https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96243
Bug ID: 96243
Summary: For vector compare to mask register, UNSPEC is needed
instead of comparison operator
Product: gcc
Version: 11.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: crazylht at gmail dot com
Target Milestone: ---
Target: i386, x86-64
When tring to relax
(define_expand "<avx512>_eq<mode>3<mask_scalar_merge_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand")
- (unspec:<avx512fmaskmode>
- [(match_operand:VI48_AVX512VL 1 "nonimmediate_operand")
- (match_operand:VI48_AVX512VL 2 "nonimmediate_operand")]
- UNSPEC_MASKED_EQ))]
+ (eq:<avx512fmaskmode>
+ (match_operand:VI48_AVX512VL 1 "nonimmediate_operand")
+ (match_operand:VI48_AVX512VL 2 "nonimmediate_operand")))]
"TARGET_AVX512F"
"ix86_fixup_binary_operands_no_copy (EQ, <MODE>mode, operands);")
I got runtime failure from gcc.target/i386/avx512vl-vpcmpeqq-2.c, that's
because cse will take (eq:QI (V4DI: 90) (V4DI: 91)) as a boolean value and do
some optimization, that's not correct for vector compare, also others places
like combine hold the same assumption.
The pattern like
(define_insn "*<avx512>_cmp<mode>3<mask_scalar_merge_name><round_saeonly_name>"
[(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=k")
(match_operator:<avx512fmaskmode> 3 "ix86_comparison_int_operator"
[(match_operand:VI48_AVX512VL 1 "register_operand" "v")
(match_operand:VI48_AVX512VL 2 "nonimmediate_operand"
"<round_saeonly_constraint>")]))]
"TARGET_AVX512F && <round_saeonly_mode512bit_condition>"
"vpcmp<ssemodesuffix>\t{%I3, <round_saeonly_mask_scalar_merge_op4>%2, %1,
%0<mask_scalar_merge_operand4>|%0<mask_scalar_merge_operand4>, %1,
%2<round_saeonly_mask_scalar_merge_op4>, %I3}"
[(set_attr "type" "ssecmp")
(set_attr "length_immediate" "1")
(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
Need to be fixed.
