i386: Improve reg pressure of double word right shift then truncate.

This patch improves register pressure during reload, inspired by PR 97756.
Normally, a double-word right-shift by a constant produces a double-word
result, the highpart of which is dead when followed by a truncation.
The dead code calculating the high part gets cleaned up post-reload, so
the issue isn't normally visible, except for the increased register
pressure during reload, sometimes leading to odd register assignments.
Providing a post-reload splitter, which clobbers a single wordmode
result register instead of a doubleword result register, helps (a bit).

An example demonstrating this effect is:

unsigned long foo (__uint128_t n)
{
  unsigned long a = n & MASK60;
  unsigned long b = (n >> 60);
  b = b & MASK60;
  unsigned long c = (n >> 120);
  return a+b+c;
}

which currently with -O2 generates (13 instructions):
foo:    movabsq $1152921504606846975, %rcx
        xchgq   %rdi, %rsi
        movq    %rsi, %rax
        shrdq   $60, %rdi, %rax
        movq    %rax, %rdx
        movq    %rsi, %rax
        movq    %rdi, %rsi
        andq    %rcx, %rax
        shrq    $56, %rsi
        andq    %rcx, %rdx
        addq    %rsi, %rax
        addq    %rdx, %rax
        ret

with this patch, we generate one less mov (12 instructions):
foo:    movabsq $1152921504606846975, %rcx
        xchgq   %rdi, %rsi
        movq    %rdi, %rdx
        movq    %rsi, %rax
        movq    %rdi, %rsi
        shrdq   $60, %rdi, %rdx
        andq    %rcx, %rax
        shrq    $56, %rsi
        addq    %rsi, %rax
        andq    %rcx, %rdx
        addq    %rdx, %rax
        ret

The significant difference is easier to see via diff:
<       shrdq   $60, %rdi, %rax
<       movq    %rax, %rdx
---
>       shrdq   $60, %rdi, %rdx

Admittedly a single "mov" isn't much of a saving on modern architectures,
but as demonstrated by the PR, people still track the number of them.

2023-11-13  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/i386/i386.md (<insn><dwi>3_doubleword_lowpart): New
	define_insn_and_split to optimize register usage of doubleword
	right shifts followed by truncation.

1 files changed, 24 insertions, 0 deletions

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index ffd9f2d..47d21f1 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14801,6 +14801,30 @@
   [(const_int 0)]
   "ix86_split_<insn> (operands, operands[3], <DWI>mode); DONE;")
 
+;; Split truncations of double word right shifts into x86_shrd_1.
+(define_insn_and_split "<insn><dwi>3_doubleword_lowpart"
+  [(set (match_operand:DWIH 0 "register_operand" "=&r")
+	(subreg:DWIH
+	  (any_shiftrt:<DWI> (match_operand:<DWI> 1 "register_operand" "r")
+			     (match_operand:QI 2 "const_int_operand")) 0))
+   (clobber (reg:CC FLAGS_REG))]
+  "UINTVAL (operands[2]) < <MODE_SIZE> * BITS_PER_UNIT"
+  "#"
+  "&& reload_completed"
+  [(parallel
+      [(set (match_dup 0)
+	    (ior:DWIH (lshiftrt:DWIH (match_dup 0) (match_dup 2))
+		      (subreg:DWIH
+			(ashift:<DWI> (zero_extend:<DWI> (match_dup 3))
+				      (match_dup 4)) 0)))
+       (clobber (reg:CC FLAGS_REG))])]
+{
+  split_double_mode (<DWI>mode, &operands[1], 1, &operands[1], &operands[3]);
+  operands[4] = GEN_INT ((<MODE_SIZE> * BITS_PER_UNIT) - INTVAL (operands[2]));
+  if (!rtx_equal_p (operands[0], operands[3]))
+    emit_move_insn (operands[0], operands[3]);
+})
+
 (define_insn "x86_64_shrd"
   [(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
         (ior:DI (lshiftrt:DI (match_dup 0)