diff options
author | Matthew Wahab <matthew.wahab@arm.com> | 2016-09-23 10:48:47 +0000 |
---|---|---|
committer | Matthew Wahab <mwahab@gcc.gnu.org> | 2016-09-23 10:48:47 +0000 |
commit | 785cf02f6855edf92cd70c657478fc1e73f01532 (patch) | |
tree | 45d14c8c981eeb3258703c57cc7cd2fedf1bdccf | |
parent | de955a690b7b888c63ef9f97e8deceba8e9b0f82 (diff) | |
download | gcc-785cf02f6855edf92cd70c657478fc1e73f01532.zip gcc-785cf02f6855edf92cd70c657478fc1e73f01532.tar.gz gcc-785cf02f6855edf92cd70c657478fc1e73f01532.tar.bz2 |
[PATCH 15/17][ARM] Add tests for ARMv8.2-A FP16 support.
testsuite/
2016-09-23 Matthew Wahab <matthew.wahab@arm.com>
* gcc.target/arm/armv8_2-fp16-neon-1.c: New.
* gcc.target/arm/armv8_2-fp16-scalar-1.c: New.
* gcc.target/arm/armv8_2-fp16-scalar-2.c: New.
* gcc.target/arm/attr-fp16-arith-1.c: Add a test of intrinsics
support.
From-SVN: r240425
-rw-r--r-- | gcc/testsuite/ChangeLog | 8 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-1.c | 490 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-1.c | 203 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-2.c | 71 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/arm/attr-fp16-arith-1.c | 13 |
5 files changed, 785 insertions, 0 deletions
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 150aff9..2c35770 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,11 @@ +2016-09-23 Matthew Wahab <matthew.wahab@arm.com> + + * gcc.target/arm/armv8_2-fp16-neon-1.c: New. + * gcc.target/arm/armv8_2-fp16-scalar-1.c: New. + * gcc.target/arm/armv8_2-fp16-scalar-2.c: New. + * gcc.target/arm/attr-fp16-arith-1.c: Add a test of intrinsics + support. + 2016-09-23 Kugan Vivekanandarajah <kuganv@linaro.org> PR ipa/77677 diff --git a/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-1.c b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-1.c new file mode 100644 index 0000000..968efae --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-neon-1.c @@ -0,0 +1,490 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target arm_v8_2a_fp16_neon_ok } */ +/* { dg-options "-O2" } */ +/* { dg-add-options arm_v8_2a_fp16_neon } */ + +/* Test instructions generated for the FP16 vector intrinsics. */ + +#include <arm_neon.h> + +#define MSTRCAT(L, str) L##str + +#define UNOP_TEST(insn) \ + float16x4_t \ + MSTRCAT (test_##insn, _16x4) (float16x4_t a) \ + { \ + return MSTRCAT (insn, _f16) (a); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn, _16x8) (float16x8_t a) \ + { \ + return MSTRCAT (insn, q_f16) (a); \ + } + +#define BINOP_TEST(insn) \ + float16x4_t \ + MSTRCAT (test_##insn, _16x4) (float16x4_t a, float16x4_t b) \ + { \ + return MSTRCAT (insn, _f16) (a, b); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn, _16x8) (float16x8_t a, float16x8_t b) \ + { \ + return MSTRCAT (insn, q_f16) (a, b); \ + } + +#define BINOP_LANE_TEST(insn, I) \ + float16x4_t \ + MSTRCAT (test_##insn##_lane, _16x4) (float16x4_t a, float16x4_t b) \ + { \ + return MSTRCAT (insn, _lane_f16) (a, b, I); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn##_lane, _16x8) (float16x8_t a, float16x4_t b) \ + { \ + return MSTRCAT (insn, q_lane_f16) (a, b, I); \ + } + +#define BINOP_LANEQ_TEST(insn, I) \ + float16x4_t \ + MSTRCAT (test_##insn##_laneq, _16x4) (float16x4_t a, float16x8_t b) \ + { \ + return MSTRCAT (insn, _laneq_f16) (a, b, I); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn##_laneq, _16x8) (float16x8_t a, float16x8_t b) \ + { \ + return MSTRCAT (insn, q_laneq_f16) (a, b, I); \ + } \ + +#define BINOP_N_TEST(insn) \ + float16x4_t \ + MSTRCAT (test_##insn##_n, _16x4) (float16x4_t a, float16_t b) \ + { \ + return MSTRCAT (insn, _n_f16) (a, b); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn##_n, _16x8) (float16x8_t a, float16_t b) \ + { \ + return MSTRCAT (insn, q_n_f16) (a, b); \ + } + +#define TERNOP_TEST(insn) \ + float16_t \ + MSTRCAT (test_##insn, _16) (float16_t a, float16_t b, float16_t c) \ + { \ + return MSTRCAT (insn, h_f16) (a, b, c); \ + } \ + float16x4_t \ + MSTRCAT (test_##insn, _16x4) (float16x4_t a, float16x4_t b, \ + float16x4_t c) \ + { \ + return MSTRCAT (insn, _f16) (a, b, c); \ + } \ + float16x8_t \ + MSTRCAT (test_##insn, _16x8) (float16x8_t a, float16x8_t b, \ + float16x8_t c) \ + { \ + return MSTRCAT (insn, q_f16) (a, b, c); \ + } + +#define VCMP1_TEST(insn) \ + uint16x4_t \ + MSTRCAT (test_##insn, _16x4) (float16x4_t a) \ + { \ + return MSTRCAT (insn, _f16) (a); \ + } \ + uint16x8_t \ + MSTRCAT (test_##insn, _16x8) (float16x8_t a) \ + { \ + return MSTRCAT (insn, q_f16) (a); \ + } + +#define VCMP2_TEST(insn) \ + uint16x4_t \ + MSTRCAT (test_##insn, _16x4) (float16x4_t a, float16x4_t b) \ + { \ + return MSTRCAT (insn, _f16) (a, b); \ + } \ + uint16x8_t \ + MSTRCAT (test_##insn, _16x8) (float16x8_t a, float16x8_t b) \ + { \ + return MSTRCAT (insn, q_f16) (a, b); \ + } + +#define VCVT_TEST(insn, TY, TO, FR) \ + MSTRCAT (TO, 16x4_t) \ + MSTRCAT (test_##insn, TY) (MSTRCAT (FR, 16x4_t) a) \ + { \ + return MSTRCAT (insn, TY) (a); \ + } \ + MSTRCAT (TO, 16x8_t) \ + MSTRCAT (test_##insn##_q, TY) (MSTRCAT (FR, 16x8_t) a) \ + { \ + return MSTRCAT (insn, q##TY) (a); \ + } + +#define VCVT_N_TEST(insn, TY, TO, FR) \ + MSTRCAT (TO, 16x4_t) \ + MSTRCAT (test_##insn##_n, TY) (MSTRCAT (FR, 16x4_t) a) \ + { \ + return MSTRCAT (insn, _n##TY) (a, 1); \ + } \ + MSTRCAT (TO, 16x8_t) \ + MSTRCAT (test_##insn##_n_q, TY) (MSTRCAT (FR, 16x8_t) a) \ + { \ + return MSTRCAT (insn, q_n##TY) (a, 1); \ + } + +VCMP1_TEST (vceqz) +/* { dg-final { scan-assembler-times {vceq\.f16\td[0-9]+, d[0-0]+, #0} 1 } } */ +/* { dg-final { scan-assembler-times {vceq\.f16\tq[0-9]+, q[0-9]+, #0} 1 } } */ + +VCMP1_TEST (vcgtz) +/* { dg-final { scan-assembler-times {vcgt\.f16\td[0-9]+, d[0-9]+, #0} 1 } } */ +/* { dg-final { scan-assembler-times {vceq\.f16\tq[0-9]+, q[0-9]+, #0} 1 } } */ + +VCMP1_TEST (vcgez) +/* { dg-final { scan-assembler-times {vcge\.f16\td[0-9]+, d[0-9]+, #0} 1 } } */ +/* { dg-final { scan-assembler-times {vcge\.f16\tq[0-9]+, q[0-9]+, #0} 1 } } */ + +VCMP1_TEST (vcltz) +/* { dg-final { scan-assembler-times {vclt.f16\td[0-9]+, d[0-9]+, #0} 1 } } */ +/* { dg-final { scan-assembler-times {vclt.f16\tq[0-9]+, q[0-9]+, #0} 1 } } */ + +VCMP1_TEST (vclez) +/* { dg-final { scan-assembler-times {vcle\.f16\td[0-9]+, d[0-9]+, #0} 1 } } */ +/* { dg-final { scan-assembler-times {vcle\.f16\tq[0-9]+, q[0-9]+, #0} 1 } } */ + +VCVT_TEST (vcvt, _f16_s16, float, int) +VCVT_N_TEST (vcvt, _f16_s16, float, int) +/* { dg-final { scan-assembler-times {vcvt\.f16\.s16\td[0-9]+, d[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.f16\.s16\tq[0-9]+, q[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.f16\.s16\td[0-9]+, d[0-9]+, #1} 1 } } + { dg-final { scan-assembler-times {vcvt\.f16\.s16\tq[0-9]+, q[0-9]+, #1} 1 } } */ + +VCVT_TEST (vcvt, _f16_u16, float, uint) +VCVT_N_TEST (vcvt, _f16_u16, float, uint) +/* { dg-final { scan-assembler-times {vcvt\.f16\.u16\td[0-9]+, d[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.f16\.u16\tq[0-9]+, q[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.f16\.u16\td[0-9]+, d[0-9]+, #1} 1 } } + { dg-final { scan-assembler-times {vcvt\.f16\.u16\tq[0-9]+, q[0-9]+, #1} 1 } } */ + +VCVT_TEST (vcvt, _s16_f16, int, float) +VCVT_N_TEST (vcvt, _s16_f16, int, float) +/* { dg-final { scan-assembler-times {vcvt\.s16\.f16\td[0-9]+, d[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.s16\.f16\tq[0-9]+, q[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.s16\.f16\td[0-9]+, d[0-9]+, #1} 1 } } + { dg-final { scan-assembler-times {vcvt\.s16\.f16\tq[0-9]+, q[0-9]+, #1} 1 } } */ + +VCVT_TEST (vcvt, _u16_f16, uint, float) +VCVT_N_TEST (vcvt, _u16_f16, uint, float) +/* { dg-final { scan-assembler-times {vcvt\.u16\.f16\td[0-9]+, d[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.u16\.f16\tq[0-9]+, q[0-9]+} 2 } } + { dg-final { scan-assembler-times {vcvt\.u16\.f16\td[0-9]+, d[0-9]+, #1} 1 } } + { dg-final { scan-assembler-times {vcvt\.u16\.f16\tq[0-9]+, q[0-9]+, #1} 1 } } */ + +VCVT_TEST (vcvta, _s16_f16, int, float) +/* { dg-final { scan-assembler-times {vcvta\.s16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvta\.s16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvta, _u16_f16, uint, float) +/* { dg-final { scan-assembler-times {vcvta\.u16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvta\.u16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtm, _s16_f16, int, float) +/* { dg-final { scan-assembler-times {vcvtm\.s16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtm\.s16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtm, _u16_f16, uint, float) +/* { dg-final { scan-assembler-times {vcvtm\.u16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtm\.u16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtn, _s16_f16, int, float) +/* { dg-final { scan-assembler-times {vcvtn\.s16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtn\.s16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtn, _u16_f16, uint, float) +/* { dg-final { scan-assembler-times {vcvtn\.u16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtn\.u16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtp, _s16_f16, int, float) +/* { dg-final { scan-assembler-times {vcvtp\.s16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtp\.s16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +VCVT_TEST (vcvtp, _u16_f16, uint, float) +/* { dg-final { scan-assembler-times {vcvtp\.u16\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcvtp\.u16\.f16\tq[0-9]+, q[0-9]+} 1 } } +*/ + +UNOP_TEST (vabs) +/* { dg-final { scan-assembler-times {vabs\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vabs\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vneg) +/* { dg-final { scan-assembler-times {vneg\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vneg\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrecpe) +/* { dg-final { scan-assembler-times {vrecpe\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrecpe\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrnd) +/* { dg-final { scan-assembler-times {vrintz\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrintz\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrnda) +/* { dg-final { scan-assembler-times {vrinta\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrinta\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrndm) +/* { dg-final { scan-assembler-times {vrintm\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrintm\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrndn) +/* { dg-final { scan-assembler-times {vrintn\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrintn\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrndp) +/* { dg-final { scan-assembler-times {vrintp\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrintp\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrndx) +/* { dg-final { scan-assembler-times {vrintx\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrintx\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +UNOP_TEST (vrsqrte) +/* { dg-final { scan-assembler-times {vrsqrte\.f16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrsqrte\.f16\tq[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vadd) +/* { dg-final { scan-assembler-times {vadd\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vadd\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vabd) +/* { dg-final { scan-assembler-times {vabd\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vabd\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcage) +/* { dg-final { scan-assembler-times {vacge\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vacge\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcagt) +/* { dg-final { scan-assembler-times {vacgt\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vacgt\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcale) +/* { dg-final { scan-assembler-times {vacle\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vacle\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcalt) +/* { dg-final { scan-assembler-times {vaclt\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vaclt\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vceq) +/* { dg-final { scan-assembler-times {vceq\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vceq\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcge) +/* { dg-final { scan-assembler-times {vcge\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcge\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcgt) +/* { dg-final { scan-assembler-times {vcgt\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcgt\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vcle) +/* { dg-final { scan-assembler-times {vcle\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vcle\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +VCMP2_TEST (vclt) +/* { dg-final { scan-assembler-times {vclt\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vclt\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vmax) +/* { dg-final { scan-assembler-times {vmax\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vmax\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vmin) +/* { dg-final { scan-assembler-times {vmin\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vmin\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vmaxnm) +/* { dg-final { scan-assembler-times {vmaxnm\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vmaxnm\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vminnm) +/* { dg-final { scan-assembler-times {vminnm\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vminnm\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vmul) +/* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 3 } } + { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ +BINOP_LANE_TEST (vmul, 2) +/* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+\[2\]} 1 } } + { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, d[0-9]+\[2\]} 1 } } */ +BINOP_N_TEST (vmul) +/* { dg-final { scan-assembler-times {vmul\.f16\td[0-9]+, d[0-9]+, d[0-9]+\[0\]} 1 } } + { dg-final { scan-assembler-times {vmul\.f16\tq[0-9]+, q[0-9]+, d[0-9]+\[0\]} 1 } }*/ + +float16x4_t +test_vpadd_16x4 (float16x4_t a, float16x4_t b) +{ + return vpadd_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vpadd\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } */ + +float16x4_t +test_vpmax_16x4 (float16x4_t a, float16x4_t b) +{ + return vpmax_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vpmax\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } */ + +float16x4_t +test_vpmin_16x4 (float16x4_t a, float16x4_t b) +{ + return vpmin_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vpmin\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } */ + +BINOP_TEST (vsub) +/* { dg-final { scan-assembler-times {vsub\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vsub\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vrecps) +/* { dg-final { scan-assembler-times {vrecps\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrecps\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +BINOP_TEST (vrsqrts) +/* { dg-final { scan-assembler-times {vrsqrts\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrsqrts\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +TERNOP_TEST (vfma) +/* { dg-final { scan-assembler-times {vfma\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vfma\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +TERNOP_TEST (vfms) +/* { dg-final { scan-assembler-times {vfms\.f16\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vfms\.f16\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +float16x4_t +test_vmov_n_f16 (float16_t a) +{ + return vmov_n_f16 (a); +} + +float16x4_t +test_vdup_n_f16 (float16_t a) +{ + return vdup_n_f16 (a); +} +/* { dg-final { scan-assembler-times {vdup\.16\td[0-9]+, r[0-9]+} 2 } } */ + +float16x8_t +test_vmovq_n_f16 (float16_t a) +{ + return vmovq_n_f16 (a); +} + +float16x8_t +test_vdupq_n_f16 (float16_t a) +{ + return vdupq_n_f16 (a); +} +/* { dg-final { scan-assembler-times {vdup\.16\tq[0-9]+, r[0-9]+} 2 } } */ + +float16x4_t +test_vdup_lane_f16 (float16x4_t a) +{ + return vdup_lane_f16 (a, 1); +} +/* { dg-final { scan-assembler-times {vdup\.16\td[0-9]+, d[0-9]+\[1\]} 1 } } */ + +float16x8_t +test_vdupq_lane_f16 (float16x4_t a) +{ + return vdupq_lane_f16 (a, 1); +} +/* { dg-final { scan-assembler-times {vdup\.16\tq[0-9]+, d[0-9]+\[1\]} 1 } } */ + +float16x4_t +test_vext_f16 (float16x4_t a, float16x4_t b) +{ + return vext_f16 (a, b, 1); +} +/* { dg-final { scan-assembler-times {vext\.16\td[0-9]+, d[0-9]+, d[0-9]+, #1} 1 } } */ + +float16x8_t +test_vextq_f16 (float16x8_t a, float16x8_t b) +{ + return vextq_f16 (a, b, 1); +} +/* { dg-final { scan-assembler-times {vext\.16\tq[0-9]+, q[0-9]+, q[0-9]+, #1} 1 } } */ + +UNOP_TEST (vrev64) +/* { dg-final { scan-assembler-times {vrev64\.16\td[0-9]+, d[0-9]+} 1 } } + { dg-final { scan-assembler-times {vrev64\.16\tq[0-9]+, q[0-9]+} 1 } } */ + +float16x4_t +test_vbsl16x4 (uint16x4_t a, float16x4_t b, float16x4_t c) +{ + return vbsl_f16 (a, b, c); +} +/* { dg-final { scan-assembler-times {vbsl\td[0-9]+, d[0-9]+, d[0-9]+} 1 } } */ + +float16x8_t +test_vbslq16x8 (uint16x8_t a, float16x8_t b, float16x8_t c) +{ + return vbslq_f16 (a, b, c); +} +/*{ dg-final { scan-assembler-times {vbsl\tq[0-9]+, q[0-9]+, q[0-9]+} 1 } } */ + +float16x4x2_t +test_vzip16x4 (float16x4_t a, float16x4_t b) +{ + return vzip_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vzip\.16\td[0-9]+, d[0-9]+} 1 } } */ + +float16x8x2_t +test_vzipq16x8 (float16x8_t a, float16x8_t b) +{ + return vzipq_f16 (a, b); +} +/*{ dg-final { scan-assembler-times {vzip\.16\tq[0-9]+, q[0-9]+} 1 } } */ + +float16x4x2_t +test_vuzp16x4 (float16x4_t a, float16x4_t b) +{ + return vuzp_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vuzp\.16\td[0-9]+, d[0-9]+} 1 } } */ + +float16x8x2_t +test_vuzpq16x8 (float16x8_t a, float16x8_t b) +{ + return vuzpq_f16 (a, b); +} +/*{ dg-final { scan-assembler-times {vuzp\.16\tq[0-9]+, q[0-9]+} 1 } } */ + +float16x4x2_t +test_vtrn16x4 (float16x4_t a, float16x4_t b) +{ + return vtrn_f16 (a, b); +} +/* { dg-final { scan-assembler-times {vtrn\.16\td[0-9]+, d[0-9]+} 1 } } */ + +float16x8x2_t +test_vtrnq16x8 (float16x8_t a, float16x8_t b) +{ + return vtrnq_f16 (a, b); +} +/*{ dg-final { scan-assembler-times {vtrn\.16\tq[0-9]+, q[0-9]+} 1 } } */ diff --git a/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-1.c b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-1.c new file mode 100644 index 0000000..2eddb76 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-1.c @@ -0,0 +1,203 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target arm_v8_2a_fp16_scalar_ok } */ +/* { dg-options "-O2" } */ +/* { dg-add-options arm_v8_2a_fp16_scalar } */ + +/* Test instructions generated for the FP16 scalar intrinsics. */ +#include <arm_fp16.h> + +#define MSTRCAT(L, str) L##str + +#define UNOP_TEST(insn) \ + float16_t \ + MSTRCAT (test_##insn, 16) (float16_t a) \ + { \ + return