From 188d00796f5bd338b9b8ab1cc8ba4b43af8ab8fd Mon Sep 17 00:00:00 2001 From: Joel Hutton Date: Mon, 19 Aug 2019 16:55:20 +0000 Subject: [PATCH] [AArch64] Use scvtf fbits option where appropriate gcc/ChangeLog: 2019-08-19 Joel Hutton * config/aarch64/aarch64-protos.h (aarch64_fpconst_pow2_recip): New prototype * config/aarch64/aarch64.c (aarch64_fpconst_pow2_recip): New function * config/aarch64/aarch64.md (*aarch64_cvtf2_mult): New pattern (*aarch64_cvtf2_mult): New pattern * config/aarch64/constraints.md (Dt): New constraint * config/aarch64/predicates.md (aarch64_fpconst_pow2_recip): New predicate gcc/testsuite/ChangeLog: 2019-08-19 Joel Hutton * gcc.target/aarch64/fmul_scvtf_1.c: New test. From-SVN: r274676 --- gcc/ChangeLog | 9 ++ gcc/config/aarch64/aarch64-protos.h | 1 + gcc/config/aarch64/aarch64.c | 23 +++ gcc/config/aarch64/aarch64.md | 39 +++++ gcc/config/aarch64/constraints.md | 7 + gcc/config/aarch64/predicates.md | 4 + gcc/testsuite/ChangeLog | 4 + .../gcc.target/aarch64/fmul_scvtf_1.c | 140 ++++++++++++++++++ 8 files changed, 227 insertions(+) create mode 100644 gcc/testsuite/gcc.target/aarch64/fmul_scvtf_1.c diff --git a/gcc/ChangeLog b/gcc/ChangeLog index ccc63c24a71..895e5f12792 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,12 @@ +2019-08-19 Joel Hutton + + * config/aarch64/aarch64-protos.h (aarch64_fpconst_pow2_recip): New prototype + * config/aarch64/aarch64.c (aarch64_fpconst_pow2_recip): New function + * config/aarch64/aarch64.md (*aarch64_cvtf2_mult): New pattern + (*aarch64_cvtf2_mult): New pattern + * config/aarch64/constraints.md (Dt): New constraint + * config/aarch64/predicates.md (aarch64_fpconst_pow2_recip): New predicate + 2019-08-19 Richard Biener PR tree-optimization/91403 diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h index 89e5e28aeeb..c4b73d26df6 100644 --- a/gcc/config/aarch64/aarch64-protos.h +++ b/gcc/config/aarch64/aarch64-protos.h @@ -525,6 +525,7 @@ enum aarch64_symbol_type aarch64_classify_tls_symbol (rtx); enum reg_class aarch64_regno_regclass (unsigned); int aarch64_asm_preferred_eh_data_format (int, int); int aarch64_fpconst_pow_of_2 (rtx); +int aarch64_fpconst_pow2_recip (rtx); machine_mode aarch64_hard_regno_caller_save_mode (unsigned, unsigned, machine_mode); int aarch64_uxt_size (int, HOST_WIDE_INT); diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c index 84341c041cf..be0162244a2 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -19750,6 +19750,29 @@ aarch64_fpconst_pow_of_2 (rtx x) return exact_log2 (real_to_integer (r)); } +/* If X is a positive CONST_DOUBLE with a value that is the reciprocal of a + power of 2 (i.e 1/2^n) return the number of float bits. e.g. for x==(1/2^n) + return n. Otherwise return -1. */ + +int +aarch64_fpconst_pow2_recip (rtx x) +{ + REAL_VALUE_TYPE r0; + + if (!CONST_DOUBLE_P (x)) + return -1; + + r0 = *CONST_DOUBLE_REAL_VALUE (x); + if (exact_real_inverse (DFmode, &r0) + && !REAL_VALUE_NEGATIVE (r0)) + { + int ret = exact_log2 (real_to_integer (&r0)); + if (ret >= 1 && ret <= 32) + return ret; + } + return -1; +} + /* If X is a vector of equal CONST_DOUBLE values and that value is Y, return the aarch64_fpconst_pow_of_2 of Y. Otherwise return -1. */ diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md index cf561f00bb0..9a07f631010 100644 --- a/gcc/config/aarch64/aarch64.md +++ b/gcc/config/aarch64/aarch64.md @@ -6051,6 +6051,44 @@ [(set_attr "type" "f_cvtf2i")] ) +;; Equal width integer to fp and multiply combine. +(define_insn "*aarch64_cvtf2_mult" + [(set (match_operand:GPF 0 "register_operand" "=w,w") + (mult:GPF (FLOATUORS:GPF + (match_operand: 1 "register_operand" "w,?r")) + (match_operand:GPF 2 "aarch64_fp_pow2_recip" "Dt,Dt")))] + "TARGET_FLOAT" + { + operands[2] = GEN_INT (aarch64_fpconst_pow2_recip (operands[2])); + switch (which_alternative) + { + case 0: + return "cvtf\t%0, %1, #%2"; + case 1: + return "cvtf\t%0, %1, #%2"; + default: + gcc_unreachable (); + } + } + [(set_attr "type" "neon_int_to_fp_,f_cvti2f") + (set_attr "arch" "simd,fp")] +) + +;; Unequal width integer to fp and multiply combine. +(define_insn "*aarch64_cvtf2_mult" + [(set (match_operand:GPF 0 "register_operand" "=w") + (mult:GPF (FLOATUORS:GPF + (match_operand: 1 "register_operand" "r")) + (match_operand:GPF 2 "aarch64_fp_pow2_recip" "Dt")))] + "TARGET_FLOAT" + { + operands[2] = GEN_INT (aarch64_fpconst_pow2_recip (operands[2])); + return "cvtf\t%0, %1, #%2"; + } + [(set_attr "type" "f_cvti2f")] +) + +;; Equal width integer to fp conversion. (define_insn "2" [(set (match_operand:GPF 0 "register_operand" "=w,w") (FLOATUORS:GPF (match_operand: 1 "register_operand" "w,?r")))] @@ -6062,6 +6100,7 @@ (set_attr "arch" "simd,fp")] ) +;; Unequal width integer to fp conversions. (define_insn "2" [(set (match_operand:GPF 0 "register_operand" "=w") (FLOATUORS:GPF (match_operand: 1 "register_operand" "r")))] diff --git a/gcc/config/aarch64/constraints.md b/gcc/config/aarch64/constraints.md index 1a43beee994..9326beca87d 100644 --- a/gcc/config/aarch64/constraints.md +++ b/gcc/config/aarch64/constraints.md @@ -344,6 +344,13 @@ (match_test "aarch64_simd_scalar_immediate_valid_for_move (op, QImode)"))) +(define_constraint "Dt" + "@internal + A const_double which is the reciprocal of an exact power of two, can be + used in an scvtf with fract bits operation" + (and (match_code "const_double") + (match_test "aarch64_fpconst_pow2_recip (op) > 0"))) + (define_constraint "Dl" "@internal A constraint that matches vector of immediates for left shifts." diff --git a/gcc/config/aarch64/predicates.md b/gcc/config/aarch64/predicates.md index 593b1be29df..d8c377994d6 100644 --- a/gcc/config/aarch64/predicates.md +++ b/gcc/config/aarch64/predicates.md @@ -104,6 +104,10 @@ (and (match_code "const_double") (match_test "aarch64_fpconst_pow_of_2 (op) > 0"))) +(define_predicate "aarch64_fp_pow2_recip" + (and (match_code "const_double") + (match_test "aarch64_fpconst_pow2_recip (op) > 0"))) + (define_predicate "aarch64_fp_vec_pow2" (match_test "aarch64_vec_fpconst_pow_of_2 (op) > 0")) diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index ad514b11b8a..6f0bec89379 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,7 @@ +2019-08-19 Joel Hutton + + * gcc.target/aarch64/fmul_scvtf_1.c: New test. + 2019-08-19 Marek Polacek PR c++/91264 - detect modifying const objects in constexpr. diff --git a/gcc/testsuite/gcc.target/aarch64/fmul_scvtf_1.c b/gcc/testsuite/gcc.target/aarch64/fmul_scvtf_1.c new file mode 100644 index 00000000000..8bfe06ac3e6 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/fmul_scvtf_1.c @@ -0,0 +1,140 @@ +/* { dg-do run } */ +/* { dg-options "-save-temps -O2 -fno-inline" } */ + +#define FUNC_DEFS(__a) \ +float \ +fsfoo##__a (int x) \ +{ \ + return ((float) x)/(1lu << __a); \ +} \ +float \ +fusfoo##__a (unsigned int x) \ +{ \ + return ((float) x)/(1lu << __a); \ +} \ +float \ +fslfoo##__a (long long x) \ +{ \ + return ((float) x)/(1lu << __a); \ +} \ +float \ +fulfoo##__a (unsigned long long x) \ +{ \ + return ((float) x)/(1lu << __a); \ +} \ + +#define FUNC_DEFD(__a) \ +double \ +dsfoo##__a (int x) \ +{ \ + return ((double) x)/(1lu << __a); \ +} \ +double \ +dusfoo##__a (unsigned int x) \ +{ \ + return ((double) x)/(1lu << __a); \ +} \ +double \ +dslfoo##__a (long long x) \ +{ \ + return ((double) x)/(1lu << __a); \ +} \ +double \ +dulfoo##__a (unsigned long long x) \ +{ \ + return ((double) x)/(1lu << __a); \ +} + +FUNC_DEFS (4) + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], w\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], w\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], x\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], x\[0-9\]*.