>>> arg0);
>>> + gimple_set_location (g, loc);
>>> + gsi_replace (gsi, g, true);
>>> + return true;
>>> + }
>>> +
>>> /* Vector Fused multiply-add (fma). */
>>> case ALTIVEC_BUILTIN_VMADDFP:
>>> case VSX_BUILTIN_XVMADDDP:
>>> case ALTIVEC_BUILTIN_VMLADDUHM:
>>> {