MSTRCAT (insn, h_f16) (a); \ + } + +#define BINOP_TEST(insn) \ + float16_t \ + MSTRCAT (test_##insn, 16) (float16_t a, float16_t b) \ + { \ + return MSTRCAT (insn, h_f16) (a, b); \ + } + +#define TERNOP_TEST(insn) \ + float16_t \ + MSTRCAT (test_##insn, 16) (float16_t a, float16_t b, float16_t c) \ + { \ + return MSTRCAT (insn, h_f16) (a, b, c); \ + } + +float16_t +test_vcvth_f16_s32 (int32_t a) +{ + return vcvth_f16_s32 (a); +} + +float16_t +test_vcvth_n_f16_s32 (int32_t a) +{ + return vcvth_n_f16_s32 (a, 1); +} +/* { dg-final { scan-assembler-times {vcvt\.f16\.s32\ts[0-9]+, s[0-9]+} 2 } } */ +/* { dg-final { scan-assembler-times {vcvt\.f16\.s32\ts[0-9]+, s[0-9]+, #1} 1 } } */ + +float16_t +test_vcvth_f16_u32 (uint32_t a) +{ + return vcvth_f16_u32 (a); +} + +float16_t +test_vcvth_n_f16_u32 (uint32_t a) +{ + return vcvth_n_f16_u32 (a, 1); +} + +/* { dg-final { scan-assembler-times {vcvt\.f16\.u32\ts[0-9]+, s[0-9]+} 2 } } */ +/* { dg-final { scan-assembler-times {vcvt\.f16\.u32\ts[0-9]+, s[0-9]+, #1} 1 } } */ + +uint32_t +test_vcvth_u32_f16 (float16_t a) +{ + return vcvth_u32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvt\.u32\.f16\ts[0-9]+, s[0-9]+} 2 } } */ + +uint32_t +test_vcvth_n_u32_f16 (float16_t a) +{ + return vcvth_n_u32_f16 (a, 1); +} +/* { dg-final { scan-assembler-times {vcvt\.u32\.f16\ts[0-9]+, s[0-9]+, #1} 1 } } */ + +int32_t +test_vcvth_s32_f16 (float16_t a) +{ + return vcvth_s32_f16 (a); +} + +int32_t +test_vcvth_n_s32_f16 (float16_t a) +{ + return vcvth_n_s32_f16 (a, 1); +} + +/* { dg-final { scan-assembler-times {vcvt\.s32\.f16\ts[0-9]+, s[0-9]+} 2 } } */ +/* { dg-final { scan-assembler-times {vcvt\.s32\.f16\ts[0-9]+, s[0-9]+, #1} 1 } } */ + +int32_t +test_vcvtah_s32_f16 (float16_t a) +{ + return vcvtah_s32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvta\.s32\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +uint32_t +test_vcvtah_u32_f16 (float16_t a) +{ + return vcvtah_u32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvta\.u32\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +int32_t +test_vcvtmh_s32_f16 (float16_t a) +{ + return vcvtmh_s32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtm\.s32\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +uint32_t +test_vcvtmh_u32_f16 (float16_t a) +{ + return vcvtmh_u32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtm\.u32\.f16\ts[0-9]+, s[0-9]+} 1 } } + */ + +int32_t +test_vcvtnh_s32_f16 (float16_t a) +{ + return vcvtnh_s32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtn\.s32\.f16\ts[0-9]+, s[0-9]+} 1 } } + */ + +uint32_t +test_vcvtnh_u32_f16 (float16_t a) +{ + return vcvtnh_u32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtn\.u32\.f16\ts[0-9]+, s[0-9]+} 1 } } + */ + +int32_t +test_vcvtph_s32_f16 (float16_t a) +{ + return vcvtph_s32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtp\.s32\.f16\ts[0-9]+, s[0-9]+} 1 } } + */ + +uint32_t +test_vcvtph_u32_f16 (float16_t a) +{ + return vcvtph_u32_f16 (a); +} +/* { dg-final { scan-assembler-times {vcvtp\.u32\.f16\ts[0-9]+, s[0-9]+} 1 } } + */ + +UNOP_TEST (vabs) +/* { dg-final { scan-assembler-times {vabs\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vneg) +/* { dg-final { scan-assembler-times {vneg\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrnd) +/* { dg-final { scan-assembler-times {vrintz\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrndi) +/* { dg-final { scan-assembler-times {vrintr\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrnda) +/* { dg-final { scan-assembler-times {vrinta\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrndm) +/* { dg-final { scan-assembler-times {vrinta\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrndn) +/* { dg-final { scan-assembler-times {vrinta\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrndp) +/* { dg-final { scan-assembler-times {vrinta\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vrndx) +/* { dg-final { scan-assembler-times {vrinta\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +UNOP_TEST (vsqrt) +/* { dg-final { scan-assembler-times {vsqrt\.f16\ts[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vadd) +/* { dg-final { scan-assembler-times {vadd\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vdiv) +/* { dg-final { scan-assembler-times {vdiv\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vmaxnm) +/* { dg-final { scan-assembler-times {vmaxnm\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vminnm) +/* { dg-final { scan-assembler-times {vminnm\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vmul) +/* { dg-final { scan-assembler-times {vmul\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +BINOP_TEST (vsub) +/* { dg-final { scan-assembler-times {vsub\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +TERNOP_TEST (vfma) +/* { dg-final { scan-assembler-times {vfma\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +TERNOP_TEST (vfms) +/* { dg-final { scan-assembler-times {vfms\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ diff --git a/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-2.c b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-2.c new file mode 100644 index 0000000..fa4828d --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/armv8_2-fp16-scalar-2.c @@ -0,0 +1,71 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target arm_v8_2a_fp16_scalar_ok } */ +/* { dg-options "-O2 -std=c11" } */ +/* { dg-add-options arm_v8_2a_fp16_scalar } */ + +/* Test compiler use of FP16 instructions. */ +#include <arm_fp16.h> + +float16_t +test_mov_imm_1 (float16_t a) +{ + return 1.0; +} + +float16_t +test_mov_imm_2 (float16_t a) +{ + float16_t b = 1.0; + return b; +} + +float16_t +test_vmov_imm_3 (float16_t a) +{ + float16_t b = 1.0; + return vaddh_f16 (a, b); +} + +float16_t +test_vmov_imm_4 (float16_t a) +{ + return vaddh_f16 (a, 1.0); +} + +/* { dg-final { scan-assembler-times {vmov.f16\ts[0-9]+, #1\.0e\+0} 4 } } + { dg-final { scan-assembler-times {vadd.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 2 } } */ + +float16_t +test_vmla_1 (float16_t a, float16_t b, float16_t c) +{ + return vaddh_f16 (vmulh_f16 (a, b), c); +} +/* { dg-final { scan-assembler-times {vmla\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +float16_t +test_vmla_2 (float16_t a, float16_t b, float16_t c) +{ + return vsubh_f16 (vmulh_f16 (vnegh_f16 (a), b), c); +} +/* { dg-final { scan-assembler-times {vnmla\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + +float16_t +test_vmls_1 (float16_t a, float16_t b, float16_t c) +{ + return vsubh_f16 (c, vmulh_f16 (a, b)); +} + +float16_t +test_vmls_2 (float16_t a, float16_t b, float16_t c) +{ + return vsubh_f16 (a, vmulh_f16 (b, c)); +} +/* { dg-final { scan-assembler-times {vmls\.f16} 2 } } */ + +float16_t +test_vnmls_1 (float16_t a, float16_t b, float16_t c) +{ + return vsubh_f16 (vmulh_f16 (a, b), c); +} +/* { dg-final { scan-assembler-times {vnmls\.f16\ts[0-9]+, s[0-9]+, s[0-9]+} 1 } } */ + diff --git a/gcc/testsuite/gcc.target/arm/attr-fp16-arith-1.c b/gcc/testsuite/gcc.target/arm/attr-fp16-arith-1.c index 5011315..a93d30f 100644 --- a/gcc/testsuite/gcc.target/arm/attr-fp16-arith-1.c +++ b/gcc/testsuite/gcc.target/arm/attr-fp16-arith-1.c @@ -28,6 +28,19 @@ #error Invalid value for __ARM_FP #endif +#include "arm_neon.h" + +float16_t +foo (float16x4_t b) +{ + float16x4_t a = {2.0, 3.0, 4.0, 5.0}; + float16x4_t res = vadd_f16 (a, b); + + return res[0]; +} + +/* { dg-final { scan-assembler "vadd\\.f16\td\[0-9\]+, d\[0-9\]+" } } */ + #pragma GCC pop_options /* Check that the FP version is correctly reset to mfpu=fp-armv8. */ |