Skip to content

R
riscv-gcc-1
Commit df62b4af by Ilya Tocar Committed by Kirill Yukhin
Options

avx512erintrin.h (_mm_rcp28_round_sd): Swap operands. 

gcc/
	* config/i386/avx512erintrin.h (_mm_rcp28_round_sd): Swap operands.
	(_mm_rcp28_round_ss): Ditto.
	(_mm_rsqrt28_round_sd): Ditto.
	(_mm_rsqrt28_round_ss): Ditto.
	* config/i386/avx512erintrin.h (_mm_rcp14_round_sd): Ditto.
	(_mm_rcp14_round_ss): Ditto.
	(_mm_rsqrt14_round_sd): Ditto.
	(_mm_rsqrt14_round_ss): Ditto.
	* config/i386/sse.md (rsqrt14<mode>): Put nonimmediate operand as
	the first input operand, get rid of match_dup.
	(avx512er_exp2<mode><mask_name><round_saeonly_name>): Set type
	attribute to sse.
	(<mask_codefor>avx512er_rcp28<mode><mask_name><round_saeonly_name>):
	Ditto.
	(avx512er_vmrcp28<mode><round_saeonly_name>): Put nonimmediate
	operand as the first input operand, set type attribute.
	(<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_saeonly_name>):
	Set type attribute.
	(avx512er_vmrsqrt28<mode><round_saeonly_name>): Put nonimmediate
	operand as the first input operand, set type attribute.


testsuite/gcc/
	* gcc.target/i386/avx512er-vrcp28sd-2.c: Distinguish src1 and src2.
	* gcc.target/i386/avx512er-vrcp28ss-2.c: Call correct intrinsic.
	* gcc.target/i386/avx512er-vrsqrt28sd-2.c: Distinguish src1 and src2.
	* gcc.target/i386/avx512er-vrsqrt28ss-2.c: Ditto.
	* gcc.target/i386/avx512f-vrcp14sd-2.c: Fix reference calculation.
	* gcc.target/i386/avx512f-vrcp14ss-2.c: Fix reference calculation.


Co-Authored-By: Kirill Yukhin <kirill.yukhin@intel.com>

From-SVN: r207932
parent a13cfd3e
Showing with 94 additions and 52 deletions
gcc/ChangeLog
2014-02-20 Ilya Tocar <ilya.tocar@intel.com>
Kirill Yukhin <kirill.yukhin@intel.com>
* config/i386/avx512erintrin.h (_mm_rcp28_round_sd): Swap operands.
(_mm_rcp28_round_ss): Ditto.
(_mm_rsqrt28_round_sd): Ditto.
(_mm_rsqrt28_round_ss): Ditto.
* config/i386/avx512erintrin.h (_mm_rcp14_round_sd): Ditto.
(_mm_rcp14_round_ss): Ditto.
(_mm_rsqrt14_round_sd): Ditto.
(_mm_rsqrt14_round_ss): Ditto.
* config/i386/sse.md (rsqrt14<mode>): Put nonimmediate operand as
the first input operand, get rid of match_dup.
(avx512er_exp2<mode><mask_name><round_saeonly_name>): Set type
attribute to sse.
(<mask_codefor>avx512er_rcp28<mode><mask_name><round_saeonly_name>):
Ditto.
(avx512er_vmrcp28<mode><round_saeonly_name>): Put nonimmediate
operand as the first input operand, set type attribute.
(<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_saeonly_name>):
Set type attribute.
(avx512er_vmrsqrt28<mode><round_saeonly_name>): Put nonimmediate
operand as the first input operand, set type attribute.
