@@ -216,6 +216,138 @@ _mm256_mask_cmp_round_ps_mask (__mmask8 __U, __m256 __A, __m256 __B,
(__mmask8) __U,
__R);
}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_cvt_roundepi32_ph (__m256i __A, const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) __A,
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_cvt_roundepi32_ph (__m128h __W, __mmask8 __U, __m256i __A,
+ const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) __A,
+ (__v8hf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_cvt_roundepi32_ph (__mmask8 __U, __m256i __A, const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) __A,
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_cvt_roundepi32_ps (__m256i __A, const int __R)
+{
+ return (__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) __A,
+ (__v8sf)
+ _mm256_undefined_ps (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_cvt_roundepi32_ps (__m256 __W, __mmask8 __U, __m256i __A,
+ const int __R)
+{
+ return (__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) __A,
+ (__v8sf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_cvt_roundepi32_ps (__mmask8 __U, __m256i __A, const int __R)
+{
+ return (__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_cvt_roundpd_ph (__m256d __A, const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) __A,
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_cvt_roundpd_ph (__m128h __W, __mmask8 __U, __m256d __A,
+ const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) __A,
+ (__v8hf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_cvt_roundpd_ph (__mmask8 __U, __m256d __A, const int __R)
+{
+ return (__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) __A,
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_cvt_roundpd_ps (__m256d __A, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) __A,
+ (__v4sf)
+ _mm_undefined_ps (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_cvt_roundpd_ps (__m128 __W, __mmask8 __U, __m256d __A,
+ const int __R)
+{
+ return (__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) __A,
+ (__v4sf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m128
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_cvt_roundpd_ps (__mmask8 __U, __m256d __A, const int __R)
+{
+ return (__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) __A,
+ (__v4sf)
+ _mm_setzero_ps (),
+ (__mmask8) __U,
+ __R);
+}
#else
#define _mm256_add_round_pd(A, B, R) \
((__m256d) __builtin_ia32_addpd256_mask_round ((__v4df) (A), \
@@ -327,6 +459,84 @@ _mm256_mask_cmp_round_ps_mask (__mmask8 __U, __m256 __A, __m256 __B,
(C), \
(__mmask8) (U), \
(R)))
+
+#define _mm256_cvt_roundepi32_ph(A, R) \
+ ((__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) (A), \
+ (__v8hf) \
+ (_mm_setzero_ph ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_cvt_roundepi32_ph(W, U, A, R) \
+ ((__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) (A), \
+ (__v8hf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_cvt_roundepi32_ph(U, A, R) \
+ ((__m128h) __builtin_ia32_vcvtdq2ph256_mask_round ((__v8si) (A), \
+ (__v8hf) \
+ (_mm_setzero_ph ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_cvt_roundepi32_ps(A, R) \
+ ((__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) (A), \
+ (__v8sf) \
+ (_mm256_undefined_ps ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_cvt_roundepi32_ps(W, U, A, R) \
+ ((__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) (A), \
+ (__v8sf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_cvt_roundepi32_ps(U, A, R) \
+ ((__m256) __builtin_ia32_cvtdq2ps256_mask_round ((__v8si) (A), \
+ (__v8sf) \
+ (_mm256_setzero_ps ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_cvt_roundpd_ph(A, R) \
+ ((__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) (A), \
+ (_mm_setzero_ph ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_cvt_roundpd_ph(W, U, A, R) \
+ ((__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) (A), \
+ (__v8hf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_cvt_roundpd_ph(U, A, R) \
+ ((__m128h) __builtin_ia32_vcvtpd2ph256_mask_round ((__v4df) (A), \
+ (_mm_setzero_ph ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_cvt_roundpd_ps(A, R) \
+ ((__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) (A), \
+ (__v4sf) \
+ (_mm_undefined_ps ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_cvt_roundpd_ps(W, U, A, R) \
+ ((__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) (A), \
+ (__v4sf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_cvt_roundpd_ps(U, A, R) \
+ ((__m128) __builtin_ia32_cvtpd2ps256_mask_round ((__v4df) (A), \
+ (__v4sf) \
+ (_mm_setzero_ps ()), \
+ (__mmask8) (U), \
+ (R)))
#endif
#ifdef __DISABLE_AVX10_2_256__
@@ -1421,3 +1421,7 @@ DEF_FUNCTION_TYPE (V8SF, V8SF, V8SF, V8SF, UQI, INT)
DEF_FUNCTION_TYPE (UQI, V4DF, V4DF, INT, UQI, INT)
DEF_FUNCTION_TYPE (UHI, V16HF, V16HF, INT, UHI, INT)
DEF_FUNCTION_TYPE (UQI, V8SF, V8SF, INT, UQI, INT)
+DEF_FUNCTION_TYPE (V8HF, V8SI, V8HF, UQI, INT)
+DEF_FUNCTION_TYPE (V8SF, V8SI, V8SF, UQI, INT)
+DEF_FUNCTION_TYPE (V8HF, V4DF, V8HF, UQI, INT)
+DEF_FUNCTION_TYPE (V4SF, V4DF, V4SF, UQI, INT)
@@ -3325,6 +3325,10 @@ BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_addv8sf3_mask_round, "__builtin
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx512vl_cmpv4df3_mask_round, "__builtin_ia32_cmppd256_mask_round", IX86_BUILTIN_CMPPD256_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V4DF_V4DF_INT_UQI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx512vl_cmpv16hf3_mask_round, "__builtin_ia32_cmpph256_mask_round", IX86_BUILTIN_CMPPH256_MASK_ROUND, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx512vl_cmpv8sf3_mask_round, "__builtin_ia32_cmpps256_mask_round", IX86_BUILTIN_CMPPS256_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8SF_V8SF_INT_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx512fp16_vcvtdq2ph_v8si_mask_round, "__builtin_ia32_vcvtdq2ph256_mask_round", IX86_BUILTIN_VCVTDQ2PH256_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8SI_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_floatv8siv8sf2_mask_round, "__builtin_ia32_cvtdq2ps256_mask_round", IX86_BUILTIN_VCVTDQ2PS256_MASK_ROUND, UNKNOWN, (int) V8SF_FTYPE_V8SI_V8SF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx512fp16_vcvtpd2ph_v4df_mask_round, "__builtin_ia32_vcvtpd2ph256_mask_round", IX86_BUILTIN_VCVTPD2PH256_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V4DF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx_cvtpd2ps256_mask_round, "__builtin_ia32_cvtpd2ps256_mask_round", IX86_BUILTIN_CVTPD2PS256_MASK_ROUND, UNKNOWN, (int) V4SF_FTYPE_V4DF_V4SF_UQI_INT)
BDESC_END (ROUND_ARGS, MULTI_ARG)
@@ -12464,10 +12464,14 @@ ix86_expand_round_builtin (const struct builtin_description *d,
case V16HF_FTYPE_V16SI_V16HF_UHI_INT:
case V8DF_FTYPE_V8SF_V8DF_QI_INT:
case V16SF_FTYPE_V16HI_V16SF_HI_INT:
+ case V8SF_FTYPE_V8SI_V8SF_UQI_INT:
case V2DF_FTYPE_V2DF_V2DF_V2DF_INT:
+ case V4SF_FTYPE_V4DF_V4SF_UQI_INT:
case V4SF_FTYPE_V4SF_V4SF_V4SF_INT:
case V8HF_FTYPE_V8DI_V8HF_UQI_INT:
case V8HF_FTYPE_V8DF_V8HF_UQI_INT:
+ case V8HF_FTYPE_V8SI_V8HF_UQI_INT:
+ case V8HF_FTYPE_V4DF_V8HF_UQI_INT:
case V16HF_FTYPE_V16SF_V16HF_UHI_INT:
case V8HF_FTYPE_V8HF_V8HF_V8HF_INT:
nargs = 4;
@@ -7384,7 +7384,7 @@
[(set (match_operand:<ssePHmode> 0 "register_operand" "=v")
(any_float:<ssePHmode>
(match_operand:VI2H_AVX512VL 1 "<round_nimm_predicate>" "<round_constraint>")))]
- "TARGET_AVX512FP16"
+ "TARGET_AVX512FP16 && <round_mode_condition>"
"vcvt<floatsuffix><sseintconvert>2ph<round_qq2phsuff>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
@@ -7889,6 +7889,19 @@
(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
+(define_expand "avx512fp16_vcvtpd2ph_v4df_mask_round"
+ [(match_operand:V8HF 0 "register_operand")
+ (match_operand:V4DF 1 "register_operand")
+ (match_operand:V8HF 2 "nonimm_or_0_operand")
+ (match_operand:QI 3 "register_operand")
+ (unspec [(match_operand:SI 4 "const_4_or_8_to_11_operand")] UNSPEC_EMBEDDED_ROUNDING)]
+ "TARGET_AVX10_2_256"
+{
+ emit_insn (gen_avx512fp16_vcvtpd2ph_v4df_mask_round_1 (
+ operands[0], operands[1], operands[2], operands[3], CONST0_RTX (V4HFmode), operands[4]));
+ DONE;
+})
+
(define_expand "avx512fp16_vcvt<castmode>2ph_<mode>_mask"
[(set (match_operand:V8HF 0 "register_operand" "=v")
(vec_concat:V8HF
@@ -7904,20 +7917,20 @@
"TARGET_AVX512FP16 && TARGET_AVX512VL"
"operands[4] = CONST0_RTX (V4HFmode);")
-(define_insn "*avx512fp16_vcvt<castmode>2ph_<mode>_mask"
+(define_insn "avx512fp16_vcvt<castmode>2ph_<mode>_mask<round_name>_1"
[(set (match_operand:V8HF 0 "register_operand" "=v")
(vec_concat:V8HF
(vec_merge:V4HF
(float_truncate:V4HF
- (match_operand:VF4_128_8_256 1 "vector_operand" "vm"))
+ (match_operand:VF4_128_8_256 1 "<round_nimm_predicate>" "<round_constraint>"))
(vec_select:V4HF
(match_operand:V8HF 2 "nonimm_or_0_operand" "0C")
(parallel [(const_int 0) (const_int 1)
(const_int 2) (const_int 3)]))
(match_operand:QI 3 "register_operand" "Yk"))
(match_operand:V4HF 4 "const0_operand")))]
- "TARGET_AVX512FP16 && TARGET_AVX512VL"
- "vcvt<castmode>2ph<ph2pssuffix><qq2phsuff>\t{%1, %0%{%3%}%N2|%0%{%3%}%N2, %1}"
+ "TARGET_AVX512FP16 && TARGET_AVX512VL && <round_mode_condition>"
+ "vcvt<castmode>2ph<ph2pssuffix><round_qq2phsuff>\t{<round_op5>%1, %0%{%3%}%N2|%0%{%3%}%N2, %1<round_op5>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
@@ -9813,12 +9826,13 @@
(set_attr "prefix" "evex")
(set_attr "mode" "V8SF")])
-(define_insn "avx_cvtpd2ps256<mask_name>"
+(define_insn "avx_cvtpd2ps256<mask_name><round_name>"
[(set (match_operand:V4SF 0 "register_operand" "=v")
(float_truncate:V4SF
- (match_operand:V4DF 1 "nonimmediate_operand" "vm")))]
- "TARGET_AVX && <mask_avx512vl_condition>"
- "vcvtpd2ps{y}\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ (match_operand:V4DF 1 "<round_nimm_predicate>" "<round_constraint>")))]
+ "TARGET_AVX && <mask_avx512vl_condition>
+ && (!<round_applied> || TARGET_AVX10_2_256)"
+ "vcvtpd2ps<round_suff>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "maybe_evex")
(set_attr "btver2_decode" "vector")
@@ -197,6 +197,7 @@
(define_subst_attr "round_sd_mask_op4" "round" "" "<round_sd_mask_operand4>")
(define_subst_attr "round_sdc_mask_op4" "round" "" "<round_sdc_mask_operand4>")
(define_subst_attr "round_constraint" "round" "vm" "v")
+(define_subst_attr "round_suff" "round" "{y}" "")
(define_subst_attr "round_qq2phsuff" "round" "<qq2phsuff>" "")
(define_subst_attr "bcst_round_constraint" "round" "vmBr" "v")
(define_subst_attr "round_constraint2" "round" "m" "v")
@@ -209,6 +210,7 @@
|| <MODE>mode == V8DFmode
|| <MODE>mode == V8DImode
|| <MODE>mode == V16SImode
+ || <MODE>mode == V32HImode
|| <MODE>mode == V32HFmode)
|| (TARGET_AVX10_2_256
&& (<MODE>mode == V8SFmode
@@ -216,6 +218,7 @@
|| <MODE>mode == V4DImode
|| <MODE>mode == V8SImode
|| <MODE>mode == V16HFmode)))")
+(define_subst_attr "round_applied" "round" "false" "true")
(define_subst_attr "round_modev4sf_condition" "round" "1" "(<MODE>mode == V4SFmode)")
(define_subst_attr "round_codefor" "round" "*" "")
@@ -260,6 +263,7 @@
|| <MODE>mode == V8DFmode
|| <MODE>mode == V8DImode
|| <MODE>mode == V16SImode
+ || <MODE>mode == V32HImode
|| <MODE>mode == V32HFmode)
|| (TARGET_AVX10_2_256
&& (<MODE>mode == V8SFmode
@@ -849,6 +849,10 @@
#define __builtin_ia32_cmppd256_mask_round(A, B, C, D, E) __builtin_ia32_cmppd256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpph256_mask_round(A, B, C, D, E) __builtin_ia32_cmpph256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpps256_mask_round(A, B, C, D, E) __builtin_ia32_cmpps256_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, 8)
#include <wmmintrin.h>
#include <immintrin.h>
@@ -15,12 +15,27 @@
/* { dg-final { scan-assembler-times "vcmpph\[ \\t\]+\[^\{\n\]*\\\$4\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%k\[0-9\]\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vcmpps\[ \\t\]+\[^\{\n\]*\{sae\}\[^\n\]*%ymm\[0-9\]+\[^\n^k\]*%k\[0-7\](?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vcmpps\[ \\t\]+\[^\{\n\]*\{sae\}\[^\n\]*%ymm\[0-9\]+\[^\n^k\]*%k\[0-7\]\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2phy\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2ph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2ph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2ps\[ \\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2ps\[ \\t\]+\[^\n\]*\{ru-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtdq2ps\[ \\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2phy\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2ph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2ph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2ps\[ \\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2ps\[ \\t\]+\[^\n\]*\{rd-sae\}\[^\{\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vcvtpd2ps\[ \\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
#include <immintrin.h>
+volatile __m128 hx;
+volatile __m128h hxh;
volatile __m256 x;
volatile __m256d xd;
volatile __m256h xh;
+volatile __m256i xi;
volatile __mmask8 m8;
volatile __mmask16 m16;
volatile __mmask32 m32;
@@ -39,7 +54,11 @@ avx10_2_test_1 (void)
x = _mm256_add_round_ps (x, x, _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC);
x = _mm256_mask_add_round_ps (x, m16, x, x, _MM_FROUND_TO_POS_INF | _MM_FROUND_NO_EXC);
x = _mm256_maskz_add_round_ps (m16, x, x, _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC);
+}
+void extern
+avx10_2_test_2 (void)
+{
m8 = _mm256_cmp_round_pd_mask (xd, xd, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
m8 = _mm256_mask_cmp_round_pd_mask (m8, xd, xd, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
@@ -51,14 +70,25 @@ avx10_2_test_1 (void)
}
void extern
-avx10_2_test_2 (void)
+avx10_2_test_3 (void)
{
- m8 = _mm256_cmp_round_pd_mask (xd, xd, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
- m8 = _mm256_mask_cmp_round_pd_mask (m8, xd, xd, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
+ hxh = _mm256_cvt_roundepi32_ph (xi, 4);
+ hxh = _mm256_mask_cvt_roundepi32_ph (hxh, m8, xi, 8);
+ hxh = _mm256_maskz_cvt_roundepi32_ph (m8, xi, 11);
- m16 = _mm256_cmp_round_ph_mask (xh, xh, 3, 8);
- m16 = _mm256_mask_cmp_round_ph_mask (m16, xh, xh, 4, 4);
+ x = _mm256_cvt_roundepi32_ps (xi, _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC);
+ x = _mm256_mask_cvt_roundepi32_ps (x, m8, xi, _MM_FROUND_TO_POS_INF | _MM_FROUND_NO_EXC);
+ x = _mm256_maskz_cvt_roundepi32_ps (m8, xi, _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC);
+}
- m8 = _mm256_cmp_round_ps_mask (x, x, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
- m8 = _mm256_mask_cmp_round_ps_mask (m8, x, x, _CMP_FALSE_OQ, _MM_FROUND_NO_EXC);
+void extern
+avx10_2_test_4 (void)
+{
+ hxh = _mm256_cvt_roundpd_ph (xd, 4);
+ hxh = _mm256_mask_cvt_roundpd_ph (hxh, m8, xd, 8);
+ hxh = _mm256_maskz_cvt_roundpd_ph (m8, xd, 11);
+
+ hx = _mm256_cvt_roundpd_ps (xd, _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC);
+ hx = _mm256_mask_cvt_roundpd_ps (hx, 4, xd, _MM_FROUND_TO_NEG_INF | _MM_FROUND_NO_EXC);
+ hx = _mm256_maskz_cvt_roundpd_ps (6, xd, _MM_FROUND_TO_ZERO | _MM_FROUND_NO_EXC);
}
@@ -856,5 +856,9 @@
#define __builtin_ia32_cmppd256_mask_round(A, B, C, D, E) __builtin_ia32_cmppd256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpph256_mask_round(A, B, C, D, E) __builtin_ia32_cmpph256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpps256_mask_round(A, B, C, D, E) __builtin_ia32_cmpps256_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, 8)
#include <x86intrin.h>
@@ -1021,15 +1021,27 @@ test_2 (_mm512_gf2p8affine_epi64_epi8, __m512i, __m512i, __m512i, 1)
test_3 (_mm_sm3rnds2_epi32, __m128i, __m128i, __m128i, __m128i, 1)
/* avx10_2roundingintrin.h */
+test_1 (_mm256_cvt_roundepi32_ph, __m128h, __m256i, 8)
+test_1 (_mm256_cvt_roundepi32_ps, __m256, __m256i, 9)
