@@ -35,6 +35,8 @@ extern bool xxspltib_constant_p (rtx, machine_mode, int *, int *);
extern int vspltis_shifted (rtx);
extern HOST_WIDE_INT const_vector_elt_as_int (rtx, unsigned int);
extern bool macho_lo_sum_memory_operand (rtx, machine_mode);
+extern int rotate_from_leading_zeros_const (unsigned HOST_WIDE_INT, int);
+extern bool compare_rotate_immediate_p (unsigned HOST_WIDE_INT);
extern int num_insns_constant (rtx, machine_mode);
extern int small_data_operand (rtx, machine_mode);
extern bool mem_operand_gpr (rtx, machine_mode);
@@ -14797,6 +14797,47 @@ rs6000_reverse_condition (machine_mode mode, enum rtx_code code)
return reverse_condition (code);
}
+/* Check if C can be rotated from an immediate which starts (as 64bit integer)
+ with at least CLZ bits zero.
+
+ Return the number by which C can be rotated from the immediate.
+ Return -1 if C can not be rotated as from. */
+
+int
+rotate_from_leading_zeros_const (unsigned HOST_WIDE_INT c, int clz)
+{
+ /* case a. 0..0xxx: already at least clz zeros. */
+ int lz = clz_hwi (c);
+ if (lz >= clz)
+ return 0;
+
+ /* case b. 0..0xxx0..0: at least clz zeros. */
+ int tz = ctz_hwi (c);
+ if (lz + tz >= clz)
+ return tz;
+
+ /* case c. xx10.....0xx: rotate 'clz + 1' bits firstly, then check case b.
+ ^bit -> Vbit
+ 00...00xxx100, 'clz + 1' >= bits of xxxx. */
+ const int rot_bits = HOST_BITS_PER_WIDE_INT - clz + 1;
+ unsigned HOST_WIDE_INT rc = (c >> rot_bits) | (c << (clz - 1));
+ tz = ctz_hwi (rc);
+ if (clz_hwi (rc) + tz >= clz)
+ return tz + rot_bits;
+
+ return -1;
+}
+
+/* Check if C can be rotated from an immediate operand of cmpdi or cmpldi. */
+
+bool
+compare_rotate_immediate_p (unsigned HOST_WIDE_INT c)
+{
+ /* leading 48 zeros (cmpldi), or leading 49 ones (cmpdi). */
+ return rotate_from_leading_zeros_const (~c, 49) > 0
+ || rotate_from_leading_zeros_const (c, 48) > 0;
+}
+
/* Generate a compare for CODE. Return a brand-new rtx that
represents the result of the compare. */
@@ -7766,6 +7766,63 @@ (define_insn "*movsi_from_df"
"xscvdpsp %x0,%x1"
[(set_attr "type" "fp")])
+
+(define_code_iterator eqne [eq ne])
+(define_code_attr EQNE [(eq "EQ") (ne "NE")])
+
+;; "i == C" ==> "rotl(i,N) == rotl(C,N)"
+(define_insn_and_split "*rotate_on_cmpdi"
+ [(set (pc)
+ (if_then_else (eqne (match_operand:DI 1 "gpc_reg_operand" "r")
+ (match_operand:DI 2 "const_int_operand" "n"))
+ (label_ref (match_operand 0 ""))
+ (pc)))]
+ "TARGET_POWERPC64 && can_create_pseudo_p ()
+ && num_insns_constant (operands[2], DImode) > 1
+ && compare_rotate_immediate_p (UINTVAL (operands[2]))"
+ "#"
+ "&& 1"
+ [(pc)]
+{
+ rtx note = find_reg_note (curr_insn, REG_BR_PROB, 0);
+ bool sgn = false;
+ unsigned HOST_WIDE_INT C = INTVAL (operands[2]);
+ int rot = rotate_from_leading_zeros_const (C, 48);
+ if (rot < 0)
+ {
+ sgn = true;
+ rot = rotate_from_leading_zeros_const (~C, 49);
+ }
+ rtx n = GEN_INT (HOST_BITS_PER_WIDE_INT - rot);
+
+ /* i' = rotl (i, n) */
+ rtx op0 = gen_reg_rtx (DImode);
+ emit_insn (gen_rtx_SET (op0, gen_rtx_ROTATE (DImode, operands[1], n)));
+
+ /* C' = rotl (C, n) */
+ rtx op1 = GEN_INT ((C << INTVAL (n)) | (C >> rot));
+
+ /* i' == C' */
+ machine_mode comp_mode = sgn ? CCmode : CCUNSmode;
+ rtx cc = gen_reg_rtx (comp_mode);
+ emit_insn (gen_rtx_SET (cc, gen_rtx_COMPARE (comp_mode, op0, op1)));
+ rtx cmp = gen_rtx_<EQNE> (CCmode, cc, const0_rtx);
+ rtx loc_ref = gen_rtx_LABEL_REF (VOIDmode, operands[0]);
+ emit_jump_insn (gen_rtx_SET (pc_rtx,
+ gen_rtx_IF_THEN_ELSE (VOIDmode, cmp,
+ loc_ref, pc_rtx)));
+ if (note)
+ {
+ profile_probability prob
+ = profile_probability::from_reg_br_prob_note (XINT (note, 0));
+
+ add_reg_br_prob_note (get_last_insn (), prob);
+ }
+
+ DONE;
+}
+)
+
;; Split a load of a large constant into the appropriate two-insn
;; sequence.
@@ -13472,7 +13529,6 @@ (define_expand "@ctr<mode>"
;; rs6000_legitimate_combined_insn prevents combine creating any of
;; the ctr<mode> insns.
-(define_code_iterator eqne [eq ne])
(define_code_attr bd [(eq "bdz") (ne "bdnz")])
(define_code_attr bd_neg [(eq "bdnz") (ne "bdz")])
new file mode 100644
@@ -0,0 +1,52 @@
+/* { dg-options "-O2" } */
+/* { dg-do compile { target has_arch_ppc64 } } */
+
+/* { dg-final { scan-assembler-times {\mcmpldi\M} 10 } } */
+/* { dg-final { scan-assembler-times {\mcmpdi\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mrotldi\M} 14 } } */
+
+int foo (int a);
+
+int __attribute__ ((noinline)) udi_fun (unsigned long long in)
+{
+ if (in == (0x8642000000000000ULL))
+ return foo (1);
+ if (in == (0x7642000000000000ULL))
+ return foo (12);
+ if (in == (0x8000000000000000ULL))
+ return foo (32);
+ if (in == (0x8000000000000001ULL))
+ return foo (33);
+ if (in == (0x8642FFFFFFFFFFFFULL))
+ return foo (46);
+ if (in == (0x7642FFFFFFFFFFFFULL))
+ return foo (51);
+ if (in == (0x7567000000ULL))
+ return foo (9);
+ if (in == (0xFFF8567FFFFFFFFFULL))
+ return foo (19);
+
+ return 0;
+}
+
+int __attribute__ ((noinline)) di_fun (long long in)
+{
+ if (in == (0x8642000000000000LL))
+ return foo (1);
+ if (in == (0x7642000000000000LL))
+ return foo (12);
+ if (in == (0x8000000000000000LL))
+ return foo (32);
+ if (in == (0x8000000000000001LL))
+ return foo (33);
+ if (in == (0x8642FFFFFFFFFFFFLL))
+ return foo (46);
+ if (in == (0x7642FFFFFFFFFFFFLL))
+ return foo (51);
+ if (in == (0x7567000000LL))
+ return foo (9);
+ if (in == (0xFFF8567FFFFFFFFFLL))
+ return foo (19);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,95 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -std=c99" } */
+
+int
+foo (int a)
+{
+ return a + 6;
+}
+
+int __attribute__ ((noinline)) udi_fun (unsigned long long in)
+{
+ if (in == (0x8642000000000000ULL))
+ return foo (1);
+ if (in == (0x7642000000000000ULL))
+ return foo (12);
+ if (in == (0x8000000000000000ULL))
+ return foo (32);
+ if (in == (0x8000000000000001ULL))
+ return foo (33);
+ if (in == (0x8642FFFFFFFFFFFFULL))
+ return foo (46);
+ if (in == (0x7642FFFFFFFFFFFFULL))
+ return foo (51);
+ if (in == (0x7567000000ULL))
+ return foo (9);
+ if (in == (0xFFF8567FFFFFFFFFULL))
+ return foo (19);
+
+ return 0;
+}
+
+int __attribute__ ((noinline)) di_fun (long long in)
+{
+ if (in == (0x8642000000000000LL))
+ return foo (1);
+ if (in == (0x7642000000000000LL))
+ return foo (12);
+ if (in == (0x8000000000000000LL))
+ return foo (32);
+ if (in == (0x8000000000000001LL))
+ return foo (33);
+ if (in == (0x8642FFFFFFFFFFFFLL))
+ return foo (46);
+ if (in == (0x7642FFFFFFFFFFFFLL))
+ return foo (51);
+ return 0;
+}
+
+int
+main ()
+{
+ int e = 0;
+ if (udi_fun (6) != 0)
+ e++;
+ if (udi_fun (0x8642000000000000ULL) != foo (1))
+ e++;
+ if (udi_fun (0x7642000000000000ULL) != foo (12))
+ e++;
+ if (udi_fun (0x8000000000000000ULL) != foo (32))
+ e++;
+ if (udi_fun (0x8000000000000001ULL) != foo (33))
+ e++;
+ if (udi_fun (0x8642FFFFFFFFFFFFULL) != foo (46))
+ e++;
+ if (udi_fun (0x7642FFFFFFFFFFFFULL) != foo (51))
+ e++;
+ if (udi_fun (0x7567000000ULL) != foo (9))
+ e++;
+ if (udi_fun (0xFFF8567FFFFFFFFFULL) != foo (19))
+ e++;
+
+ if (di_fun (6) != 0)
+ e++;
+ if (di_fun (0x8642000000000000LL) != foo (1))
+ e++;
+ if (di_fun (0x7642000000000000LL) != foo (12))
+ e++;
+ if (di_fun (0x8000000000000000LL) != foo (32))
+ e++;
+ if (di_fun (0x8000000000000001LL) != foo (33))
+ e++;
+ if (di_fun (0x8642FFFFFFFFFFFFLL) != foo (46))
+ e++;
+ if (di_fun (0x7642FFFFFFFFFFFFLL) != foo (51))
+ e++;
+ if (udi_fun (0x7567000000LL) != foo (9))
+ e++;
+ if (udi_fun (0xFFF8567FFFFFFFFFLL) != foo (19))
+ e++;
+
+ if (e)
+ __builtin_abort ();
+ return 0;
+}
+
Hi, When checking eq/ne with a constant which has only 16bits, it can be optimized to check the rotated data. By this, the constant building is optimized. As the example in PR103743: For "in == 0x8000000000000000LL", this patch generates: rotldi %r3,%r3,16 cmpldi %cr0,%r3,32768 instead: li %r9,-1 rldicr %r9,%r9,0,0 cmpd %cr0,%r3,%r9 This is updated patch based on previous patch and comments: https://gcc.gnu.org/pipermail/gcc-patches/2022-August/600164.html This patch pass bootstrap and regtest on ppc64 and ppc64le. Is it ok for trunk? Thanks for comments! BR, Jeff(Jiufu) PR target/103743 gcc/ChangeLog: * config/rs6000/rs6000-protos.h (rotate_from_leading_zeros_const): New. (compare_rotate_immediate_p): New. * config/rs6000/rs6000.cc (rotate_from_leading_zeros_const): New definition. (compare_rotate_immediate_p): New definition. * config/rs6000/rs6000.md (EQNE): New code_attr. (*rotate_on_cmpdi): New define_insn_and_split. gcc/testsuite/ChangeLog: * gcc.target/powerpc/pr103743.c: New test. * gcc.target/powerpc/pr103743_1.c: New test. --- gcc/config/rs6000/rs6000-protos.h | 2 + gcc/config/rs6000/rs6000.cc | 41 ++++++++ gcc/config/rs6000/rs6000.md | 58 ++++++++++- gcc/testsuite/gcc.target/powerpc/pr103743.c | 52 ++++++++++ gcc/testsuite/gcc.target/powerpc/pr103743_1.c | 95 +++++++++++++++++++ 5 files changed, 247 insertions(+), 1 deletion(-) create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743.c create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743_1.c