+2019-10-15 Hongyu Wang <hongtao.wang@intel.com>
+
+ PR target/92035
+ * config/i386/avx512fintrin.h (_mm_mask_roundscale_ss,
+ _mm_maskz_roundscale_ss, _mm_maskz_roundscale_round_ss,
+ _mm_maskz_roundscale_round_ss, _mm_mask_roundscale_sd,
+ _mm_maskz_roundscale_sd, _mm_mask_roundscale_round_sd,
+ _mm_maskz_roundscale_round_sd): New intrinsics.
+ (_mm_roundscale_ss, _mm_roundscale_round_ss): Use
+ __builtin_ia32_rndscales?_mask_round builtins instead of
+ __builtin_ia32_rndscales?_round.
+ * config/i386/i386-builtin.def (__builtin_ia32_rndscaless_round,
+ __builtin_ia32_rndscalesd_round): Remove.
+ (__builtin_ia32_rndscaless_mask_round,
+ __builtin_ia32_rndscalesd_mask_round): New intrinsics.
+ * config/i386/sse.md
+ (avx512f_rndscale<mode><round_saeonly_name>): Renamed to ...
+ (avx512f_rndscale<mode><mask_scalar_name><round_saeonly_scalar_name>):
+ ... this, adjust and add subst atrributes to make it maskable.
+
2019-10-15 Richard Biener <rguenther@suse.de>
PR middle-end/92046
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm, const int __R)
+_mm_roundscale_round_ss (__m128 __A, __m128 __B, const int __imm,
+ const int __R)
+{
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+ (__v4sf) __B, __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_ss (__m128 __A, __mmask8 __B, __m128 __C,
+ __m128 __D, const int __imm, const int __R)
{
- return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
- (__v4sf) __B, __imm, __R);
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+ (__v4sf) __D, __imm,
+ (__v4sf) __A,
+ (__mmask8) __B,
+ __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_ss (__mmask8 __A, __m128 __B, __m128 __C,
+ const int __imm, const int __R)
+{
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+ (__v4sf) __C, __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) __A,
+ __R);
}
extern __inline __m128d
_mm_roundscale_round_sd (__m128d __A, __m128d __B, const int __imm,
const int __R)
{
- return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
- (__v2df) __B, __imm, __R);
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+ (__v2df) __B, __imm,
+ (__v2df)
+ _mm_setzero_pd (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_round_sd (__m128d __A, __mmask8 __B, __m128d __C,
+ __m128d __D, const int __imm, const int __R)
+{
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+ (__v2df) __D, __imm,
+ (__v2df) __A,
+ (__mmask8) __B,
+ __R);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_round_sd (__mmask8 __A, __m128d __B, __m128d __C,
+ const int __imm, const int __R)
+{
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+ (__v2df) __C, __imm,
+ (__v2df)
+ _mm_setzero_pd (),
+ (__mmask8) __A,
+ __R);
}
#else
(int)(C), \
(__v8df)_mm512_setzero_pd(),\
(__mmask8)(A), R))
-#define _mm_roundscale_round_ss(A, B, C, R) \
- ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A), \
- (__v4sf)(__m128)(B), (int)(C), R))
-#define _mm_roundscale_round_sd(A, B, C, R) \
- ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A), \
- (__v2df)(__m128d)(B), (int)(C), R))
+#define _mm_roundscale_round_ss(A, B, I, R) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A), \
+ (__v4sf) (__m128) (B), \
+ (int) (I), \
+ (__v4sf) _mm_setzero_ps (), \
+ (__mmask8) (-1), \
+ (int) (R)))
+#define _mm_mask_roundscale_round_ss(A, U, B, C, I, R) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B), \
+ (__v4sf) (__m128) (C), \
+ (int) (I), \
+ (__v4sf) (__m128) (A), \
+ (__mmask8) (U), \
+ (int) (R)))
+#define _mm_maskz_roundscale_round_ss(U, A, B, I, R) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A), \
+ (__v4sf) (__m128) (B), \
+ (int) (I), \
+ (__v4sf) _mm_setzero_ps (), \
