From: "Hu, Lin1" <lin1...@intel.com>
gcc/ChangeLog:
* config/i386/avx10_2roundingintrin.h: New intrins.
* config/i386/i386-builtin.def (BDESC): Add new builtins.
gcc/testsuite/ChangeLog:
* gcc.target/i386/avx-1.c: Add new builtin test.
* gcc.target/i386/sse-13.c: Ditto.
* gcc.target/i386/sse-14.c: Ditto.
* gcc.target/i386/sse-22.c: Add new macro test.
* gcc.target/i386/sse-23.c: Ditto.
* gcc.target/i386/avx10_2-rounding-3.c: Add test.
---
gcc/config/i386/avx10_2roundingintrin.h | 339 ++++++++++++++++++
gcc/config/i386/i386-builtin.def | 6 +
gcc/testsuite/gcc.target/i386/avx-1.c | 6 +
.../gcc.target/i386/avx10_2-rounding-3.c | 50 +++
gcc/testsuite/gcc.target/i386/sse-13.c | 7 +
gcc/testsuite/gcc.target/i386/sse-14.c | 18 +
gcc/testsuite/gcc.target/i386/sse-22.c | 15 +
gcc/testsuite/gcc.target/i386/sse-23.c | 6 +
8 files changed, 447 insertions(+)
diff --git a/gcc/config/i386/avx10_2roundingintrin.h
b/gcc/config/i386/avx10_2roundingintrin.h
index f35f2337858..c7146e37ec9 100644
--- a/gcc/config/i386/avx10_2roundingintrin.h
+++ b/gcc/config/i386/avx10_2roundingintrin.h
@@ -3986,6 +3986,216 @@ _mm256_maskz_scalef_round_ps (__mmask8 __U, __m256 __A,
__m256 __B,
(__mmask8) __U,
__R);
}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sqrt_round_pd (__m256d __A, const int __R)
+{
+ return (__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) __A,
+ (__v4df)
+ _mm256_undefined_pd (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sqrt_round_pd (__m256d __W, __mmask8 __U, __m256d __A,
+ const int __R)
+{
+ return (__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) __A,
+ (__v4df) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sqrt_round_pd (__mmask8 __U, __m256d __A, const int __R)
+{
+ return (__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) __A,
+ (__v4df)
+ _mm256_setzero_pd (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sqrt_round_ph (__m256h __A, const int __R)
+{
+ return (__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) __A,
+ (__v16hf)
+ _mm256_undefined_ph (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sqrt_round_ph (__m256h __W, __mmask16 __U, __m256h __A,
+ const int __R)
+{
+ return (__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) __A,
+ (__v16hf) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sqrt_round_ph (__mmask16 __U, __m256h __A, const int __R)
+{
+ return (__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) __A,
+ (__v16hf)
+ _mm256_setzero_ph (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sqrt_round_ps (__m256 __A, const int __R)
+{
+ return (__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) __A,
+ (__v8sf)
+ _mm256_undefined_ps (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sqrt_round_ps (__m256 __W, __mmask8 __U, __m256 __A,
+ const int __R)
+{
+ return (__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) __A,
+ (__v8sf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sqrt_round_ps (__mmask8 __U, __m256 __A, const int __R)
+{
+ return (__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) __A,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sub_round_pd (__m256d __A, __m256d __B, const int __R)
+{
+ return (__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) __A,
+ (__v4df) __B,
+ (__v4df)
+ _mm256_undefined_pd (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sub_round_pd (__m256d __W, __mmask8 __U, __m256d __A,
+ __m256d __B, const int __R)
+{
+ return (__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) __A,
+ (__v4df) __B,
+ (__v4df) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256d
