Hi,
This patch is based on: https://gcc.gnu.org/pipermail/gcc-patches/2022-May/594252.html. When checking eq/neq with a constant which has only 16bits, then 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 Compare with previous patch, this patch refactors the code, and also supports the comparison on the constant like: "0xc000000000000001LL", which constant has 16bits (combined from high and low bits). This patch pass bootstrap and regtest on ppc64 and ppc64le. Ok for trunk? Thanks! BR, Jiufu PR target/103743 gcc/ChangeLog: * config/rs6000/rs6000.cc (rot_bits_to_mask): New. (rotate_comparison_ops): New. (rs6000_generate_compare): Optimize compare on const. gcc/testsuite/ChangeLog: * gcc.target/powerpc/pr103743.c: New test. * gcc.target/powerpc/pr103743_1.c: New test. --- gcc/config/rs6000/rs6000.cc | 100 ++++++++++++++++++ gcc/testsuite/gcc.target/powerpc/pr103743.c | 52 +++++++++ gcc/testsuite/gcc.target/powerpc/pr103743_1.c | 95 +++++++++++++++++ 3 files changed, 247 insertions(+) create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743.c create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743_1.c diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index 4030864aa1a..dee1c575adc 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -14868,6 +14868,92 @@ rs6000_reverse_condition (machine_mode mode, enum rtx_code code) return reverse_condition (code); } +/* If C can be rotated to a constant which all bits are 0, except lowest + N bits. MASK contains 1 in the lowest N bits, other bits are 0. + e.g. rotl(0x0000098760000000ULL, 36) == 0x9876, which high 48bits are 0. + Return the number by which the SRC is rotated, or -1 if fail to rotate. */ + +static int +rot_bits_to_mask (unsigned HOST_WIDE_INT C, unsigned HOST_WIDE_INT mask, + int total_bits = 64) +{ + /* The position of mask regard to the highest bit. */ + int pos_mask = clz_hwi (mask); + + /* Bits are lowest already, e.g. 0x1234ULL. */ + int pos = clz_hwi (C); + if (pos_mask < pos) + return 0; + + /* Bits in the middle, e.g. 0x0000098760000000ULL => 0x9876. */ + if ((C & (mask << (pos_mask - pos))) == C) + return total_bits - (pos_mask - pos); + + /* Bits are at hightest and lowest together: + e.g. 0xc000000000000001ULL => 0xe000. */ + unsigned HOST_WIDE_INT low_bits = C & mask; + pos = clz_hwi (low_bits); + int n = pos - pos_mask; + unsigned HOST_WIDE_INT rot_C = (C << n) | (C >> (total_bits - n)); + if ((rot_C & mask) == rot_C) + return n; + + return -1; +} + +/* Check if able to optimize the comparison on rotated operands. + Return the number by which the SRC is rotated, or -1 if fail to rotate. + */ +static int +rotate_comparison_ops (rtx cmp, machine_mode mode, bool *sgn_cmp, rtx *cst) +{ + /* Now only support compare on DImode, for "== or !=". */ + if (mode != DImode) + return -1; + + enum rtx_code code = GET_CODE (cmp); + if (code != NE && code != EQ) + return -1; + + rtx op1 = XEXP (cmp, 1); + + /* The constant would already been set to a reg in the last insn. */ + rtx_insn *last = get_last_insn_anywhere (); + rtx src = NULL_RTX; + if (last && single_set (last) && SET_DEST (single_set (last)) == op1) + src = SET_SRC (single_set (last)); + + /* It constant may be in constant pool. */ + if (src && MEM_P (src)) + src = avoid_constant_pool_reference (src); + + /* Check if able to compare against rotated const. */ + if (!(src && CONST_INT_P (src))) + return -1; + + unsigned HOST_WIDE_INT C = INTVAL (src); + + /* For case like 0x0000098760000000ULL, use logical cmpldi. */ + int rot = rot_bits_to_mask (C, 0xFFFFULL); + if (rot >= 0) + { + *cst = src; + *sgn_cmp = false; + return rot; + } + + /* For case like 0x8765FFFFFFFFFFFFLL, use sign cmpdi. */ + rot = rot_bits_to_mask (~C, 0x7FFFULL); + if (rot >= 0) + { + *cst = src; + *sgn_cmp = true; + return rot; + } + + return -1; +} + /* Generate a compare for CODE. Return a brand-new rtx that represents the result of the compare. */ @@ -14897,6 +14983,20 @@ rs6000_generate_compare (rtx cmp, machine_mode mode) else comp_mode = CCmode; + /* "i == C" ==> "rotl(i,N) == rotl(C,N)" if rotl(C,N) only low 16bits. */ + bool sgn_cmp = false; + rtx cst = NULL_RTX; + int rot_bits = rotate_comparison_ops (cmp, mode, &sgn_cmp, &cst); + if (rot_bits > 0) + { + rtx n = GEN_INT (rot_bits); + rtx rot_op0 = gen_reg_rtx (mode); + emit_insn (gen_rtx_SET (rot_op0, gen_rtx_ROTATE (mode, op0, n))); + op0 = rot_op0; + op1 = simplify_gen_binary (ROTATE, mode, cst, n); + comp_mode = sgn_cmp ? CCmode : CCUNSmode; + } + /* If we have an unsigned compare, make sure we don't have a signed value as an immediate. */ if (comp_mode == CCUNSmode && CONST_INT_P (op1) diff --git a/gcc/testsuite/gcc.target/powerpc/pr103743.c b/gcc/testsuite/gcc.target/powerpc/pr103743.c new file mode 100644 index 00000000000..55f365395a7 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr103743.c @@ -0,0 +1,52 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target lp64 } */ +/* { dg-options "-O2" } */ +/* { dg-final { scan-assembler-times "cmpldi" 10 } } */ +/* { dg-final { scan-assembler-times "cmpdi" 4 } } */ +/* { dg-final { scan-assembler-times "rotldi" 10 } } */ + +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; +} diff --git a/gcc/testsuite/gcc.target/powerpc/pr103743_1.c b/gcc/testsuite/gcc.target/powerpc/pr103743_1.c new file mode 100644 index 00000000000..2c08c56714a --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr103743_1.c @@ -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; +} + -- 2.25.1