2014-02-19 Bill Schmidt <wschmidt@linux.vnet.ibm.com>
* config/rs6000/rs6000.c (vspltis_constant): Fix most significant
......
gcc/config/i386/avx512erintrin.h
......@@ -163,8 +163,8 @@ extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_sd (__m128d __A, __m128d __B, int __R)
{
return (__m128d) __builtin_ia32_rcp28sd_round ((__v2df) __A,
(__v2df) __B,
return (__m128d) __builtin_ia32_rcp28sd_round ((__v2df) __B,
(__v2df) __A,
__R);
}
......@@ -172,8 +172,8 @@ extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_ss (__m128 __A, __m128 __B, int __R)
{
return (__m128) __builtin_ia32_rcp28ss_round ((__v4sf) __A,
(__v4sf) __B,
return (__m128) __builtin_ia32_rcp28ss_round ((__v4sf) __B,
(__v4sf) __A,
__R);
}
......@@ -237,8 +237,8 @@ extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_sd (__m128d __A, __m128d __B, int __R)
{
return (__m128d) __builtin_ia32_rsqrt28sd_round ((__v2df) __A,
(__v2df) __B,
return (__m128d) __builtin_ia32_rsqrt28sd_round ((__v2df) __B,
(__v2df) __A,
__R);
}
......@@ -246,8 +246,8 @@ extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_ss (__m128 __A, __m128 __B, int __R)
{
return (__m128) __builtin_ia32_rsqrt28ss_round ((__v4sf) __A,
(__v4sf) __B,
return (__m128) __builtin_ia32_rsqrt28ss_round ((__v4sf) __B,
(__v4sf) __A,
__R);
}
......@@ -375,16 +375,16 @@ _mm_rsqrt28_round_ss (__m128 __A, __m128 __B, int __R)
_mm512_maskz_rsqrt28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rcp28_sd(A, B) \
__builtin_ia32_rcp28sd_round(A, B, _MM_FROUND_CUR_DIRECTION)
__builtin_ia32_rcp28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rcp28_ss(A, B) \
__builtin_ia32_rcp28ss_round(A, B, _MM_FROUND_CUR_DIRECTION)
__builtin_ia32_rcp28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rsqrt28_sd(A, B) \
__builtin_ia32_rsqrt28sd_round(A, B, _MM_FROUND_CUR_DIRECTION)
__builtin_ia32_rsqrt28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rsqrt28_ss(A, B) \
__builtin_ia32_rsqrt28ss_round(A, B, _MM_FROUND_CUR_DIRECTION)
__builtin_ia32_rsqrt28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)
#ifdef __DISABLE_AVX512ER__
#undef __DISABLE_AVX512ER__
......
gcc/config/i386/avx512fintrin.h
......@@ -1470,16 +1470,16 @@ extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp14_sd (__m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rcp14sd ((__v2df) __A,
(__v2df) __B);
return (__m128d) __builtin_ia32_rcp14sd ((__v2df) __B,
(__v2df) __A);
}
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp14_ss (__m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rcp14ss ((__v4sf) __A,
(__v4sf) __B);
return (__m128) __builtin_ia32_rcp14ss ((__v4sf) __B,
(__v4sf) __A);
}
extern __inline __m512d
......@@ -1544,16 +1544,16 @@ extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt14_sd (__m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rsqrt14sd ((__v2df) __A,
(__v2df) __B);
return (__m128d) __builtin_ia32_rsqrt14sd ((__v2df) __B,
(__v2df) __A);
}
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt14_ss (__m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rsqrt14ss ((__v4sf) __A,
(__v4sf) __B);
return (__m128) __builtin_ia32_rsqrt14ss ((__v4sf) __B,
(__v4sf) __A);
}
#ifdef __OPTIMIZE__
......
gcc/config/i386/sse.md
......@@ -1551,13 +1551,12 @@
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(unspec:VF_128
[(match_operand:VF_128 1 "register_operand" "v")
(match_operand:VF_128 2 "nonimmediate_operand" "vm")]
[(match_operand:VF_128 1 "nonimmediate_operand" "vm")]
UNSPEC_RSQRT14)
(match_dup 1)
(match_operand:VF_128 2 "register_operand" "v")
(const_int 1)))]
"TARGET_AVX512F"
"vrsqrt14<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
"vrsqrt14<ssescalarmodesuffix>\t{%1, %2, %0|%0, %2, %1}"
[(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
......@@ -12804,6 +12803,7 @@
"TARGET_AVX512ER"
"vexp2<ssemodesuffix>\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "type" "sse")
(set_attr "mode" "<MODE>")])
(define_insn "<mask_codefor>avx512er_rcp28<mode><mask_name><round_saeonly_name>"
......@@ -12814,6 +12814,7 @@
"TARGET_AVX512ER"
"vrcp28<ssemodesuffix>\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "type" "sse")
(set_attr "mode" "<MODE>")])
(define_insn "avx512er_vmrcp28<mode><round_saeonly_name>"
......@@ -12825,9 +12826,10 @@
(match_operand:VF_128 2 "register_operand" "v")
(const_int 1)))]
"TARGET_AVX512ER"
"vrcp28<ssescalarmodesuffix>\t{<round_saeonly_op3>%2, %1, %0|%0, %1, %2<round_saeonly_op3>}"
"vrcp28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %1<round_saeonly_op3>}"
[(set_attr "length_immediate" "1")
(set_attr "prefix" "evex")
(set_attr "type" "sse")
(set_attr "mode" "<MODE>")])
(define_insn "<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_saeonly_name>"
......@@ -12838,6 +12840,7 @@
"TARGET_AVX512ER"
"vrsqrt28<ssemodesuffix>\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "type" "sse")
(set_attr "mode" "<MODE>")])
(define_insn "avx512er_vmrsqrt28<mode><round_saeonly_name>"
......@@ -12849,8 +12852,9 @@
(match_operand:VF_128 2 "register_operand" "v")
(const_int 1)))]
"TARGET_AVX512ER"
"vrsqrt28<ssescalarmodesuffix>\t{<round_saeonly_op3>%2, %1, %0|%0, %1, %2<round_saeonly_op3>}"
"vrsqrt28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %1<round_saeonly_op3>}"
[(set_attr "length_immediate" "1")
(set_attr "type" "sse")
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
......
gcc/testsuite/ChangeLog
2014-02-20 Ilya Tocar <ilya.tocar@intel.com>
Kirill Yukhin <kirill.yukhin@intel.com>
* gcc.target/i386/avx512er-vrcp28sd-2.c: Distinguish src1 and src2.
* gcc.target/i386/avx512er-vrcp28ss-2.c: Call correct intrinsic.
* gcc.target/i386/avx512er-vrsqrt28sd-2.c: Distinguish src1 and src2.
* gcc.target/i386/avx512er-vrsqrt28ss-2.c: Ditto.
* gcc.target/i386/avx512f-vrcp14sd-2.c: Fix reference calculation.
* gcc.target/i386/avx512f-vrcp14ss-2.c: Fix reference calculation.
2014-02-19 Jakub Jelinek <jakub@redhat.com>
PR c/37743
......
gcc/testsuite/gcc.target/i386/avx512er-vrcp28sd-2.c
......@@ -10,19 +10,20 @@
void static
avx512er_test (void)
{
union128d src, res;
union128d src1, src2, res;
double res_ref[2];
int i;
for (i = 0; i < 2; i++)
{
src.a[i] = 179.345 - 6.5645 * i;
res_ref[i] = src.a[i];
src1.a[i] = 179.345 - 6.5645 * i;
src2.a[i] = 204179.345 + 6.5645 * i;
res_ref[i] = src1.a[i];
}
res_ref[0] = 1.0 / src.a[0];
res_ref[0] = 1.0 / src2.a[0];
res.x = _mm_rcp28_round_sd (src.x, src.x, _MM_FROUND_NO_EXC);
res.x = _mm_rcp28_round_sd (src1.x, src2.x, _MM_FROUND_NO_EXC);
if (checkVd (res.a, res_ref, 2))
abort ();
......
gcc/testsuite/gcc.target/i386/avx512er-vrcp28ss-2.c
......@@ -10,19 +10,20 @@
void static
avx512er_test (void)
{
union128 src, res;
union128 src1, src2, res;
float res_ref[4];
int i;
for (i = 0; i < 4; i++)
{
src.a[i] = 179.345 - 6.5645 * i;
res_ref[i] = src.a[i];
src1.a[i] = 179.345 - 6.5645 * i;
src2.a[i] = 179345.006 + 6.5645 * i;
res_ref[i] = src1.a[i];
}
res_ref[0] = 1.0 / src.a[0];
res_ref[0] = 1.0 / src2.a[0];
res.x = _mm_rsqrt28_round_ss (src.x, src.x, _MM_FROUND_NO_EXC);
res.x = _mm_rcp28_round_ss (src1.x, src2.x, _MM_FROUND_NO_EXC);
if (checkVf (res.a, res_ref, 4))
abort ();
......
gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28sd-2.c
......@@ -10,19 +10,20 @@
void static
avx512er_test (void)
{
union128d src, res;
union128d src1, src2, res;
double res_ref[2];
int i;
for (i = 0; i < 2; i++)
{
src.a[i] = 179.345 - 6.5645 * i;
res_ref[i] = src.a[i];
src1.a[i] = 179.345 - 6.5645 * i;
src2.a[i] = 45 - 6.5645 * i;
res_ref[i] = src1.a[i];
}
res_ref[0] = 1.0 / sqrt (src.a[0]);
res_ref[0] = 1.0 / sqrt (src2.a[0]);
res.x = _mm_rsqrt28_round_sd (src.x, src.x, _MM_FROUND_NO_EXC);
res.x = _mm_rsqrt28_round_sd (src1.x, src2.x, _MM_FROUND_NO_EXC);
if (checkVd (res.a, res_ref, 2))
abort ();
......
gcc/testsuite/gcc.target/i386/avx512er-vrsqrt28ss-2.c
......@@ -10,19 +10,20 @@
void static
avx512er_test (void)
{
union128 src, res;
union128 src1, src2, res;
float res_ref[4];
int i;
for (i = 0; i < 4; i++)
{
src.a[i] = 179.345 - 6.5645 * i;
res_ref[i] = src.a[i];
src1.a[i] = 179.345 - 6.5645 * i;
src2.a[i] = 179221345 + 6.5645 * i;
res_ref[i] = src1.a[i];
}
res_ref[0] = 1.0 / sqrt (src.a[0]);
res_ref[0] = 1.0 / sqrt (src2.a[0]);
res.x = _mm_rsqrt28_round_ss (src.x, src.x, _MM_FROUND_NO_EXC);
res.x = _mm_rsqrt28_round_ss (src1.x, src2.x, _MM_FROUND_NO_EXC);
if (checkVf (res.a, res_ref, 4))
abort ();
......
gcc/testsuite/gcc.target/i386/avx512f-vrcp14sd-2.c
......@@ -8,8 +8,8 @@
static void
compute_vrcp14sd (double *s1, double *s2, double *r)
{
r[0] = 1.0 / s1[0];
r[1] = s2[1];
r[0] = 1.0 / s2[0];
r[1] = s1[1];
}
static void
......
gcc/testsuite/gcc.target/i386/avx512f-vrcp14ss-2.c
......@@ -8,10 +8,10 @@
static void
compute_vrcp14ss (float *s1, float *s2, float *r)
{
r[0] = 1.0 / s1[0];
r[1] = s2[1];
r[2] = s2[2];
r[3] = s2[3];
r[0] = 1.0 / s2[0];
r[1] = s1[1];
r[2] = s1[2];
r[3] = s1[3];
}
static void
......
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