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_insn_and_split "*anddi3_doubleword"
-  [(set (match_operand:DI 0 "nonimmediate_operand")
- (and:DI
- (match_operand:DI 1 "nonimmediate_operand")
- (match_operand:DI 2 "x86_64_szext_general_operand")))
+(define_insn_and_split "*and<dwi>3_doubleword"
+  [(set (match_operand:<DWI> 0 "nonimmediate_operand")
+ (and:<DWI>
+ (match_operand:<DWI> 1 "nonimmediate_operand")
+ (match_operand:<DWI> 2 "<general_operand>")))
    (clobber (reg:CC FLAGS_REG))]
-  "!TARGET_64BIT
-   && ix86_binary_operator_ok (AND, DImode, operands)
+  "ix86_binary_operator_ok (AND, <DWI>mode, operands)
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
-  [(const_int 0)]
+  [(parallel
+    [(set (match_dup 0) (and:DWIH (match_dup 1) (match_dup 2)))
+     (clobber (reg:CC FLAGS_REG))])
+   (parallel
+    [(set (match_dup 3) (and:DWIH (match_dup 4) (match_dup 5)))
+     (clobber (reg:CC FLAGS_REG))])]

Please also note that the above pattern generation will never be
reached, you have unconditional DONE in the insn preparation
statement.

 {
-  split_double_mode (DImode, &operands[0], 3, &operands[0], &operands[3]);
+  split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);

   if (operands[2] == const0_rtx)
     emit_move_insn (operands[0], const0_rtx);
   else if (operands[2] == constm1_rtx)
     emit_move_insn (operands[0], operands[1]);
   else
-    emit_insn (gen_andsi3 (operands[0], operands[1], operands[2]));
+    ix86_expand_binary_operator (AND, <MODE>mode, &operands[0]);

   if (operands[5] == const0_rtx)
     emit_move_insn (operands[3], const0_rtx);
   else if (operands[5] == constm1_rtx)
     emit_move_insn (operands[3], operands[4]);
   else
-    emit_insn (gen_andsi3 (operands[3], operands[4], operands[5]));
+    ix86_expand_binary_operator (AND, <MODE>mode, &operands[3]);

   DONE;
 })

-(define_insn_and_split "*<code>di3_doubleword"
-  [(set (match_operand:DI 0 "nonimmediate_operand")
- (any_or:DI
- (match_operand:DI 1 "nonimmediate_operand")
- (match_operand:DI 2 "x86_64_szext_general_operand")))
+(define_insn_and_split "*<code><dwi>3_doubleword"
+  [(set (match_operand:<DWI> 0 "nonimmediate_operand")
+ (any_or:<DWI>
+ (match_operand:<DWI> 1 "nonimmediate_operand")
+ (match_operand:<DWI> 2 "<general_hilo_operand>")))
    (clobber (reg:CC FLAGS_REG))]
-  "!TARGET_64BIT
-   && ix86_binary_operator_ok (<CODE>, DImode, operands)
+  "ix86_binary_operator_ok (<CODE>, <DWI>mode, operands)
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
-  [(const_int 0)]
+  [(parallel
+    [(set (match_dup 0) (any_or:DWIH (match_dup 1) (match_dup 2)))
+     (clobber (reg:CC FLAGS_REG))])
+   (parallel
+    [(set (match_dup 3) (any_or:DWIH (match_dup 4) (match_dup 5)))
+     (clobber (reg:CC FLAGS_REG))])]

Also here.

Uros.