*#4" 1 } } */ + +FUNC_DEFD (4) + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], w\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], w\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], x\[0-9\]*.*#4" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], x\[0-9\]*.*#4" 1 } } */ + +FUNC_DEFS (8) + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], w\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], w\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], x\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], x\[0-9\]*.*#8" 1 } } */ + +FUNC_DEFD (8) + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], w\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], w\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], x\[0-9\]*.*#8" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], x\[0-9\]*.*#8" 1 } } */ + +FUNC_DEFS (16) + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], w\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], w\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], x\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], x\[0-9\]*.*#16" 1 } } */ + +FUNC_DEFD (16) + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], w\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], w\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], x\[0-9\]*.*#16" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], x\[0-9\]*.*#16" 1 } } */ + +FUNC_DEFS (32) + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], w\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], w\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\ts\[0-9\], x\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\ts\[0-9\], x\[0-9\]*.*#32" 1 } } */ + +FUNC_DEFD (32) + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], w\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], w\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "scvtf\td\[0-9\], x\[0-9\]*.*#32" 1 } } */ + /* { dg-final { scan-assembler-times "ucvtf\td\[0-9\], x\[0-9\]*.*#32" 1 } } */ + +#define FUNC_TESTS(__a, __b) \ +do \ +{ \ + if (fsfoo##__a (__b) != ((int) i) * (1.0f/(1lu << __a)) ) \ + __builtin_abort (); \ + if (fusfoo##__a (__b) != ((int) i) * (1.0f/(1lu << __a)) ) \ + __builtin_abort (); \ + if (fslfoo##__a (__b) != ((int) i) * (1.0f/(1lu << __a)) ) \ + __builtin_abort (); \ + if (fulfoo##__a (__b) != ((int) i) * (1.0f/(1lu << __a)) ) \ + __builtin_abort (); \ +} while (0) + +#define FUNC_TESTD(__a, __b) \ +do \ +{ \ + if (dsfoo##__a (__b) != ((int) i) * (1.0d/(1lu << __a)) ) \ + __builtin_abort (); \ + if (dusfoo##__a (__b) != ((int) i) * (1.0d/(1lu << __a)) ) \ + __builtin_abort (); \ + if (dslfoo##__a (__b) != ((int) i) * (1.0d/(1lu << __a)) ) \ + __builtin_abort (); \ + if (dulfoo##__a (__b) != ((int) i) * (1.0d/(1lu << __a)) ) \ + __builtin_abort (); \ +} while (0) + +int +main (void) +{ + int i; + + for (i = 0; i < 32; i ++) + { + FUNC_TESTS (4, i); + FUNC_TESTS (8, i); + FUNC_TESTS (16, i); + FUNC_TESTS (32, i); + + FUNC_TESTD (4, i); + FUNC_TESTD (8, i); + FUNC_TESTD (16, i); + FUNC_TESTD (32, i); + } + return 0; +}