On 19/09/23 2:36 pm, Xi Ruoyao wrote:
> On Tue, 2023-09-19 at 14:29 +0530, Ajit Agarwal wrote:
>> This new version of patch 7 use improve ree pass for rs6000 target
>> using defined ABI interfaces.
>> Bootstrapped and regtested on power64-linux-gnu.
>
> You should drop the "4/4" in subject if it does not depends on other
> non-committed patches. Otherwise you should send all the non-committed
> dependencies in a series.
>
> If you just have the 4/4 there without {1..3}/4, people will believe
> this is an incomplete patch submission and likely ignore it.
>
There are 4 oatches that are already under review and all the provious
patches are under review.
I will send 3/4 patches again for review.
Thanks & Regards
Ajit
>> Review comments incorporated.
>>
>> Thanks & Regards
>> Ajit
>>
>> ree: Improve ree pass for rs6000 target using defined abi interfaces
>>
>> For rs6000 target we see redundant zero and sign extension and done to
>> improve ree pass to eliminate such redundant zero and sign extension
>> using defined ABI interfaces.
>>
>> 2023-09-19 Ajit Kumar Agarwal <aagar...@linux.ibm.com>
>>
>> gcc/ChangeLog:
>>
>> * ree.cc (combine_reaching_defs): Use of zero_extend and
>> sign_extend
>> defined abi interfaces.
>> (add_removable_extension): Use of defined abi interfaces for
>> no
>> reaching defs.
>> (abi_extension_candidate_return_reg_p): New function.
>> (abi_extension_candidate_p): New function.
>> (abi_extension_candidate_argno_p): New function.
>> (abi_handle_regs_without_defs_p): New function.
>> (abi_target_promote_function_mode): New function.
>>
>> gcc/testsuite/ChangeLog:
>>
>> * g++.target/powerpc/zext-elim-3.C
>> ---
>> gcc/ree.cc | 148
>> +++++++++++++++++-
>> .../g++.target/powerpc/zext-elim-3.C | 13 ++
>> 2 files changed, 158 insertions(+), 3 deletions(-)
>> create mode 100644 gcc/testsuite/g++.target/powerpc/zext-elim-3.C
>>
>> diff --git a/gcc/ree.cc b/gcc/ree.cc
>> index fc04249fa84..79fc54f38a3 100644
>> --- a/gcc/ree.cc
>> +++ b/gcc/ree.cc
>> @@ -514,7 +514,8 @@ get_uses (rtx_insn *insn, rtx reg)
>> if (REGNO (DF_REF_REG (def)) == REGNO (reg))
>> break;
>>
>> - gcc_assert (def != NULL);
>> + if (def == NULL)
>> + return NULL;
>>
>> ref_chain = DF_REF_CHAIN (def);
>>
>> @@ -750,6 +751,122 @@ get_extended_src_reg (rtx src)
>> return src;
>> }
>>
>> +/* Return TRUE if target mode is equal to source mode of zero_extend
>> + or sign_extend otherwise false. */
>> +
>> +static bool
>> +abi_target_promote_function_mode (machine_mode mode)
>> +{
>> + int unsignedp;
>> + machine_mode tgt_mode
>> + = targetm.calls.promote_function_mode (NULL_TREE, mode,
>> &unsignedp,
>> + NULL_TREE, 1);
>> +
>> + if (tgt_mode == mode)
>> + return true;
>> + else
>> + return false;
>> +}
>> +
>> +/* Return TRUE if the candidate insn is zero extend and regno is
>> + a return registers. */
>> +
>> +static bool
>> +abi_extension_candidate_return_reg_p (rtx_insn *insn, int regno)
>> +{
>> + rtx set = single_set (insn);
>> +
>> + if (GET_CODE (SET_SRC (set)) != ZERO_EXTEND)
>> + return false;
>> +
>> + if (targetm.calls.function_value_regno_p (regno))
>> + return true;
>> +
>> + return false;
>> +}
>> +
>> +/* Return TRUE if reg source operand of zero_extend is argument
>> registers
>> + and not return registers and source and destination operand are
>> same
>> + and mode of source and destination operand are not same. */
>> +
>> +static bool
>> +abi_extension_candidate_p (rtx_insn *insn)
>> +{
>> + rtx set = single_set (insn);
>> +
>> + if (GET_CODE (SET_SRC (set)) != ZERO_EXTEND)
>> + return false;
>> +
>> + machine_mode dst_mode = GET_MODE (SET_DEST (set));
>> + rtx orig_src = XEXP (SET_SRC (set), 0);
>> +
>> + if (!FUNCTION_ARG_REGNO_P (REGNO (orig_src))
>> + || abi_extension_candidate_return_reg_p (insn, REGNO
>> (orig_src)))
>> + return false;
>> +
>> + /* Mode of destination and source of zero_extend should be
>> different. */
>> + if (dst_mode == GET_MODE (orig_src))
>> + return false;
>> +
>> + /* REGNO of source and destination of zero_extend should be same.
>> */
>> + if (REGNO (SET_DEST (set)) != REGNO (orig_src))
>> + return false;
>> +
>> + return true;
>> +}
>> +
>> +/* Return TRUE if the candidate insn is zero extend and regno is
>> + an argument registers. */
>> +
>> +static bool
>> +abi_extension_candidate_argno_p (rtx_code code, int regno)
>> +{
>> + if (code != ZERO_EXTEND && code != SIGN_EXTEND)
>> + return false;
>> +
>> + if (FUNCTION_ARG_REGNO_P (regno))
>> + return true;
>> +
>> + return false;
>> +}
>> +
>> +/* Return TRUE if the candidate insn doesn't have defs and have
>> + * uses without RTX_BIN_ARITH/RTX_COMM_ARITH/RTX_UNARY rtx class. */
>> +
>> +static bool
>> +abi_handle_regs_without_defs_p (rtx_insn *insn)
>> +{
>> + if (side_effects_p (PATTERN (insn)))
>> + return false;
>> +
>> + struct df_link *uses = get_uses (insn, SET_DEST (PATTERN (insn)));
>> +
>> + if (!uses)
>> + return false;
>> +
>> + for (df_link *use = uses; use; use = use->next)
>> + {
>> + if (!use->ref)
>> + return false;
>> +
>> + if (BLOCK_FOR_INSN (insn) != BLOCK_FOR_INSN (DF_REF_INSN (use-
>>> ref)))
>> + return false;
>> +
>> + rtx_insn *use_insn = DF_REF_INSN (use->ref);
>> +
>> + if (GET_CODE (PATTERN (use_insn)) == SET)
>> + {
>> + rtx_code code = GET_CODE (SET_SRC (PATTERN (use_insn)));
>> +
>> + if (GET_RTX_CLASS (code) == RTX_BIN_ARITH
>> + || GET_RTX_CLASS (code) == RTX_COMM_ARITH
>> + || GET_RTX_CLASS (code) == RTX_UNARY)
>> + return false;
>> + }
>> + }
>> + return true;
>> +}
>> +
>> /* This function goes through all reaching defs of the source
>> of the candidate for elimination (CAND) and tries to combine
>> the extension with the definition instruction. The changes
>> @@ -770,6 +887,11 @@ combine_reaching_defs (ext_cand *cand, const_rtx
>> set_pat, ext_state *state)
>>
>> state->defs_list.truncate (0);
>> state->copies_list.truncate (0);
>> + rtx orig_src = XEXP (SET_SRC (cand->expr),0);
>> +
>> + if (abi_extension_candidate_p (cand->insn)
>> + && (!get_defs (cand->insn, orig_src, NULL)))
>> + return abi_handle_regs_without_defs_p (cand->insn);
>>
>> outcome = make_defs_and_copies_lists (cand->insn, set_pat, state);
>>
>> @@ -1036,6 +1158,15 @@ combine_reaching_defs (ext_cand *cand,
>> const_rtx set_pat, ext_state *state)
>> }
>> }
>>
>> + rtx insn_set = single_set (cand->insn);
>> +
>> + machine_mode mode = (GET_MODE (XEXP (SET_SRC (insn_set), 0)));
>> +
>> + bool promote_p = abi_target_promote_function_mode (mode);
>> +
>> + if (promote_p)
>> + return true;
>> +
>> if (merge_successful)
>> {
>> /* Commit the changes here if possible
>> @@ -1112,6 +1243,7 @@ add_removable_extension (const_rtx expr,
>> rtx_insn *insn,
>> rtx reg = XEXP (src, 0);
>> struct df_link *defs, *def;
>> ext_cand *cand;
>> + defs = get_defs (insn, reg, NULL);
>>
>> /* Zero-extension of an undefined value is partly defined (it's
>> completely undefined for sign-extension, though). So if
>> there exists
>> @@ -1131,9 +1263,14 @@ add_removable_extension (const_rtx expr,
>> rtx_insn *insn,
>> }
>>
>> /* Second, make sure we can get all the reaching definitions.
>> */
>> - defs = get_defs (insn, reg, NULL);
>> if (!defs)
>> {
>> + if (abi_extension_candidate_argno_p (code, REGNO (reg)))
>> + {
>> + ext_cand e = {expr, code, mode, insn};
>> + insn_list->safe_push (e);
>> + return;
>> + }
>> if (dump_file)
>> {
>> fprintf (dump_file, "Cannot eliminate extension:\n");
>> @@ -1321,7 +1458,8 @@ find_and_remove_re (void)
>> && (REGNO (SET_DEST (set)) != REGNO (XEXP (SET_SRC
>> (set), 0))))
>> {
>> reinsn_copy_list.safe_push (curr_cand->insn);
>> - reinsn_copy_list.safe_push (state.defs_list[0]);
>> + if (state.defs_list.length () != 0)
>> + reinsn_copy_list.safe_push (state.defs_list[0]);
>> }
>> reinsn_del_list.safe_push (curr_cand->insn);
>> state.modified[INSN_UID (curr_cand->insn)].deleted = 1;
>> @@ -1345,6 +1483,10 @@ find_and_remove_re (void)
>> for (unsigned int i = 0; i < reinsn_copy_list.length (); i += 2)
>> {
>> rtx_insn *curr_insn = reinsn_copy_list[i];
>> +
>> + if ((i+1) >= reinsn_copy_list.length ())
>> + continue;
>> +
>> rtx_insn *def_insn = reinsn_copy_list[i + 1];
>>
>> /* Use the mode of the destination of the defining insn
>> diff --git a/gcc/testsuite/g++.target/powerpc/zext-elim-3.C
>> b/gcc/testsuite/g++.target/powerpc/zext-elim-3.C
>> new file mode 100644
>> index 00000000000..5a050df06ff
>> --- /dev/null
>> +++ b/gcc/testsuite/g++.target/powerpc/zext-elim-3.C
>> @@ -0,0 +1,13 @@
>> +/* { dg-options "-mcpu=power9 -O2" } */
>> +
>> +void *memset(void *b, int c, unsigned long len)
>> +{
>> + unsigned long i;
>> +
>> + for (i = 0; i < len; i++)
>> + ((unsigned char *)b)[i] = c;
>> +
>> + return b;
>> +}
>> +
>> +/* { dg-final { scan-assembler-not "\mrlwinm\M" } } */
>
