[gcc r13-1282] Implement __imag__ of float _Complex using shufps on x86_64.

[gcc r13-1282] Implement __imag__ of float _Complex using shufps on x86_64.

[Roger Sayle]

https://gcc.gnu.org/g:64d4f27a0ce47e97867512bda7fa5683acf8a134

commit r13-1282-g64d4f27a0ce47e97867512bda7fa5683acf8a134
Author: Roger Sayle <roger@nextmovesoftware.com>
Date:   Mon Jun 27 07:47:40 2022 +0100

    Implement __imag__ of float _Complex using shufps on x86_64.
    
    This patch is a follow-up improvement to my recent patch for
    PR rtl-optimization/7061.  That patch added the test case
    gcc.target/i386/pr7061-2.c:
    
    float im(float _Complex a) { return __imag__ a; }
    
    For which GCC on x86_64 currently generates:
    
            movq    %xmm0, %rax
            shrq    $32, %rax
            movd    %eax, %xmm0
            ret
    
    but with this patch we now generate (the same as LLVM):
    
            shufps  $85, %xmm0, %xmm0
            ret
    
    This is achieved by providing a define_insn_and_split that allows
    truncated lshiftrt:DI by 32 to be performed on either SSE or general
    regs, where if the register allocator prefers to use SSE, we split
    to a shufps_v4si, or if not, we use a regular shrq.
    
    2022-06-27  Roger Sayle  <roger@nextmovesoftware.com>
    
    gcc/ChangeLog
            PR rtl-optimization/7061
            * config/i386/i386.md (*highpartdisi2): New define_insn_and_split.
    
    gcc/testsuite/ChangeLog
            PR rtl-optimization/7061
            * gcc.target/i386/pr7061-2.c: Update to look for shufps.

Diff:
---
 gcc/config/i386/i386.md                  | 25 +++++++++++++++++++++++++
 gcc/testsuite/gcc.target/i386/pr7061-2.c |  4 ++++
 2 files changed, 29 insertions(+)

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index dd173f78508..125a3b44a6d 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -13249,6 +13249,31 @@
        (const_string "*")))
    (set_attr "mode" "<MODE>")])
 
+;; Specialization of *lshr<mode>3_1 below, extracting the SImode
+;; highpart of a DI to be extracted, but allowing it to be clobbered.
+(define_insn_and_split "*highpartdisi2"
+  [(set (subreg:DI (match_operand:SI 0 "register_operand" "=r,x,?k") 0)
+        (lshiftrt:DI (match_operand:DI 1 "register_operand" "0,0,k")
+		     (const_int 32)))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_64BIT"
+  "#"
+  "&& reload_completed"
+  [(parallel
+    [(set (match_dup 0) (lshiftrt:DI (match_dup 1) (const_int 32)))
+     (clobber (reg:CC FLAGS_REG))])]
+{
+  if (SSE_REG_P (operands[0]))
+    {
+      rtx tmp = gen_rtx_REG (V4SImode, REGNO (operands[0]));
+      emit_insn (gen_sse_shufps_v4si (tmp, tmp, tmp,
+				      const1_rtx, const1_rtx,
+				      GEN_INT (5), GEN_INT (5)));
+      DONE;
+    }
+  operands[0] = gen_rtx_REG (DImode, REGNO (operands[0]));
+})
+
 (define_insn "*lshr<mode>3_1"
   [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,?k")
 	(lshiftrt:SWI48
diff --git a/gcc/testsuite/gcc.target/i386/pr7061-2.c b/gcc/testsuite/gcc.target/i386/pr7061-2.c
index ac33340099b..837cd83e156 100644
--- a/gcc/testsuite/gcc.target/i386/pr7061-2.c
+++ b/gcc/testsuite/gcc.target/i386/pr7061-2.c
@@ -1,5 +1,9 @@
 /* { dg-do compile { target { ! ia32 } } } */
 /* { dg-options "-O2" } */
 float im(float _Complex a) { return __imag__ a; }
+/* { dg-final { scan-assembler "shufps" } } */
+/* { dg-final { scan-assembler-not "movd" } } */
+/* { dg-final { scan-assembler-not "movq" } } */
 /* { dg-final { scan-assembler-not "movss" } } */
 /* { dg-final { scan-assembler-not "rsp" } } */
+/* { dg-final { scan-assembler-not "shr" } } */