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sub_round_pd (__mmask8 __U, __m256d __A, __m256d __B,
+ const int __R)
+{
+ return (__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) __A,
+ (__v4df) __B,
+ (__v4df)
+ _mm256_setzero_pd (),
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sub_round_ph (__m256h __A, __m256h __B, const int __R)
+{
+ return (__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) __A,
+ (__v16hf) __B,
+ (__v16hf)
+ _mm256_undefined_ph (),
+ (__mmask16) -1,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sub_round_ph (__m256h __W, __mmask16 __U, __m256h __A,
+ __m256h __B, const int __R)
+{
+ return (__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) __A,
+ (__v16hf) __B,
+ (__v16hf) __W,
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sub_round_ph (__mmask16 __U, __m256h __A, __m256h __B,
+ const int __R)
+{
+ return (__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) __A,
+ (__v16hf) __B,
+ (__v16hf)
+ _mm256_setzero_ph (),
+ (__mmask16) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_sub_round_ps (__m256 __A, __m256 __B, const int __R)
+{
+ return (__m256) __builtin_ia32_subps256_mask_round ((__v8sf) __A,
+ (__v8sf) __B,
+ (__v8sf)
+ _mm256_undefined_ps (),
+ (__mmask8) -1,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_sub_round_ps (__m256 __W, __mmask8 __U, __m256 __A, __m256 __B,
+ const int __R)
+{
+ return (__m256) __builtin_ia32_subps256_mask_round ((__v8sf) __A,
+ (__v8sf) __B,
+ (__v8sf) __W,
+ (__mmask8) __U,
+ __R);
+}
+
+extern __inline __m256
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_sub_round_ps (__mmask8 __U, __m256 __A, __m256 __B,
+ const int __R)
+{
+ return (__m256) __builtin_ia32_subps256_mask_round ((__v8sf) __A,
+ (__v8sf) __B,
+ (__v8sf)
+ _mm256_setzero_ps (),
+ (__mmask8) __U,
+ __R);
+}
#else
#define _mm256_add_round_pd(A, B, R) \
((__m256d) __builtin_ia32_addpd256_mask_round ((__v4df) (A), \
@@ -6072,6 +6282,135 @@ _mm256_maskz_scalef_round_ps (__mmask8 __U, __m256 __A,
__m256 __B,
(_mm256_setzero_ps ()), \
(__mmask8) (U), \
(R)))
+
+#define _mm256_sqrt_round_pd(A, R) \
+ ((__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) (A), \
+ (__v4df) \
+ (_mm256_undefined_pd ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_sqrt_round_pd(W, U, A, R) \
+ ((__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) (A), \
+ (__v4df) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_sqrt_round_pd(U, A, R) \
+ ((__m256d) __builtin_ia32_sqrtpd256_mask_round ((__v4df) (A), \
+ (__v4df) \
+ (_mm256_setzero_pd ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_sqrt_round_ph(A, R) \
+ ((__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) (A), \
+ (__v16hf) \
+ (_mm256_undefined_ph ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_sqrt_round_ph(W, U, A, R) \
+ ((__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) (A), \
+ (__v16hf) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_sqrt_round_ph(U, A, R) \
+ ((__m256h) __builtin_ia32_sqrtph256_mask_round ((__v16hf) (A), \
+ (__v16hf) \
+ (_mm256_setzero_ph ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_sqrt_round_ps(A, R) \
+ ((__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) (A), \
+ (__v8sf) \
+ (_mm256_undefined_ps ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_sqrt_round_ps(W, U, A, R) \
+ ((__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) (A), \
+ (__v8sf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_sqrt_round_ps(U, A, R) \
+ ((__m256) __builtin_ia32_sqrtps256_mask_round ((__v8sf) (A), \
+ (__v8sf) \
