Skip to content

R
riscv-gcc-1
Commit 9556ef20 by Prathamesh Kulkarni Committed by Prathamesh Kulkarni
Options

re PR target/88839 ([SVE] Poor implementation of blend-like permutes) 

2019-08-22  Prathamesh Kulkarni  <prathamesh.kulkarni@linaro.org>
	    Richard Sandiford  <richard.sandiford@arm.com>

	PR target/88839
	* config/aarch64/aarch64.c (aarch64_evpc_sel): New function.
	(aarch64_expand_vec_perm_const_1): Call aarch64_evpc_sel.

testsuite/
	* gcc.target/aarch64/sve/sel_1.c: New test.
	* gcc.target/aarch64/sve/sel_2.c: Likewise.
	* gcc.target/aarch64/sve/sel_3.c: Likewise.
	* gcc.target/aarch64/sve/sel_4.c: Likewise.
	* gcc.target/aarch64/sve/sel_5.c: Likewise.
	* gcc.target/aarch64/sve/sel_6.c: Likewise.

Co-Authored-By: Richard Sandiford <richard.sandiford@arm.com>

From-SVN: r274810
parent 846f78d4
Showing with 324 additions and 0 deletions
gcc/ChangeLog
2019-08-22 Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Richard Sandiford <richard.sandiford@arm.com>
PR target/88839
* config/aarch64/aarch64.c (aarch64_evpc_sel): New function.
(aarch64_expand_vec_perm_const_1): Call aarch64_evpc_sel.
2019-08-21 Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
PR target/90724
......
gcc/config/aarch64/aarch64.c
......@@ -17975,6 +17975,50 @@ aarch64_evpc_sve_tbl (struct expand_vec_perm_d *d)
return true;
}
/* Try to implement D using SVE SEL instruction. */
static bool
aarch64_evpc_sel (struct expand_vec_perm_d *d)
{
machine_mode vmode = d->vmode;
int unit_size = GET_MODE_UNIT_SIZE (vmode);
if (d->vec_flags != VEC_SVE_DATA
|| unit_size > 8)
return false;
int n_patterns = d->perm.encoding ().npatterns ();
poly_int64 vec_len = d->perm.length ();
for (int i = 0; i < n_patterns; ++i)
if (!known_eq (d->perm[i], i)
&& !known_eq (d->perm[i], vec_len + i))
return false;
for (int i = n_patterns; i < n_patterns * 2; i++)
if (!d->perm.series_p (i, n_patterns, i, n_patterns)
&& !d->perm.series_p (i, n_patterns, vec_len + i, n_patterns))
return false;
if (d->testing_p)
return true;
machine_mode pred_mode = aarch64_sve_pred_mode (unit_size).require ();
rtx_vector_builder builder (pred_mode, n_patterns, 2);
for (int i = 0; i < n_patterns * 2; i++)
{
rtx elem = known_eq (d->perm[i], i) ? CONST1_RTX (BImode)
: CONST0_RTX (BImode);
builder.quick_push (elem);
}
rtx const_vec = builder.build ();
rtx pred = force_reg (pred_mode, const_vec);
emit_insn (gen_vcond_mask (vmode, vmode, d->target, d->op1, d->op0, pred));
return true;
}
static bool
aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
{
......@@ -18007,6 +18051,8 @@ aarch64_expand_vec_perm_const_1 (struct expand_vec_perm_d *d)
return true;
else if (aarch64_evpc_trn (d))
return true;
else if (aarch64_evpc_sel (d))
return true;
if (d->vec_flags == VEC_SVE_DATA)
return aarch64_evpc_sve_tbl (d);
else if (d->vec_flags == VEC_ADVSIMD)
......
gcc/testsuite/ChangeLog
2019-08-22 Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Richard Sandiford <richard.sandiford@arm.com>
PR target/88839
* gcc.target/aarch64/sve/sel_1.c: New test.
* gcc.target/aarch64/sve/sel_2.c: Likewise.
* gcc.target/aarch64/sve/sel_3.c: Likewise.
* gcc.target/aarch64/sve/sel_4.c: Likewise.
* gcc.target/aarch64/sve/sel_5.c: Likewise.
* gcc.target/aarch64/sve/sel_6.c: Likewise.
2019-08-21 Richard Sandiford <richard.sandiford@arm.com>
PR c++/91505
......
gcc/testsuite/gcc.target/aarch64/sve/sel_1.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int8_t vnx16qi __attribute__((vector_size (32)));
/* Predicate vector: 1 0 1 0 ... */
#define MASK_32 { 0, 33, 2, 35, 4, 37, 6, 39, 8, 41, \