+ (__mmask8) (U), \
+ (int) (R)))
+#define _mm_roundscale_round_sd(A, B, I, R) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A), \
+ (__v2df) (__m128d) (B), \
+ (int) (I), \
+ (__v2df) _mm_setzero_pd (), \
+ (__mmask8) (-1), \
+ (int) (R)))
+#define _mm_mask_roundscale_round_sd(A, U, B, C, I, R) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B), \
+ (__v2df) (__m128d) (C), \
+ (int) (I), \
+ (__v2df) (__m128d) (A), \
+ (__mmask8) (U), \
+ (int) (R)))
+#define _mm_maskz_roundscale_round_sd(U, A, B, I, R) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A), \
+ (__v2df) (__m128d) (B), \
+ (int) (I), \
+ (__v2df) _mm_setzero_pd (), \
+ (__mmask8) (U), \
+ (int) (R)))
#endif
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_roundscale_ss (__m128 __A, __m128 __B, const int __imm)
{
- return (__m128) __builtin_ia32_rndscaless_round ((__v4sf) __A,
- (__v4sf) __B, __imm,
- _MM_FROUND_CUR_DIRECTION);
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __A,
+ (__v4sf) __B, __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_ss (__m128 __A, __mmask8 __B, __m128 __C, __m128 __D,
+ const int __imm)
+{
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __C,
+ (__v4sf) __D, __imm,
+ (__v4sf) __A,
+ (__mmask8) __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_ss (__mmask8 __A, __m128 __B, __m128 __C,
+ const int __imm)
+{
+ return (__m128)
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) __B,
+ (__v4sf) __C, __imm,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_roundscale_sd (__m128d __A, __m128d __B, const int __imm)
{
- return (__m128d) __builtin_ia32_rndscalesd_round ((__v2df) __A,
- (__v2df) __B, __imm,
- _MM_FROUND_CUR_DIRECTION);
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __A,
+ (__v2df) __B, __imm,
+ (__v2df)
+ _mm_setzero_pd (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_roundscale_sd (__m128d __A, __mmask8 __B, __m128d __C, __m128d __D,
+ const int __imm)
+{
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __C,
+ (__v2df) __D, __imm,
+ (__v2df) __A,
+ (__mmask8) __B,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __m128d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_roundscale_sd (__mmask8 __A, __m128d __B, __m128d __C,
+ const int __imm)
+{
+ return (__m128d)
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) __B,
+ (__v2df) __C, __imm,
+ (__v2df)
+ _mm_setzero_pd (),
+ (__mmask8) __A,
+ _MM_FROUND_CUR_DIRECTION);
}
#else
(int)(C), \
(__v8df)_mm512_setzero_pd(),\
(__mmask8)(A), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_ss(A, B, C) \
- ((__m128) __builtin_ia32_rndscaless_round ((__v4sf)(__m128)(A), \
- (__v4sf)(__m128)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_sd(A, B, C) \
- ((__m128d) __builtin_ia32_rndscalesd_round ((__v2df)(__m128d)(A), \
- (__v2df)(__m128d)(B), (int)(C), _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_ss(A, B, I) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A), \
+ (__v4sf) (__m128) (B), \
+ (int) (I), \
+ (__v4sf) _mm_setzero_ps (), \
+ (__mmask8) (-1), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_ss(A, U, B, C, I) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (B), \
+ (__v4sf) (__m128) (C), \
+ (int) (I), \
+ (__v4sf) (__m128) (A), \
+ (__mmask8) (U), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_ss(U, A, B, I) \
+ ((__m128) \
+ __builtin_ia32_rndscaless_mask_round ((__v4sf) (__m128) (A), \
+ (__v4sf) (__m128) (B), \
+ (int) (I), \
+ (__v4sf) _mm_setzero_ps (), \
+ (__mmask8) (U), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm_roundscale_sd(A, B, I) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A), \
+ (__v2df) (__m128d) (B), \
+ (int) (I), \
+ (__v2df) _mm_setzero_pd (), \
+ (__mmask8) (-1), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm_mask_roundscale_sd(A, U, B, C, I) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (B), \
+ (__v2df) (__m128d) (C), \
+ (int) (I), \
+ (__v2df) (__m128d) (A), \
+ (__mmask8) (U), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm_maskz_roundscale_sd(U, A, B, I) \
+ ((__m128d) \
+ __builtin_ia32_rndscalesd_mask_round ((__v2df) (__m128d) (A), \
+ (__v2df) (__m128d) (B), \
+ (int) (I), \
+ (__v2df) _mm_setzero_pd (), \
+ (__mmask8) (U), \
+ _MM_FROUND_CUR_DIRECTION))
#endif
#ifdef __OPTIMIZE__
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_sse_vmmulv4sf3_mask_round, "__builtin_ia32_mulss_mask_round", IX86_BUILTIN_MULSS_MASK_ROUND, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_V4SF_UQI_INT)
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev8df_mask_round, "__builtin_ia32_rndscalepd_mask", IX86_BUILTIN_RNDSCALEPD, UNKNOWN, (int) V8DF_FTYPE_V8DF_INT_V8DF_QI_INT)
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev16sf_mask_round, "__builtin_ia32_rndscaleps_mask", IX86_BUILTIN_RNDSCALEPS, UNKNOWN, (int) V16SF_FTYPE_V16SF_INT_V16SF_HI_INT)
-BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev2df_round, "__builtin_ia32_rndscalesd_round", IX86_BUILTIN_RNDSCALESD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT_INT)
-BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev4sf_round, "__builtin_ia32_rndscaless_round", IX86_BUILTIN_RNDSCALESS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT_INT)
+BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev2df_mask_round, "__builtin_ia32_rndscalesd_mask_round", IX86_BUILTIN_RNDSCALESD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_INT_V2DF_UQI_INT)
+BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_rndscalev4sf_mask_round, "__builtin_ia32_rndscaless_mask_round", IX86_BUILTIN_RNDSCALESS, UNKNOWN, (int) V4SF_FTYPE_V4SF_V4SF_INT_V4SF_UQI_INT)
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_scalefv8df_mask_round, "__builtin_ia32_scalefpd512_mask", IX86_BUILTIN_SCALEFPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_V8DF_UQI_INT)
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_scalefv16sf_mask_round, "__builtin_ia32_scalefps512_mask", IX86_BUILTIN_SCALEFPS512, UNKNOWN, (int) V16SF_FTYPE_V16SF_V16SF_V16SF_HI_INT)
BDESC (OPTION_MASK_ISA_AVX512F, 0, CODE_FOR_avx512f_vmscalefv2df_mask_round, "__builtin_ia32_scalefsd_mask_round", IX86_BUILTIN_SCALEFSD, UNKNOWN, (int) V2DF_FTYPE_V2DF_V2DF_V2DF_UQI_INT)
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_rndscale<mode><round_saeonly_name>"
+(define_insn "avx512f_rndscale<mode><mask_scalar_name><round_saeonly_scalar_name>"
[(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 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")
+ [(match_operand:VF_128 2 "<round_saeonly_scalar_nimm_predicate>" "<round_saeonly_scalar_constraint>")
(match_operand:SI 3 "const_0_to_255_operand")]
UNSPEC_ROUND)
- (match_dup 1)
+ (match_operand:VF_128 1 "register_operand" "v")
(const_int 1)))]
"TARGET_AVX512F"
- "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %<iptr>2<round_saeonly_op4>, %3}"
+ "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_scalar_mask_op4>%2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %<iptr>2<round_saeonly_scalar_mask_op4>, %3}"
[(set_attr "length_immediate" "1")
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
+2019-10-15 Hongyu Wang <hongyu.wang@intel.com>
+
+ PR target/92035
+ * gcc.target/i386/avx512f-vrndscaless-1.c: Add scan-assembler-times
+ directives for newly expected instructions.
+ * gcc.target/i386/avx512f-vrndscalesd-1.c: Likewise.
+ * gcc.target/i386/avx512f-vrndscaless-2.c
+ (avx512f_test): Add tests for new intrinsics.
+ * gcc.target/i386/avx512f-vrndscalesd-2.c: Likewise.
+ * gcc.target/i386/avx-1.c (__builtin_ia32_rndscalefss_round,
+ __builtin_ia32_rndscalefsd_round): Remove.
+ (__builtin_ia32_rndscalefss_mask_round,
+ __builtin_ia32_rndscalefsd_mask_round): Define.
+ * gcc.target/i386/sse-13.c: Ditto.
+ * gcc.target/i386/sse-23.c: Ditto.
+
2019-10-15 Richard Biener <rguenther@suse.de>
PR middle-end/92046
#define __builtin_ia32_pternlogq512_maskz(A, B, C, F, E) __builtin_ia32_pternlogq512_maskz(A, B, C, 1, E)
#define __builtin_ia32_rndscalepd_mask(A, F, C, D, E) __builtin_ia32_rndscalepd_mask(A, 1, C, D, 8)
#define __builtin_ia32_rndscaleps_mask(A, F, C, D, E) __builtin_ia32_rndscaleps_mask(A, 1, C, D, 8)
-#define __builtin_ia32_rndscalesd_round(A, B, C, D) __builtin_ia32_rndscalesd_round(A, B, 1, 4)
-#define __builtin_ia32_rndscaless_round(A, B, C, D) __builtin_ia32_rndscaless_round(A, B, 1, 4)
+#define __builtin_ia32_rndscalesd_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesd_mask_round(A, B, 1, D, E, 4)
+#define __builtin_ia32_rndscaless_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscaless_mask_round(A, B, 1, D, E, 4)
#define __builtin_ia32_scalefpd512_mask(A, B, C, D, E) __builtin_ia32_scalefpd512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefps512_mask(A, B, C, D, E) __builtin_ia32_scalefps512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefsd_mask_round(A, B, C, D, E) __builtin_ia32_scalefsd_mask_round(A, B, C, D, 8)
/* { dg-do compile } */
/* { dg-options "-mavx512f -O2" } */
-/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\\S*,\[ \\t\]+\{sae\}\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscalesd\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
#include <immintrin.h>
volatile __m128d x1, x2;
+volatile __mmask8 m;
void extern
avx512f_test (void)
{
x1 = _mm_roundscale_sd (x1, x2, 0x42);
x1 = _mm_roundscale_round_sd (x1, x2, 0x42, _MM_FROUND_NO_EXC);
+ x1 = _mm_mask_roundscale_sd (x1, m, x1, x2, 0x42);
+ x1 = _mm_mask_roundscale_round_sd (x1, m, x1, x2, 0x42, _MM_FROUND_NO_EXC);
+ x1 = _mm_maskz_roundscale_sd (m, x1, x2, 0x42);
+ x1 = _mm_maskz_roundscale_round_sd (m, x1, x2, 0x42, _MM_FROUND_NO_EXC);
}
#include <math.h>
#include "avx512f-check.h"
+#include "avx512f-mask-type.h"
static void
compute_rndscalesd (double *s1, double *s2, double *r, int imm)
static void
avx512f_test (void)
{
- int imm = _MM_FROUND_FLOOR | (7 << 4);
- union128d s1, s2, res1;
+ int i, imm;
+ union128d s1, s2, res1, res2, res3, res4, res5, res6;
double res_ref[SIZE];
+
+ MASK_TYPE mask = MASK_VALUE;
+
+ imm = _MM_FROUND_FLOOR | (7 << 4);
s1.x = _mm_set_pd (4.05084, -1.23162);
s2.x = _mm_set_pd (-3.53222, 7.33527);
+ for(i = 0; i < SIZE; i++)
+ {
+ res2.a[i] = DEFAULT_VALUE;
+ res5.a[i] = DEFAULT_VALUE;
+ }
+
res1.x = _mm_roundscale_sd (s1.x, s2.x, imm);
+ res2.x = _mm_mask_roundscale_sd (res2.x, mask, s1.x, s2.x, imm);
+ res3.x = _mm_maskz_roundscale_sd (mask, s1.x, s2.x, imm);
+ res4.x = _mm_roundscale_round_sd (s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
+ res5.x = _mm_mask_roundscale_round_sd (res5.x, mask, s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
+ res6.x = _mm_maskz_roundscale_round_sd (mask, s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
compute_rndscalesd (s1.a, s2.a, res_ref, imm);
if (check_union128d (res1, res_ref))
abort ();
+
+ MASK_MERGE (d) (res_ref, mask, 1);
+ if (check_union128d (res2, res_ref))
+ abort ();
+
+ MASK_ZERO (d) (res_ref, mask, 1);
+ if (check_union128d (res3, res_ref))
+ abort ();
+
+ compute_rndscalesd (s1.a, s2.a, res_ref, imm);
+
+ if (check_union128d (res4, res_ref))
+ abort ();
+
+ MASK_MERGE (d) (res_ref, mask, 1);
+ if (check_union128d (res5, res_ref))
+ abort ();
+
+ MASK_ZERO (d) (res_ref, mask, 1);
+ if (check_union128d (res6, res_ref))
+ abort ();
+
}
/* { dg-do compile } */
/* { dg-options "-mavx512f -O2" } */
-/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\\S*,\[ \\t\]+\{sae\}\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vrndscaless\[ \\t\]+\[^\n\]*\{sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
#include <immintrin.h>
volatile __m128 x1, x2;
+volatile __mmask8 m;
void extern
avx512f_test (void)
{
x1 = _mm_roundscale_ss (x1, x2, 0x42);
x1 = _mm_roundscale_round_ss (x1, x2, 0x42, _MM_FROUND_NO_EXC);
+ x1 = _mm_mask_roundscale_ss (x1, m, x1, x2, 0x42);
+ x1 = _mm_mask_roundscale_round_ss (x1, m, x1, x2, 0x42, _MM_FROUND_NO_EXC);
+ x1 = _mm_maskz_roundscale_ss (m, x1, x2, 0x42);
+ x1 = _mm_maskz_roundscale_round_ss (m, x1, x2, 0x42, _MM_FROUND_NO_EXC);
}
#include <math.h>
#include "avx512f-check.h"
+#include "avx512f-mask-type.h"
static void
compute_rndscaless (float *s1, float *s2, float *r, int imm)
static void
avx512f_test (void)
{
- int imm = _MM_FROUND_FLOOR | (7 << 4);
- union128 s1, s2, res1;
+ int i, imm;
+ union128 s1, s2, res1, res2, res3, res4, res5, res6;
float res_ref[SIZE];
+
+ MASK_TYPE mask = MASK_VALUE;
+ imm = _MM_FROUND_FLOOR | (7 << 4);
+
s1.x = _mm_set_ps (4.05084, -1.23162, 2.00231, -6.22103);
s2.x = _mm_set_ps (-4.19319, -3.53222, 7.33527, 5.57655);
+
+ for(i = 0; i < SIZE; i++)
+ {
+ res2.a[i] = DEFAULT_VALUE;
+ res5.a[i] = DEFAULT_VALUE;
+ }
res1.x = _mm_roundscale_ss (s1.x, s2.x, imm);
+ res2.x = _mm_mask_roundscale_ss (res2.x, mask, s1.x, s2.x, imm);
+ res3.x = _mm_maskz_roundscale_ss (mask, s1.x, s2.x, imm);
+ res4.x = _mm_roundscale_round_ss (s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
+ res5.x = _mm_mask_roundscale_round_ss (res5.x, mask, s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
+ res6.x = _mm_maskz_roundscale_round_ss (mask, s1.x, s2.x, imm, _MM_FROUND_NO_EXC);
compute_rndscaless (s1.a, s2.a, res_ref, imm);
if (check_union128 (res1, res_ref))
abort ();
+
+ MASK_MERGE () (res_ref, mask, 1);
+ if (check_union128 (res2, res_ref))
+ abort ();
+
+ MASK_ZERO () (res_ref, mask, 1);
+ if (check_union128 (res3, res_ref))
+ abort ();
+
+ compute_rndscaless (s1.a, s2.a, res_ref, imm);
+
+ if (check_union128 (res4, res_ref))
+ abort ();
+
+ MASK_MERGE () (res_ref, mask, 1);
+ if (check_union128 (res5, res_ref))
+ abort ();
+
+ MASK_ZERO () (res_ref, mask, 1);
+ if (check_union128 (res6, res_ref))
+ abort ();
}
#define __builtin_ia32_pternlogq512_maskz(A, B, C, F, E) __builtin_ia32_pternlogq512_maskz(A, B, C, 1, E)
#define __builtin_ia32_rndscalepd_mask(A, F, C, D, E) __builtin_ia32_rndscalepd_mask(A, 1, C, D, 8)
#define __builtin_ia32_rndscaleps_mask(A, F, C, D, E) __builtin_ia32_rndscaleps_mask(A, 1, C, D, 8)
-#define __builtin_ia32_rndscalesd_round(A, B, C, D) __builtin_ia32_rndscalesd_round(A, B, 1, 4)
-#define __builtin_ia32_rndscaless_round(A, B, C, D) __builtin_ia32_rndscaless_round(A, B, 1, 4)
+#define __builtin_ia32_rndscalesd_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesd_mask_round(A, B, 1, D, E, 4)
+#define __builtin_ia32_rndscaless_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscaless_mask_round(A, B, 1, D, E, 4)
#define __builtin_ia32_scalefpd512_mask(A, B, C, D, E) __builtin_ia32_scalefpd512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefps512_mask(A, B, C, D, E) __builtin_ia32_scalefps512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefsd_mask_round(A, B, C, D, E) __builtin_ia32_scalefsd_mask_round(A, B, C, D, 8)
#define __builtin_ia32_pternlogq512_maskz(A, B, C, F, E) __builtin_ia32_pternlogq512_maskz(A, B, C, 1, E)
#define __builtin_ia32_rndscalepd_mask(A, F, C, D, E) __builtin_ia32_rndscalepd_mask(A, 1, C, D, 8)
#define __builtin_ia32_rndscaleps_mask(A, F, C, D, E) __builtin_ia32_rndscaleps_mask(A, 1, C, D, 8)
-#define __builtin_ia32_rndscalesd_round(A, B, C, D) __builtin_ia32_rndscalesd_round(A, B, 1, 4)
-#define __builtin_ia32_rndscaless_round(A, B, C, D) __builtin_ia32_rndscaless_round(A, B, 1, 4)
+#define __builtin_ia32_rndscalesd_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesd_mask_round(A, B, 1, D, E, 4)
+#define __builtin_ia32_rndscaless_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscaless_mask_round(A, B, 1, D, E, 4)
#define __builtin_ia32_scalefpd512_mask(A, B, C, D, E) __builtin_ia32_scalefpd512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefps512_mask(A, B, C, D, E) __builtin_ia32_scalefps512_mask(A, B, C, D, 8)
#define __builtin_ia32_scalefsd_mask_round(A, B, C, D, E) __builtin_ia32_scalefsd_mask_round(A, B, C, D, 8)
projects / gcc.git / commitdiff