+test_1 (_mm256_cvt_roundpd_ph, __m128h, __m256d, 8)
+test_1 (_mm256_cvt_roundpd_ps, __m128, __m256d, 9)
test_2 (_mm256_add_round_pd, __m256d, __m256d, __m256d, 9)
test_2 (_mm256_add_round_ph, __m256h, __m256h, __m256h, 8)
test_2 (_mm256_add_round_ps, __m256, __m256, __m256, 9)
+test_2 (_mm256_maskz_cvt_roundepi32_ph, __m128h, __mmask8, __m256i, 8)
+test_2 (_mm256_maskz_cvt_roundepi32_ps, __m256, __mmask8, __m256i, 9)
+test_2 (_mm256_maskz_cvt_roundpd_ph, __m128h, __mmask8, __m256d, 8)
+test_2 (_mm256_maskz_cvt_roundpd_ps, __m128, __mmask8, __m256d, 9)
test_2x (_mm256_cmp_round_pd_mask, __mmask8, __m256d, __m256d, 1, 8)
test_2x (_mm256_cmp_round_ph_mask, __mmask16, __m256h, __m256h, 1, 8)
test_2x (_mm256_cmp_round_ps_mask, __mmask8, __m256, __m256, 1, 8)
test_3 (_mm256_maskz_add_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
test_3 (_mm256_maskz_add_round_ph, __m256h, __mmask16, __m256h, __m256h, 8)
test_3 (_mm256_maskz_add_round_ps, __m256, __mmask8, __m256, __m256, 9)
+test_3 (_mm256_mask_cvt_roundepi32_ph, __m128h, __m128h, __mmask8, __m256i, 8)
+test_3 (_mm256_mask_cvt_roundepi32_ps, __m256, __m256, __mmask8, __m256i, 9)
+test_3 (_mm256_mask_cvt_roundpd_ph, __m128h, __m128h, __mmask8, __m256d, 8)
+test_3 (_mm256_mask_cvt_roundpd_ps, __m128, __m128, __mmask8, __m256d, 9)
test_3x (_mm256_mask_cmp_round_pd_mask, __mmask8, __mmask8, __m256d, __m256d, 1, 8)
test_3x (_mm256_mask_cmp_round_ph_mask, __mmask16, __mmask16, __m256h, __m256h, 1, 8)
test_3x (_mm256_mask_cmp_round_ps_mask, __mmask8, __mmask8, __m256, __m256, 1, 8)
@@ -1062,15 +1062,27 @@ test_1 ( __bextri_u64, unsigned long long, unsigned long long, 1)
test_3 (_mm_sm3rnds2_epi32, __m128i, __m128i, __m128i, __m128i, 1)
/* avx10_2roundingintrin.h */
+test_1 (_mm256_cvt_roundepi32_ph, __m128h, __m256i, 8)
+test_1 (_mm256_cvt_roundepi32_ps, __m256, __m256i, 9)
+test_1 (_mm256_cvt_roundpd_ph, __m128h, __m256d, 8)
+test_1 (_mm256_cvt_roundpd_ps, __m128, __m256d, 9)
test_2 (_mm256_add_round_pd, __m256d, __m256d, __m256d, 9)
test_2 (_mm256_add_round_ph, __m256h, __m256h, __m256h, 8)
test_2 (_mm256_add_round_ps, __m256, __m256, __m256, 9)
+test_2 (_mm256_maskz_cvt_roundepi32_ph, __m128h, __mmask8, __m256i, 8)
+test_2 (_mm256_maskz_cvt_roundepi32_ps, __m256, __mmask8, __m256i, 9)
+test_2 (_mm256_maskz_cvt_roundpd_ph, __m128h, __mmask8, __m256d, 8)
+test_2 (_mm256_maskz_cvt_roundpd_ps, __m128, __mmask8, __m256d, 9)
test_2x (_mm256_cmp_round_pd_mask, __mmask8, __m256d, __m256d, 1, 8)
test_2x (_mm256_cmp_round_ph_mask, __mmask16, __m256h, __m256h, 1, 8)
test_2x (_mm256_cmp_round_ps_mask, __mmask8, __m256, __m256, 1, 8)
test_3 (_mm256_maskz_add_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
test_3 (_mm256_maskz_add_round_ph, __m256h, __mmask16, __m256h, __m256h, 8)
test_3 (_mm256_maskz_add_round_ps, __m256, __mmask8, __m256, __m256, 9)
+test_3 (_mm256_mask_cvt_roundepi32_ph, __m128h, __m128h, __mmask8, __m256i, 8)
+test_3 (_mm256_mask_cvt_roundepi32_ps, __m256, __m256, __mmask8, __m256i, 9)
+test_3 (_mm256_mask_cvt_roundpd_ph, __m128h, __m128h, __mmask8, __m256d, 8)
+test_3 (_mm256_mask_cvt_roundpd_ps, __m128, __m128, __mmask8, __m256d, 9)