10, 43, 12, 45, 14, 47, 16, 49, 18, 51, \
20, 53, 22, 55, 24, 57, 26, 59, 28, 61, 30, 63 }
#define INDEX_32 vnx16qi
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx16qi, 32)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.b, p[0-9]+, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
/* { dg-final { scan-assembler-times {\tptrue\tp[0-9]+\.h, vl16\n} 1 } } */
gcc/testsuite/gcc.target/aarch64/sve/sel_2.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int8_t vnx16qi __attribute__((vector_size (32)));
typedef int16_t vnx8hi __attribute__((vector_size (32)));
typedef int32_t vnx4si __attribute__((vector_size (32)));
typedef _Float16 vnx8hf __attribute__((vector_size (32)));
typedef float vnx4sf __attribute__((vector_size (32)));
/* Predicate vector: 1 0 0 0 ... */
#define MASK_32 { 0, 33, 34, 35, 4, 37, 38, 39, 8, 41, 42, 43, 12, \
45, 46, 47, 16, 49, 50, 51, 20, 53, 54, 55, 24, \
57, 58, 59, 28, 61, 62, 63 }
/* Predicate vector: 1 0 1 0 ... */
#define MASK_16 {0, 17, 2, 19, 4, 21, 6, 23, 8, 25, 10, 27, 12, 29, 14, 31}
#define INDEX_32 vnx16qi
#define INDEX_16 vnx8hi
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx16qi, 32)
PERMUTE(vnx8hi, 16)
PERMUTE(vnx8hf, 16)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.b, p[0-9]+, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.h, p[0-9]+, z[0-9]+\.h, z[0-9]+\.h\n} 2 } } */
/* { dg-final { scan-assembler-times {\tptrue\tp[0-9]+\.s, vl8\n} 3 } } */
gcc/testsuite/gcc.target/aarch64/sve/sel_3.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int8_t vnx16qi __attribute__((vector_size (32)));
typedef int16_t vnx8hi __attribute__((vector_size (32)));
typedef int32_t vnx4si __attribute__((vector_size (32)));
typedef _Float16 vnx8hf __attribute__((vector_size (32)));
typedef float vnx4sf __attribute__((vector_size (32)));
/* Predicate vector: 1 0 0 0 0 0 0 0 ... */
#define MASK_32 { 0, 33, 34, 35, 36, 37, 38, 39, \
8, 41, 42, 43, 44, 45, 46, 47, \
16, 49, 50, 51, 52, 53, 54, 55, \
24, 57, 58, 59, 60, 61, 62, 63 }
/* Predicate vector: 1 0 0 0 ... */
#define MASK_16 { 0, 17, 18, 19, 4, 21, 22, 23, \
8, 25, 26, 27, 12, 29, 30, 31 }
/* Predicate vector: 1 0 ... */
#define MASK_8 { 0, 9, 2, 11, 4, 13, 6, 15 }
#define INDEX_32 vnx16qi
#define INDEX_16 vnx8hi
#define INDEX_8 vnx4si
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx16qi, 32)
PERMUTE(vnx8hi, 16)
PERMUTE(vnx4si, 8)
PERMUTE(vnx8hf, 16)
PERMUTE(vnx4sf, 8)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.b, p[0-9]+, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.h, p[0-9]+, z[0-9]+\.h, z[0-9]+\.h\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.s, p[0-9]+, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
/* { dg-final { scan-assembler-times {\tptrue\tp[0-9]+\.d, vl4\n} 5 } } */
gcc/testsuite/gcc.target/aarch64/sve/sel_4.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int8_t vnx16qi __attribute__((vector_size (32)));
typedef int16_t vnx8hi __attribute__((vector_size (32)));
typedef int32_t vnx4si __attribute__((vector_size (32)));
typedef int64_t vnx2di __attribute__((vector_size (32)));
typedef _Float16 vnx8hf __attribute__((vector_size (32)));
typedef float vnx4sf __attribute__((vector_size (32)));
typedef double vnx2df __attribute__((vector_size (32)));
/* Predicate vector: 1 1 0 0 ... */
#define MASK_32 { 0, 1, 34, 35, 4, 5, 38, 39, 8, 9, 42, 43, 12, 13, \
46, 47, 16, 17, 50, 51, 20, 21, 54, 55, 24, 25, \
58, 59, 28, 29, 62, 63 }
#define MASK_16 {0, 1, 18, 19, 4, 5, 22, 23, 8, 9, 26, 27, 12, 13, 30, 31}
