From cb77875a86c67f606ff59261348e1d81b945aa44 Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Mon, 18 Nov 2019 15:29:03 +0000 Subject: [PATCH] Two RTL CC tweaks for SVE pmore/plast conditions SVE has two composite conditions: pmore == at least one bit set && last bit clear plast == no bits set || last bit set So in general we generate them from: A: CC = test bits B: reg1 = first condition C: CC = test bits D: reg2 = second condition E: result = (reg1 op reg2) where op is || or && To fold all this into a single test, we need to be able to remove the redundant C (the cse.c patch) and then fold B, D and E down to a single condition (the simplify-rtx.c patch). The underlying conditions are unsigned, so the simplify-rtx.c part needs to support both unsigned comparisons and AND. However, to avoid opening the can of worms that is ANDing FP comparisons for unordered inputs, I've restricted the new AND handling to cases in which NaNs can be ignored. I think this is still a strict extension of what we have now, it just doesn't go as far as it could. Going further would need an entirely different set of testcases so I think would make more sense as separate work. 2019-11-18 Richard Sandiford gcc/ * cse.c (cse_insn): Delete no-op register moves too. * simplify-rtx.c (comparison_to_mask): Handle unsigned comparisons. Take a second comparison to control the value for NE. (mask_to_comparison): Handle unsigned comparisons. (simplify_logical_relational_operation): Likewise. Update call to comparison_to_mask. Handle AND if !HONOR_NANs. (simplify_binary_operation_1): Call the above for AND too. gcc/testsuite/ * gcc.target/aarch64/sve/acle/asm/ptest_pmore.c: New test. From-SVN: r278411 --- gcc/ChangeLog | 10 +++ gcc/cse.c | 14 ++-- gcc/simplify-rtx.c | 56 ++++++++++++---- gcc/testsuite/ChangeLog | 4 ++ .../gcc.target/aarch64/sve/acle/asm/ptest_pmore.c | 77 ++++++++++++++++++++++ 5 files changed, 140 insertions(+), 21 deletions(-) create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/acle/asm/ptest_pmore.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 932b87a..4198461 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,5 +1,15 @@ 2019-11-18 Richard Sandiford + * cse.c (cse_insn): Delete no-op register moves too. + * simplify-rtx.c (comparison_to_mask): Handle unsigned comparisons. + Take a second comparison to control the value for NE. + (mask_to_comparison): Handle unsigned comparisons. + (simplify_logical_relational_operation): Likewise. Update call + to comparison_to_mask. Handle AND if !HONOR_NANs. + (simplify_binary_operation_1): Call the above for AND too. + +2019-11-18 Richard Sandiford + * fold-const.c (native_encode_vector): Turn into a wrapper function, splitting the main code out into... (native_encode_vector_part): ...this new function. diff --git a/gcc/cse.c b/gcc/cse.c index ab9b8b4..0ab79b9 100644 --- a/gcc/cse.c +++ b/gcc/cse.c @@ -4625,7 +4625,7 @@ cse_insn (rtx_insn *insn) for (i = 0; i < n_sets; i++) { bool repeat = false; - bool mem_noop_insn = false; + bool noop_insn = false; rtx src, dest; rtx src_folded; struct table_elt *elt = 0, *p; @@ -5324,17 +5324,17 @@ cse_insn (rtx_insn *insn) } /* Similarly, lots of targets don't allow no-op - (set (mem x) (mem x)) moves. */ + (set (mem x) (mem x)) moves. Even (set (reg x) (reg x)) + might be impossible for certain registers (like CC registers). */ else if (n_sets == 1 - && MEM_P (trial) - && MEM_P (dest) + && (MEM_P (trial) || REG_P (trial)) && rtx_equal_p (trial, dest) && !side_effects_p (dest) && (cfun->can_delete_dead_exceptions || insn_nothrow_p (insn))) { SET_SRC (sets[i].rtl) = trial; - mem_noop_insn = true; + noop_insn = true; break; } @@ -5562,8 +5562,8 @@ cse_insn (rtx_insn *insn) sets[i].rtl = 0; } - /* Similarly for no-op MEM moves. */ - else if (mem_noop_insn) + /* Similarly for no-op moves. */ + else if (noop_insn) { if (cfun->can_throw_non_call_exceptions && can_throw_internal (insn)) cse_cfg_altered = true; diff --git a/gcc/simplify-rtx.c b/gcc/simplify-rtx.c index b2ba922..f16516e 100644 --- a/gcc/simplify-rtx.c +++ b/gcc/simplify-rtx.c @@ -2125,12 +2125,17 @@ simplify_associative_operation (enum rtx_code code, machine_mode mode, return 0; } -/* Return a mask describing the COMPARISON. */ +/* Return a mask describing the COMPARISON. Treat NE as unsigned + if OTHER_COMPARISON is. */ static int -comparison_to_mask (enum rtx_code comparison) +comparison_to_mask (rtx_code comparison, rtx_code other_comparison) { switch (comparison) { + case LTU: + return 32; + case GTU: + return 16; case LT: return 8; case GT: @@ -2140,6 +2145,10 @@ comparison_to_mask (enum rtx_code comparison) case UNORDERED: return 1; + case LEU: + return 34; + case GEU: + return 18; case LTGT: return 12; case LE: @@ -2156,7 +2165,10 @@ comparison_to_mask (enum rtx_code comparison) case ORDERED: return 14; case NE: - return 13; + return (other_comparison == LTU + || other_comparison == LEU + || other_comparison == GTU + || other_comparison == GEU ? 48 : 13); case UNLE: return 11; case UNGE: @@ -2173,6 +2185,10 @@ mask_to_comparison (int mask) { switch (mask) { + case 32: + return LTU; + case 16: + return GTU; case 8: return LT; case 4: @@ -2182,6 +2198,10 @@ mask_to_comparison (int mask) case 1: return UNORDERED; + case 34: + return LEU; + case 18: + return GEU; case 12: return LTGT; case 10: @@ -2197,6 +2217,7 @@ mask_to_comparison (int mask) case 14: return ORDERED; + case 48: case 13: return NE; case 11: @@ -2216,8 +2237,9 @@ rtx simplify_logical_relational_operation (enum rtx_code code, machine_mode mode, rtx op0, rtx op1) { - /* We only handle IOR of two relational operations. */ - if (code != IOR) + /* We only handle AND if we can ignore unordered cases. */ + bool honor_nans_p = HONOR_NANS (GET_MODE (op0)); + if (code != IOR && (code != AND || honor_nans_p)) return 0; if (!(COMPARISON_P (op0) && COMPARISON_P (op1))) @@ -2230,18 +2252,20 @@ simplify_logical_relational_operation (enum rtx_code code, machine_mode mode, enum rtx_code code0 = GET_CODE (op0); enum rtx_code code1 = GET_CODE (op1); - /* We don't handle unsigned comparisons currently. */ - if (code0 == LTU || code0 == GTU || code0 == LEU || code0 == GEU) - return 0; - if (code1 == LTU || code1 == GTU || code1 == LEU || code1 == GEU) - return 0; + int mask0 = comparison_to_mask (code0, code1); + int mask1 = comparison_to_mask (code1, code0); - int mask0 = comparison_to_mask (code0); - int mask1 = comparison_to_mask (code1); + /* Reject combinations of signed and unsigned comparisons, + with ORDERED being signed. */ + if (((mask0 & 13) && (mask1 & 48)) || ((mask1 & 13) && (mask0 & 48))) + return NULL_RTX; - int mask = mask0 | mask1; + int mask = (code == IOR ? mask0 | mask1 : mask0 & mask1); - if (mask == 15) + if (mask == 0) + return const0_rtx; + + if (mask == 50 || mask == 15) return const_true_rtx; code = mask_to_comparison (mask); @@ -3450,6 +3474,10 @@ simplify_binary_operation_1 (enum rtx_code code, machine_mode mode, tem = simplify_associative_operation (code, mode, op0, op1); if (tem) return tem; + + tem = simplify_logical_relational_operation (code, mode, op0, op1); + if (tem) + return tem; break; case UDIV: diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 033f2e1..3a37d94 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,5 +1,9 @@ 2019-11-18 Richard Sandiford + * gcc.target/aarch64/sve/acle/asm/ptest_pmore.c: New test. + +2019-11-18 Richard Sandiford + * gcc.target/aarch64/sve/acle/general/temporaries_1.c: New test. 2019-11-18 Richard Sandiford diff --git a/gcc/testsuite/gcc.target/aarch64/sve/acle/asm/ptest_pmore.c b/gcc/testsuite/gcc.target/aarch64/sve/acle/asm/ptest_pmore.c new file mode 100644 index 0000000..bdae9b8 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/acle/asm/ptest_pmore.c @@ -0,0 +1,77 @@ +/* { dg-additional-options "-msve-vector-bits=scalable" } */ +/* { dg-final { check-function-bodies "**" "" "-DCHECK_ASM" } } */ + +#include "test_sve_acle.h" +#include + +/* +** test_bool_pmore: +** ptest p0, p1\.b +** cset [wx]0, pmore +** ret +*/ +TEST_PTEST (test_bool_pmore, bool, + x0 = svptest_any (p0, p1) & !svptest_last (p0, p1)); + +/* +** test_bool_plast: +** ptest p0, p1\.b +** cset [wx]0, plast +** ret +*/ +TEST_PTEST (test_bool_plast, bool, + x0 = !svptest_any (p0, p1) | svptest_last (p0, p1)); + +/* +** test_int_pmore: +** ptest p0, p1\.b +** cset [wx]0, pmore +** ret +*/ +TEST_PTEST (test_int_pmore, int, + x0 = svptest_any (p0, p1) & !svptest_last (p0, p1)); + +/* +** test_int_plast: +** ptest p0, p1\.b +** cset [wx]0, plast +** ret +*/ +TEST_PTEST (test_int_plast, int, + x0 = !svptest_any (p0, p1) | svptest_last (p0, p1)); + +/* +** test_int64_t_pmore: +** ptest p0, p1\.b +** cset [wx]0, pmore +** ret +*/ +TEST_PTEST (test_int64_t_pmore, int64_t, + x0 = svptest_any (p0, p1) & !svptest_last (p0, p1)); + +/* +** test_int64_t_plast: +** ptest p0, p1\.b +** cset [wx]0, plast +** ret +*/ +TEST_PTEST (test_int64_t_plast, int64_t, + x0 = !svptest_any (p0, p1) | svptest_last (p0, p1)); + +/* +** sel_pmore: +** ptest p0, p1\.b +** csel x0, (x0, x1, pmore|x1, x0, plast) +** ret +*/ +TEST_PTEST (sel_pmore, int64_t, + x0 = svptest_any (p0, p1) & !svptest_last (p0, p1) ? x0 : x1); + +/* +** sel_plast: +** ptest p0, p1\.b +** csel x0, (x0, x1, plast|x1, x0, pmore) +** ret +*/ +TEST_PTEST (sel_plast, int64_t, + x0 = !svptest_any (p0, p1) | svptest_last (p0, p1) ? x0 : x1); -- 2.7.4