+ (_mm256_setzero_ps ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_sub_round_pd(A, B, R) \
+ ((__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) (A), \
+ (__v4df) (B), \
+ (__v4df) \
+ (_mm256_undefined_pd ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_sub_round_pd(W, U, A, B, R) \
+ ((__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) (A), \
+ (__v4df) (B), \
+ (__v4df) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_sub_round_pd(U, A, B, R) \
+ ((__m256d) __builtin_ia32_subpd256_mask_round ((__v4df) (A), \
+ (__v4df) (B), \
+ (__v4df) \
+ (_mm256_setzero_pd ()), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_sub_round_ph(A, B, R) \
+ ((__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) (A), \
+ (__v16hf) (B), \
+ (__v16hf) \
+ (_mm256_undefined_ph ()), \
+ (__mmask16) (-1), \
+ (R)))
+
+#define _mm256_mask_sub_round_ph(W, U, A, B, R) \
+ ((__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) (A), \
+ (__v16hf) (B), \
+ (__v16hf) (W), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_maskz_sub_round_ph(U, A, B, R) \
+ ((__m256h) __builtin_ia32_subph256_mask_round ((__v16hf) (A), \
+ (__v16hf) (B), \
+ (__v16hf) \
+ (_mm256_setzero_ph ()), \
+ (__mmask16) (U), \
+ (R)))
+
+#define _mm256_sub_round_ps(A, B, R) \
+ ((__m256) __builtin_ia32_subps256_mask_round ((__v8sf) (A), \
+ (__v8sf) (B), \
+ (__v8sf) \
+ (_mm256_undefined_ps ()), \
+ (__mmask8) (-1), \
+ (R)))
+
+#define _mm256_mask_sub_round_ps(W, U, A, B, R) \
+ ((__m256) __builtin_ia32_subps256_mask_round ((__v8sf) (A), \
+ (__v8sf) (B), \
+ (__v8sf) (W), \
+ (__mmask8) (U), \
+ (R)))
+
+#define _mm256_maskz_sub_round_ps(U, A, B, R) \
+ ((__m256) __builtin_ia32_subps256_mask_round ((__v8sf) (A), \
+ (__v8sf) (B), \
+ (__v8sf) \
+ (_mm256_setzero_ps ()), \
+ (__mmask8) (U), \
+ (R)))
#endif
#define _mm256_cmul_round_pch(A, B, R) _mm256_fcmul_round_pch ((A), (B), (R))
diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index 8be3e117f76..416944f8b5b 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -3471,6 +3471,12 @@ BDESC (0, OPTION_MASK_ISA2_AVX10_2_256,
CODE_FOR_avx512vl_rndscalev8sf_mask_roun
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256,
CODE_FOR_avx512vl_scalefv4df_mask_round,
"__builtin_ia32_scalefpd256_mask_round", IX86_BUILTIN_VSCALEFPD256_MASK_ROUND,
UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF_V4DF_UQI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256,
CODE_FOR_avx512vl_scalefv16hf_mask_round,
"__builtin_ia32_scalefph256_mask_round", IX86_BUILTIN_VSCALEFPH256_MASK_ROUND,
UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX10_2_256,
CODE_FOR_avx512vl_scalefv8sf_mask_round,
"__builtin_ia32_scalefps256_mask_round", IX86_BUILTIN_VSCALEFPS256_MASK_ROUND,
UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF_V8SF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx_sqrtv4df2_mask_round,
"__builtin_ia32_sqrtpd256_mask_round", IX86_BUILTIN_VSQRTPD256_MASK_ROUND,
UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256,
CODE_FOR_avx512fp16_sqrtv16hf2_mask_round,
"__builtin_ia32_sqrtph256_mask_round", IX86_BUILTIN_VSQRTPH256_MASK_ROUND,
UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_avx_sqrtv8sf2_mask_round,
"__builtin_ia32_sqrtps256_mask_round", IX86_BUILTIN_VSQRTPS256_MASK_ROUND,
UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_subv4df3_mask_round,
"__builtin_ia32_subpd256_mask_round", IX86_BUILTIN_VSUBPD256_MASK_ROUND,
UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF_V4DF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_subv16hf3_mask_round,
"__builtin_ia32_subph256_mask_round", IX86_BUILTIN_VSUBPH256_MASK_ROUND,
UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX10_2_256, CODE_FOR_subv8sf3_mask_round,
"__builtin_ia32_subps256_mask_round", IX86_BUILTIN_VSUBPS256_MASK_ROUND,
UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF_V8SF_UQI_INT)
BDESC_END (ROUND_ARGS, MULTI_ARG)
diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c
b/gcc/testsuite/gcc.target/i386/avx-1.c
index e41a4ecdcd6..f64d0c88264 100644
--- a/gcc/testsuite/gcc.target/i386/avx-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx-1.c
@@ -995,6 +995,12 @@
#define __builtin_ia32_scalefpd256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefpd256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefph256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefph256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefps256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefps256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_sqrtpd256_mask_round(A, B, C, D)
__builtin_ia32_sqrtpd256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtph256_mask_round(A, B, C, D)
__builtin_ia32_sqrtph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtps256_mask_round(A, B, C, D)
__builtin_ia32_sqrtps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_subpd256_mask_round(A, B, C, D, E)
__builtin_ia32_subpd256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph256_mask_round(A, B, C, D, E)
__builtin_ia32_subph256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subps256_mask_round(A, B, C, D, E)
__builtin_ia32_subps256_mask_round(A, B, C, D, 8)
#include <wmmintrin.h>
#include <immintrin.h>
diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-rounding-3.c
b/gcc/testsuite/gcc.target/i386/avx10_2-rounding-3.c
index 331e79ce1fa..f065785d23e 100644
--- a/gcc/testsuite/gcc.target/i386/avx10_2-rounding-3.c
+++ b/gcc/testsuite/gcc.target/i386/avx10_2-rounding-3.c
@@ -183,6 +183,24 @@
/* { dg-final { scan-assembler-times "vscalefps\[
\\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
/* { dg-final { scan-assembler-times "vscalefps\[
\\t\]+\[^\n\]*\{ru-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1
} } */
/* { dg-final { scan-assembler-times "vscalefps\[
\\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtpd\[
\\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtpd\[
\\t\]+\[^\n\]*\{rd-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1
} } */
+/* { dg-final { scan-assembler-times "vsqrtpd\[
\\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtph\[
\\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtph\[
\\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtph\[
\\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtps\[
\\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsqrtps\[
\\t\]+\[^\n\]*\{ru-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1
} } */
+/* { dg-final { scan-assembler-times "vsqrtps\[
\\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubpd\[
\\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubpd\[
\\t\]+\[^\n\]*\{rd-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1
} } */
+/* { dg-final { scan-assembler-times "vsubpd\[
\\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubph\[
\\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubph\[
\\t\]+\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubph\[
\\t\]+\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[
\\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubps\[
\\t\]+\[^\n\]*\{rn-sae\}\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vsubps\[
\\t\]+\[^\n\]*\{ru-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1
} } */
+/* { dg-final { scan-assembler-times "vsubps\[
\\t\]+\[^\n\]*\{rz-sae\}\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[
\\t\]+#)" 1 } } */
#include <immintrin.h>
@@ -549,3 +567,35 @@ avx10_2_test_24 (void)
x = _mm256_mask_scalef_round_ps (x, m8, x, x, _MM_FROUND_TO_POS_INF |
_MM_FROUND_NO_EXC);
x = _mm256_maskz_scalef_round_ps (m8, x, x, _MM_FROUND_TO_ZERO |
_MM_FROUND_NO_EXC);
}
+
+void extern
+avx10_2_test_25 (void)
+{
+ xd = _mm256_sqrt_round_pd (xd, _MM_FROUND_TO_NEAREST_INT |
_MM_FROUND_NO_EXC);
+ xd = _mm256_mask_sqrt_round_pd (xd, m8, xd, _MM_FROUND_TO_NEG_INF |
_MM_FROUND_NO_EXC);
+ xd = _mm256_maskz_sqrt_round_pd (m8, xd, _MM_FROUND_TO_ZERO |
_MM_FROUND_NO_EXC);
+
+ xh = _mm256_sqrt_round_ph (xh, 4);
+ xh = _mm256_mask_sqrt_round_ph (xh, m16, xh, 8);
+ xh = _mm256_maskz_sqrt_round_ph (m16, xh, 11);
+
+ x = _mm256_sqrt_round_ps (x, _MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC);
+ x = _mm256_mask_sqrt_round_ps (x, m8, x, _MM_FROUND_TO_POS_INF |
_MM_FROUND_NO_EXC);
+ x = _mm256_maskz_sqrt_round_ps (m8, x, _MM_FROUND_TO_ZERO |
_MM_FROUND_NO_EXC);
+}
+
+void extern
+avx10_2_test_26 (void)
+{
+ xd = _mm256_sub_round_pd (xd, xd, _MM_FROUND_TO_NEAREST_INT |
_MM_FROUND_NO_EXC);
+ xd = _mm256_mask_sub_round_pd (xd, m8, xd, xd, _MM_FROUND_TO_NEG_INF |
_MM_FROUND_NO_EXC);
+ xd = _mm256_maskz_sub_round_pd (m8, xd, xd, _MM_FROUND_TO_ZERO |
_MM_FROUND_NO_EXC);
+
+ xh = _mm256_sub_round_ph (xh, xh, 8);
+ xh = _mm256_mask_sub_round_ph (xh, m16, xh, xh, 8);
+ xh = _mm256_maskz_sub_round_ph (m16, xh, xh, 11);
+
+ x = _mm256_sub_round_ps (x, x, _MM_FROUND_TO_NEAREST_INT |
_MM_FROUND_NO_EXC);
+ x = _mm256_mask_sub_round_ps (x, m8, x, x, _MM_FROUND_TO_POS_INF |
_MM_FROUND_NO_EXC);
+ x = _mm256_maskz_sub_round_ps (m8, x, x, _MM_FROUND_TO_ZERO |
_MM_FROUND_NO_EXC);
+}
diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c
b/gcc/testsuite/gcc.target/i386/sse-13.c
index a393e28c54e..a5b1775ed2d 100644
--- a/gcc/testsuite/gcc.target/i386/sse-13.c
+++ b/gcc/testsuite/gcc.target/i386/sse-13.c
@@ -1002,5 +1002,12 @@
#define __builtin_ia32_scalefpd256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefpd256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefph256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefph256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefps256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefps256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_sqrtps256_mask_round(A, B, C, D)
__builtin_ia32_sqrtps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtpd256_mask_round(A, B, C, D)
__builtin_ia32_sqrtpd256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtph256_mask_round(A, B, C, D)
__builtin_ia32_sqrtph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtps256_mask_round(A, B, C, D)
__builtin_ia32_sqrtps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_subpd256_mask_round(A, B, C, D, E)
__builtin_ia32_subpd256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph256_mask_round(A, B, C, D, E)
__builtin_ia32_subph256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subps256_mask_round(A, B, C, D, E)
__builtin_ia32_subps256_mask_round(A, B, C, D, 8)
#include <x86intrin.h>
diff --git a/gcc/testsuite/gcc.target/i386/sse-14.c
b/gcc/testsuite/gcc.target/i386/sse-14.c
index ddec892824c..4736b2a5d52 100644
--- a/gcc/testsuite/gcc.target/i386/sse-14.c
+++ b/gcc/testsuite/gcc.target/i386/sse-14.c
@@ -1069,6 +1069,9 @@ test_1 (_mm256_cvt_roundepi16_ph, __m256h, __m256i, 8)
test_1 (_mm256_getexp_round_pd, __m256d, __m256d, 8)
test_1 (_mm256_getexp_round_ph, __m256h, __m256h, 8)
test_1 (_mm256_getexp_round_ps, __m256, __m256, 8)
+test_1 (_mm256_sqrt_round_pd, __m256d, __m256d, 9)
+test_1 (_mm256_sqrt_round_ph, __m256h, __m256h, 9)
+test_1 (_mm256_sqrt_round_ps, __m256, __m256, 9)
test_1x (_mm256_reduce_round_ph, __m256h, __m256h, 123, 8)
test_1x (_mm256_reduce_round_ps, __m256, __m256, 123, 8)
test_1x (_mm256_reduce_round_pd, __m256d, __m256d, 123, 8)
@@ -1147,6 +1150,12 @@ test_2 (_mm256_mul_round_ps, __m256, __m256, __m256, 9)
test_2 (_mm256_scalef_round_pd, __m256d, __m256d, __m256d, 9)
test_2 (_mm256_scalef_round_ph, __m256h, __m256h, __m256h, 9)
test_2 (_mm256_scalef_round_ps, __m256, __m256, __m256, 9)
+test_2 (_mm256_maskz_sqrt_round_pd, __m256d, __mmask8, __m256d, 9)
+test_2 (_mm256_maskz_sqrt_round_ph, __m256h, __mmask16, __m256h, 9)
+test_2 (_mm256_maskz_sqrt_round_ps, __m256, __mmask8, __m256, 9)
+test_2 (_mm256_sub_round_pd, __m256d, __m256d, __m256d, 9)
+test_2 (_mm256_sub_round_ph, __m256h, __m256h, __m256h, 9)
+test_2 (_mm256_sub_round_ps, __m256, __m256, __m256, 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)
@@ -1251,6 +1260,12 @@ test_3 (_mm256_maskz_mul_round_ps, __m256, __mmask8,
__m256, __m256, 9)
test_3 (_mm256_maskz_scalef_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
test_3 (_mm256_maskz_scalef_round_ph, __m256h, __mmask16, __m256h, __m256h, 9)
test_3 (_mm256_maskz_scalef_round_ps, __m256, __mmask8, __m256, __m256, 9)
+test_3 (_mm256_mask_sqrt_round_pd, __m256d, __m256d, __mmask8, __m256d, 9)
+test_3 (_mm256_mask_sqrt_round_ph, __m256h, __m256h, __mmask16, __m256h, 9)
+test_3 (_mm256_mask_sqrt_round_ps, __m256, __m256, __mmask8, __m256, 9)
+test_3 (_mm256_maskz_sub_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
+test_3 (_mm256_maskz_sub_round_ph, __m256h, __mmask16, __m256h, __m256h, 9)
+test_3 (_mm256_maskz_sub_round_ps, __m256, __mmask8, __m256, __m256, 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)
@@ -1347,6 +1362,9 @@ test_4 (_mm256_mask_mul_round_ps, __m256, __m256,
__mmask8, __m256, __m256, 9)
test_4 (_mm256_mask_scalef_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256d, 9)
test_4 (_mm256_mask_scalef_round_ph, __m256h, __m256h, __mmask16, __m256h,
__m256h, 9)
test_4 (_mm256_mask_scalef_round_ps, __m256, __m256, __mmask8, __m256, __m256,
9)
+test_4 (_mm256_mask_sub_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256d, 9)
+test_4 (_mm256_mask_sub_round_ph, __m256h, __m256h, __mmask16, __m256h,
__m256h, 9)
+test_4 (_mm256_mask_sub_round_ps, __m256, __m256, __mmask8, __m256, __m256, 9)
test_4x (_mm256_maskz_fixupimm_round_pd, __m256d, __mmask8, __m256d, __m256d,
__m256i, 3, 8)
test_4x (_mm256_maskz_fixupimm_round_ps, __m256, __mmask8, __m256, __m256,
__m256i, 3, 8)
test_4x (_mm256_mask_fixupimm_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256i, 3, 8)
diff --git a/gcc/testsuite/gcc.target/i386/sse-22.c
b/gcc/testsuite/gcc.target/i386/sse-22.c
index b5d964552bc..5bfccd52630 100644
--- a/gcc/testsuite/gcc.target/i386/sse-22.c
+++ b/gcc/testsuite/gcc.target/i386/sse-22.c
@@ -1112,6 +1112,9 @@ test_1 (_mm256_cvt_roundepi16_ph, __m256h, __m256i, 8)
test_1 (_mm256_getexp_round_pd, __m256d, __m256d, 8)
test_1 (_mm256_getexp_round_ph, __m256h, __m256h, 8)
test_1 (_mm256_getexp_round_ps, __m256, __m256, 8)
+test_1 (_mm256_sqrt_round_pd, __m256d, __m256d, 9)
+test_1 (_mm256_sqrt_round_ph, __m256h, __m256h, 9)
+test_1 (_mm256_sqrt_round_ps, __m256, __m256, 9)
test_1x (_mm256_reduce_round_ph, __m256h, __m256h, 123, 8)
test_1x (_mm256_reduce_round_ps, __m256, __m256, 123, 8)
test_1x (_mm256_reduce_round_pd, __m256d, __m256d, 123, 8)
@@ -1190,6 +1193,12 @@ test_2 (_mm256_mul_round_ps, __m256, __m256, __m256, 9)
test_2 (_mm256_scalef_round_pd, __m256d, __m256d, __m256d, 9)
test_2 (_mm256_scalef_round_ph, __m256h, __m256h, __m256h, 9)
test_2 (_mm256_scalef_round_ps, __m256, __m256, __m256, 9)
+test_2 (_mm256_maskz_sqrt_round_pd, __m256d, __mmask8, __m256d, 9)
+test_2 (_mm256_maskz_sqrt_round_ph, __m256h, __mmask16, __m256h, 9)
+test_2 (_mm256_maskz_sqrt_round_ps, __m256, __mmask8, __m256, 9)
+test_2 (_mm256_sub_round_pd, __m256d, __m256d, __m256d, 9)
+test_2 (_mm256_sub_round_ph, __m256h, __m256h, __m256h, 9)
+test_2 (_mm256_sub_round_ps, __m256, __m256, __m256, 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)
@@ -1293,6 +1302,9 @@ test_3 (_mm256_maskz_mul_round_ps, __m256, __mmask8,
__m256, __m256, 9)
test_3 (_mm256_maskz_scalef_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
test_3 (_mm256_maskz_scalef_round_ph, __m256h, __mmask16, __m256h, __m256h, 9)
test_3 (_mm256_maskz_scalef_round_ps, __m256, __mmask8, __m256, __m256, 9)
+test_3 (_mm256_maskz_sub_round_pd, __m256d, __mmask8, __m256d, __m256d, 9)
+test_3 (_mm256_maskz_sub_round_ph, __m256h, __mmask16, __m256h, __m256h, 9)
+test_3 (_mm256_maskz_sub_round_ps, __m256, __mmask8, __m256, __m256, 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)
@@ -1389,6 +1401,9 @@ test_4 (_mm256_mask_mul_round_ps, __m256, __m256,
__mmask8, __m256, __m256, 9)
test_4 (_mm256_mask_scalef_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256d, 9)
test_4 (_mm256_mask_scalef_round_ph, __m256h, __m256h, __mmask16, __m256h,
__m256h, 9)
test_4 (_mm256_mask_scalef_round_ps, __m256, __m256, __mmask8, __m256, __m256,
9)
+test_4 (_mm256_mask_sub_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256d, 9)
+test_4 (_mm256_mask_sub_round_ph, __m256h, __m256h, __mmask16, __m256h,
__m256h, 9)
+test_4 (_mm256_mask_sub_round_ps, __m256, __m256, __mmask8, __m256, __m256, 9)
test_4x (_mm256_maskz_fixupimm_round_pd, __m256d, __mmask8, __m256d, __m256d,
__m256i, 3, 8)
test_4x (_mm256_maskz_fixupimm_round_ps, __m256, __mmask8, __m256, __m256,
__m256i, 3, 8)
test_4x (_mm256_mask_fixupimm_round_pd, __m256d, __m256d, __mmask8, __m256d,
__m256i, 3, 8)
diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c
b/gcc/testsuite/gcc.target/i386/sse-23.c
index bd9f93db8cd..e63c100f452 100644
--- a/gcc/testsuite/gcc.target/i386/sse-23.c
+++ b/gcc/testsuite/gcc.target/i386/sse-23.c
@@ -977,6 +977,12 @@
#define __builtin_ia32_scalefpd256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefpd256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefph256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefph256_mask_round(A, B, C, D, 8)
#define __builtin_ia32_scalefps256_mask_round(A, B, C, D, E)
__builtin_ia32_scalefps256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_sqrtpd256_mask_round(A, B, C, D)
__builtin_ia32_sqrtpd256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtph256_mask_round(A, B, C, D)
__builtin_ia32_sqrtph256_mask_round(A, B, C, 8)
+#define __builtin_ia32_sqrtps256_mask_round(A, B, C, D)
__builtin_ia32_sqrtps256_mask_round(A, B, C, 8)
+#define __builtin_ia32_subpd256_mask_round(A, B, C, D, E)
__builtin_ia32_subpd256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph256_mask_round(A, B, C, D, E)
__builtin_ia32_subph256_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subps256_mask_round(A, B, C, D, E)
__builtin_ia32_subps256_mask_round(A, B, C, D, 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")
--
2.31.1