#define MASK_8 {0, 1, 10, 11, 4, 5, 14, 15}
#define MASK_4 {0, 1, 6, 7}
#define INDEX_32 vnx16qi
#define INDEX_16 vnx8hi
#define INDEX_8 vnx4si
#define INDEX_4 vnx2di
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx16qi, 32)
PERMUTE(vnx8hi, 16)
PERMUTE(vnx4si, 8)
PERMUTE(vnx2di, 4)
PERMUTE(vnx8hf, 16)
PERMUTE(vnx4sf, 8)
PERMUTE(vnx2df, 4)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.b, p[0-9]+, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.h, p[0-9]+, z[0-9]+\.h, z[0-9]+\.h\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.s, p[0-9]+, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.d, p[0-9]+, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
gcc/testsuite/gcc.target/aarch64/sve/sel_5.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int8_t vnx16qi __attribute__((vector_size (32)));
typedef int16_t vnx8hi __attribute__((vector_size (32)));
typedef int32_t vnx4si __attribute__((vector_size (32)));
typedef int64_t vnx2di __attribute__((vector_size (32)));
typedef _Float16 vnx8hf __attribute__((vector_size (32)));
typedef float vnx4sf __attribute__((vector_size (32)));
typedef double vnx2df __attribute__((vector_size (32)));
/* Predicate vector: 1 0 0 1 ... */
#define MASK_32 { 0, 33, 34, 3, 4, 37, 38, 7, 8, 41, 42, 11, 12, 45, 46, \
15, 16, 49, 50, 19, 20, 53, 54, 23, 24, 57, 58, 27, 28, \
61, 62, 31 }
#define MASK_16 {0, 17, 18, 3, 4, 21, 22, 7, 8, 25, 26, 11, 12, 29, 30, 15}
#define MASK_8 {0, 9, 10, 3, 4, 13, 14, 7}
#define MASK_4 {0, 5, 6, 3}
#define INDEX_32 vnx16qi
#define INDEX_16 vnx8hi
#define INDEX_8 vnx4si
#define INDEX_4 vnx2di
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx16qi, 32)
PERMUTE(vnx8hi, 16)
PERMUTE(vnx4si, 8)
PERMUTE(vnx2di, 4)
PERMUTE(vnx8hf, 16)
PERMUTE(vnx4sf, 8)
PERMUTE(vnx2df, 4)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.b, p[0-9]+, z[0-9]+\.b, z[0-9]+\.b\n} 1 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.h, p[0-9]+, z[0-9]+\.h, z[0-9]+\.h\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.s, p[0-9]+, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.d, p[0-9]+, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
gcc/testsuite/gcc.target/aarch64/sve/sel_6.c 0 → 100644
/* { dg-do assemble { target aarch64_asm_sve_ok } } */
/* { dg-options "-O2 -msve-vector-bits=256 --save-temps" } */
#include <stdint.h>
typedef int32_t vnx4si __attribute__((vector_size (32)));
typedef int64_t vnx2di __attribute__((vector_size (32)));
typedef float vnx4sf __attribute__((vector_size (32)));
typedef double vnx2df __attribute__((vector_size (32)));
/* Predicate vector: 1 0 0 0 ... */
#define MASK_32 { 0, 33, 34, 35, 4, 37, 38, 39, 8, 41, 42, 43, 12, \
45, 46, 47, 16, 49, 50, 51, 20, 53, 54, 55, 24, \
57, 58, 59, 28, 61, 62, 63 }
#define MASK_16 {0, 17, 18, 19, 4, 21, 22, 23, 8, 25, 26, 27, 12, 29, 30, 31}
#define MASK_8 {0, 9, 10, 11, 4, 13, 14, 15}
#define MASK_4 {0, 5, 6, 7}
#define INDEX_8 vnx4si
#define INDEX_4 vnx2di
#define PERMUTE(type, nunits) \
type permute_##type (type x, type y) \
{ \
return __builtin_shuffle (x, y, (INDEX_##nunits) MASK_##nunits); \
}
PERMUTE(vnx4si, 8)
PERMUTE(vnx2di, 4)
PERMUTE(vnx4sf, 8)
PERMUTE(vnx2df, 4)
/* { dg-final { scan-assembler-not {\ttbl\t} } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.s, p[0-9]+, z[0-9]+\.s, z[0-9]+\.s\n} 2 } } */
/* { dg-final { scan-assembler-times {\tsel\tz[0-9]+\.d, p[0-9]+, z[0-9]+\.d, z[0-9]+\.d\n} 2 } } */
/* { dg-final { scan-assembler-times {\tptrue\tp[0-9]+\.d, vl4\n} 2 } } */
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment