Re: [x86 PATCH] Double word implementation of and; cmp to not; test optimization.

[Uros Bizjak <ubizjak@gmail.com>]

On Sun, Jun 5, 2022 at 7:19 PM Roger Sayle <roger@nextmovesoftware.com> wrote:
>
>
> This patch extends the recent and;cmp to not;test optimization to also
> perform this transformation for TImode on TARGET_64BIT and DImode on -m32,
> One motivation for this is that it's a step to fixing the current failure
> of gcc.target/i386/pr65105-5.c on -m32.
>
> A more direct benefit for x86_64 is that the following code:
>
> int foo(__int128 x, __int128 y)
> {
>   return (x & y) == y;
> }
>
> improves (with -O2 -mbmi) from:
>
>         movq    %rdi, %r8
>         movq    %rsi, %rdi
>         movq    %rdx, %rsi
>         andq    %rcx, %rdi
>         movq    %r8, %rax
>         andq    %rdx, %rax
>         movq    %rdi, %rdx
>         xorq    %rsi, %rax
>         xorq    %rcx, %rdx
>         orq     %rdx, %rax
>         sete    %al
>         movzbl  %al, %eax
>         ret
>
> to the much better:
>
>         movq    %rdi, %r8
>         movq    %rsi, %rdi
>         andn    %rdx, %r8, %rax
>         andn    %rcx, %rdi, %rsi
>         orq     %rsi, %rax
>         sete    %al
>         movzbl  %al, %eax
>         ret
>
> The major theme of this patch is to generalize many of i386.md's
> *di3_doubleword patterns to become *<dwi>_doubleword patterns, i.e.
> whenever there exists a "double word" optimization for DImode with -m32,
> there should be an equivalent TImode optimization on TARGET_64BIT.
>
> The following patch has been tested on x86_64-pc-linux-gnu with
> make bootstrap and make -k check, where on TARGET_64BIT there are
> no new failures, but paradoxically with --target_board=unix{-m32}
> the other dg-final clause in gcc.target/i386/pr65105-5.c now fails.
> Counter-intuitively, this is progress, and pr65105-5.c may now be
> fixed (without using peephole2) simply by tweaking the STV pass to
> handle andn/test (in a follow-up patch).
> OK for mainline?
>
>
> 2022-06-05  Roger Sayle  <roger@nextmovesoftware.com>
>
> gcc/ChangeLog
>         * config/i386/i386.cc (ix86_rtx_costs) <COMPARE>: Provide costs
>         for double word comparisons and tests (comparisons against zero).
>         * config/i386/i386.md (*test<mode>_not_doubleword): Split DWI
>         and;cmp into andn;cmp $0 as a pre-reload splitter.
>         (define_expand and<mode>3): Generalize from SWIM1248x to SWIDWI.
>         (define_insn_and_split "*anddi3_doubleword"): Rename/generalize...
>         (define_insn_and_split "*and<dwi>3_doubleword"): ... to this.
>         (define_insn "*andndi3_doubleword"): Rename and generalize...
>         (define_insn "*andn<mode>3_doubleword): ... to this.
>         (define_split): Split andn when TARGET_BMI for both <DWI> modes.
>         (define_split): Split andn when !TARGET_BMI for both <DWI> modes.
>         (define_expand <any_or><mode>3): Generalize from SWIM1248x to
> SWIDWI.
>         (define_insn_and_split "*<any_or><dwi>3_doubleword): Generalize
>         from DI mode to both <DWI> modes.
>
> gcc/testsuite/ChangeLog
>         * gcc.target/i386/testnot-3.c: New test case.

 (define_expand "and<mode>3"
-  [(set (match_operand:SWIM1248x 0 "nonimmediate_operand")
-    (and:SWIM1248x (match_operand:SWIM1248x 1 "nonimmediate_operand")
-               (match_operand:SWIM1248x 2 "<general_szext_operand>")))]
+  [(set (match_operand:SWIDWI 0 "nonimmediate_operand")
+    (and:SWIDWI (match_operand:SWIDWI 1 "nonimmediate_operand")
+            (match_operand:SWIDWI 2 "<general_operand>")))]


SWIM1248x should be changed to SDWIM mode iterator, not SWIDWI:

;; Math-dependant integer modes with DImode.
(define_mode_iterator SWIM1248x
    [(QI "TARGET_QIMODE_MATH")
     (HI "TARGET_HIMODE_MATH")
     SI DI])

;; All math-dependant single and double word integer modes.
(define_mode_iterator SDWIM [(QI "TARGET_QIMODE_MATH")
                 (HI "TARGET_HIMODE_MATH")
                 SI DI (TI "TARGET_64BIT")])

but

;; SWI and DWI together.
(define_mode_iterator SWIDWI [QI HI SI DI (TI "TARGET_64BIT")])

does not handle QI and HI correctly w.r.t. TARGET_[QI,HI]MODE_MATH.

Uros.