[Bug target/104704] [12 Regression] ix86_gen_scratch_sse_rtx doesn't work with explicit XMM7/XMM15/XMM31 usage
crazylht at gmail dot com
gcc-bugzilla@gcc.gnu.org
Thu Mar 3 01:28:10 GMT 2022
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104704
--- Comment #12 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to H.J. Lu from comment #10)
> Created attachment 52553 [details]
> A patch to always return pseudo register in ix86_gen_scratch_sse_rtx
For pr100865-8a.c,pr100865-9c.c,pr100865-8c.c
+/* { dg-final { scan-assembler-times "(?:vpbroadcastd|vpshufd)\[\\t
\]+\[^\n\]*, %xmm\[0-9\]+" 1 { xfail *-*-* } } } */
This can be fixed by
(define_insn "*vec_dupv4si"
- [(set (match_operand:V4SI 0 "register_operand" "=v,v,x")
+ [(set (match_operand:V4SI 0 "register_operand" "=v,v,x,v")
(vec_duplicate:V4SI
- (match_operand:SI 1 "nonimmediate_operand" "Yv,m,0")))]
+ (match_operand:SI 1 "nonimmediate_operand" "Yv,m,0,$r")))]
"TARGET_SSE"
"@
%vpshufd\t{$0, %1, %0|%0, %1, 0}
vbroadcastss\t{%1, %0|%0, %1}
- shufps\t{$0, %0, %0|%0, %0, 0}"
- [(set_attr "isa" "sse2,avx,noavx")
- (set_attr "type" "sselog1,ssemov,sselog1")
- (set_attr "length_immediate" "1,0,1")
- (set_attr "prefix_extra" "0,1,*")
- (set_attr "prefix" "maybe_vex,maybe_evex,orig")
- (set_attr "mode" "TI,V4SF,V4SF")])
+ shufps\t{$0, %0, %0|%0, %0, 0}
+ #"
+ [(set_attr "isa" "sse2,avx,noavx,noavx512vl")
+ (set_attr "type" "sselog1,ssemov,sselog1,sselog1")
+ (set_attr "length_immediate" "1,0,1,1")
+ (set_attr "prefix_extra" "0,1,*,0")
+ (set_attr "prefix" "maybe_vex,maybe_evex,orig,maybe_vex")
+ (set_attr "mode" "TI,V4SF,V4SF,TI")
+ (set (attr "preferred_for_speed")
+ (cond [(eq_attr "alternative" "3")
+ (symbol_ref "TARGET_INTER_UNIT_MOVES_TO_VEC")
+ ]
+ (symbol_ref "true")))])
+
+(define_split
+ [(set (match_operand:V4SI 0 "sse_reg_operand")
+ (vec_duplicate:V4SI
+ (match_operand:SI 1 "general_reg_operand")))]
+ "TARGET_SSE && reload_completed
+ /* Disable this splitter if avx512vl_vec_dup_gprv4si insn is
+ available, because then we can broadcast from GPRs directly. */
+ && !TARGET_AVX512VL"
+ [(const_int 0)]
+{
+ emit_insn (gen_vec_setv4si_0 (gen_lowpart (V4SImode, operands[0]),
+ CONST0_RTX (V4SImode),
+ gen_lowpart (SImode, operands[1])));
+ emit_insn (gen_vec_duplicatev4si (operands[0], operands[0]));
+ DONE;
+})
More information about the Gcc-bugs
mailing list