[gcc r12-6081] i386: Fix <sse2p4_1>_pinsr<ssemodesuffix> and its splitters [PR103772]

[Uros Bizjak]

https://gcc.gnu.org/g:72c68d7ad90221075102f08f22256d0b4a7631b3

commit r12-6081-g72c68d7ad90221075102f08f22256d0b4a7631b3
Author: Uros Bizjak <ubizjak@gmail.com>
Date:   Mon Dec 20 21:15:50 2021 +0100

    i386: Fix <sse2p4_1>_pinsr<ssemodesuffix> and its splitters [PR103772]
    
    The clever trick to duplicate the value of the input operand into itself
    proved not so clever after all.  The splitter should not clobber the input
    operand in any case, since the register can hold the value outside the HImode
    lowpart when accessed as subreg.  Use the standard earlyclobber approach
    instead.
    
    The testcase fails with avx2 ISA, but I was not able to create the testcase
    that wouldn't require -mavx512fp16 compile flag.
    
    2021-12-20  Uroš Bizjak  <ubizjak@gmail.com>
    
    gcc/ChangeLog:
    
            PR target/103772
            * config/i386/sse.md (<sse2p4_1>_pinsr<ssemodesuffix>): Add
            earlyclobber to (x,x,x,i) alternative.
            (<sse2p4_1>_pinsr<ssemodesuffix> peephole2): Remove.
            (<sse2p4_1>_pinsr<ssemodesuffix> splitter): Use output
            operand as a temporary register.  Split after reload_completed.

Diff:
---
 gcc/config/i386/sse.md | 31 ++++---------------------------
 1 file changed, 4 insertions(+), 27 deletions(-)

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 5196149ee32..cb1c0b1edec 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -17430,7 +17430,7 @@
 
 ;; sse4_1_pinsrd must come before sse2_loadld since it is preferred.
 (define_insn "<sse2p4_1>_pinsr<ssemodesuffix>"
-  [(set (match_operand:PINSR_MODE 0 "register_operand" "=x,x,x,x,v,v,x")
+  [(set (match_operand:PINSR_MODE 0 "register_operand" "=x,x,x,x,v,v,&x")
 	(vec_merge:PINSR_MODE
 	  (vec_duplicate:PINSR_MODE
 	    (match_operand:<ssescalarmode> 2 "nonimmediate_operand" "r,m,r,m,r,m,x"))
@@ -17499,25 +17499,6 @@
 	   (const_string "*")))])
 
 ;; For TARGET_AVX2, implement insert from XMM reg with PBROADCASTW + PBLENDW.
-;; First try to get a scratch register and go through it.  In case this fails,
-;; overwrite source reg with broadcasted value and blend from there.
-(define_peephole2
-  [(match_scratch:V8_128 4 "x")
-   (set (match_operand:V8_128 0 "sse_reg_operand")
-	(vec_merge:V8_128
-	  (vec_duplicate:V8_128
-	    (match_operand:<ssescalarmode> 2 "sse_reg_operand"))
-	  (match_operand:V8_128 1 "sse_reg_operand")
-	  (match_operand:SI 3 "const_int_operand")))]
-  "TARGET_AVX2
-   && INTVAL (operands[3]) > 1
-   && ((unsigned) exact_log2 (INTVAL (operands[3]))
-       < GET_MODE_NUNITS (<MODE>mode))"
-  [(set (match_dup 4)
-	(vec_duplicate:V8_128 (match_dup 2)))
-   (set (match_dup 0)
-	(vec_merge:V8_128 (match_dup 4) (match_dup 1) (match_dup 3)))])
-
 (define_split
   [(set (match_operand:V8_128 0 "sse_reg_operand")
 	(vec_merge:V8_128
@@ -17525,18 +17506,14 @@
 	    (match_operand:<ssescalarmode> 2 "sse_reg_operand"))
 	  (match_operand:V8_128 1 "sse_reg_operand")
 	  (match_operand:SI 3 "const_int_operand")))]
-  "TARGET_AVX2 && epilogue_completed
+  "TARGET_AVX2 && reload_completed
    && INTVAL (operands[3]) > 1
    && ((unsigned) exact_log2 (INTVAL (operands[3]))
        < GET_MODE_NUNITS (<MODE>mode))"
-  [(set (match_dup 4)
+  [(set (match_dup 0)
 	(vec_duplicate:V8_128 (match_dup 2)))
    (set (match_dup 0)
-	(vec_merge:V8_128 (match_dup 4) (match_dup 1) (match_dup 3)))]
-{
-  operands[4] = lowpart_subreg (<MODE>mode, operands[2],
-				<ssescalarmode>mode);
-})
+	(vec_merge:V8_128 (match_dup 0) (match_dup 1) (match_dup 3)))])
 
 (define_expand "<extract_type>_vinsert<shuffletype><extract_suf>_mask"
   [(match_operand:AVX512_VEC 0 "register_operand")