test_3x (_mm256_mask_cmp_round_pd_mask, __mmask8, __mmask8, __m256d, __m256d, 1, 8)
test_3x (_mm256_mask_cmp_round_ph_mask, __mmask16, __mmask16, __m256h, __m256h, 1, 8)
test_3x (_mm256_mask_cmp_round_ps_mask, __mmask8, __mmask8, __m256, __m256, 1, 8)
@@ -831,6 +831,10 @@
#define __builtin_ia32_cmppd256_mask_round(A, B, C, D, E) __builtin_ia32_cmppd256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpph256_mask_round(A, B, C, D, E) __builtin_ia32_cmpph256_mask_round(A, B, 1, D, 8)
#define __builtin_ia32_cmpps256_mask_round(A, B, C, D, E) __builtin_ia32_cmpps256_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtdq2ps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, D) __builtin_ia32_vcvtpd2ph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, D) __builtin_ia32_cvtpd2ps256_mask_round(A, B, C, 8)
#pragma GCC target ("sse4a,3dnow,avx,avx2,fma4,xop,aes,pclmul,popcnt,abm,lzcnt,bmi,bmi2,tbm,lwp,fsgsbase,rdrnd,f16c,fma,rtm,rdseed,prfchw,adx,fxsr,xsaveopt,sha,xsavec,xsaves,clflushopt,clwb,mwaitx,clzero,pku,sgx,rdpid,gfni,vpclmulqdq,pconfig,wbnoinvd,enqcmd,avx512vp2intersect,serialize,tsxldtrk,amx-tile,amx-int8,amx-bf16,kl,widekl,avxvnni,avxifma,avxvnniint8,avxneconvert,cmpccxadd,amx-fp16,prefetchi,raoint,amx-complex,avxvnniint16,sm3,sha512,sm4,avx10.2-512")
From: "Hu, Lin1" <lin1.hu@intel.com> gcc/ChangeLog: * config/i386/avx10_2roundingintrin.h: Add new intrins. * config/i386/i386-builtin-types.def: Add new DEF_FUNCTION_TYPE. * config/i386/i386-builtin.def (BDESC): Add new builtins. * config/i386/i386-expand.cc (ix86_expand_round_builtin): Handle V8SF_FTYPE_V8SI_V8SF_UQI_INT, V4SF_FTYPE_V4DF_V4SF_UQI_INT, V8HF_FTYPE_V8SI_V8HF_UQI_INT, V8HF_FTYPE_V4DF_V8HF_UQI_INT. * config/i386/sse.md: (avx512fp16_vcvt<floatsuffix><sseintconvert>2ph_<mode><mask_name><round_name>): Add condition check. (avx512fp16_vcvtpd2ph_v4df_mask_round): New expand. (*avx512fp16_vcvt<castmode>2ph_<mode>_mask): Change name to avx512fp16_vcvt<castmode>2ph_<mode>_mask<round_name>_1 and extend pattern to generate 256bit insns. (avx_cvtpd2ps256<mask_name>): Change name to avx_cvtpd2ps256<mask_name><round_name> and extend pattern to generate 256bit insns. * config/i386/subst.md (round_applied): New condition. (round_suff): New iterator. (round_mode_condition): Add V32HI check for 512bit. (round_saeonly_mode_condition): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/avx-1.c: Add new builtin test. * gcc.target/i386/sse-13.c: Ditto. * gcc.target/i386/sse-23.c: Ditto. * gcc.target/i386/sse-14.c: Add new macro test. * gcc.target/i386/sse-22.c: Ditto. * gcc.target/i386/avx10_2-rounding-1.c: Add test. --- gcc/config/i386/avx10_2roundingintrin.h | 210 ++++++++++++++++++ gcc/config/i386/i386-builtin-types.def | 4 + gcc/config/i386/i386-builtin.def | 4 + gcc/config/i386/i386-expand.cc | 4 + gcc/config/i386/sse.md | 32 ++- gcc/config/i386/subst.md | 4 + gcc/testsuite/gcc.target/i386/avx-1.c | 4 + .../gcc.target/i386/avx10_2-rounding-1.c | 44 +++- gcc/testsuite/gcc.target/i386/sse-13.c | 4 + gcc/testsuite/gcc.target/i386/sse-14.c | 12 + gcc/testsuite/gcc.target/i386/sse-22.c | 12 + gcc/testsuite/gcc.target/i386/sse-23.c | 4 + 12 files changed, 322 insertions(+), 16 deletions(-)