re PR target/85281 (Assembler messages: Error: operand size mismatch for `vpbroadcastb' with -mavx512bw -masm=intel)

	PR target/85281
	* config/i386/sse.md (reduces<mode><mask_scalar_name>,
	avx512f_vmcmp<mode>3<round_saeonly_name>,
	avx512f_vmcmp<mode>3_mask<round_saeonly_name>,
	avx512f_sgetexp<mode><mask_scalar_name><round_saeonly_scalar_name>,
	avx512f_rndscale<mode><round_saeonly_name>,
	avx512dq_ranges<mode><mask_scalar_name><round_saeonly_scalar_name>,
	avx512f_vgetmant<mode><mask_scalar_name><round_saeonly_scalar_name>):
	Use %<iptr>2 instead of %2 for -masm=intel.
	(avx512f_vcvtss2usi<round_name>, avx512f_vcvtss2usiq<round_name>,
	avx512f_vcvttss2usi<round_saeonly_name>,
	avx512f_vcvttss2usiq<round_saeonly_name>): Use %k1 instead of %1 for
	-masm=intel.
	(avx512f_vcvtsd2usi<round_name>, avx512f_vcvtsd2usiq<round_name>,
	avx512f_vcvttsd2usi<round_saeonly_name>,
	avx512f_vcvttsd2usiq<round_saeonly_name>, ufloatv2siv2df2<mask_name>):
	Use %q1 instead of %1 for -masm=intel.
	(avx512f_sfixupimm<mode><sd_maskz_name><round_saeonly_name>,
	avx512f_sfixupimm<mode>_mask<round_saeonly_name>): Use %<iptr>3 instead
	of %3 for -masm=intel.
	(sse2_shufpd_v2df_mask): Fix a typo, change %{6%} to %{%6%} for
	-masm=intel.
	(*avx512vl_<code>v2div2qi2_store): Use %w0 instead of %0 for
	-masm=intel.
	(*avx512vl_<code><mode>v4qi2_store): Use %k0 instead of %0 for
	-masm=intel.
	(avx512vl_<code><mode>v4qi2_mask_store): Use a single pattern with
	%k0 and %1 for -masm=intel rather than two patterns, one with %0 and
	%g1.
	(*avx512vl_<code><mode>v8qi2_store): Use %q0 instead of %0 for
	-masm=intel.
	(avx512vl_<code><mode>v8qi2_mask_store): Use a single pattern with
	%q0 and %1 for -masm=intel rather than two patterns, one with %0 and
	%g1 and one with %0 and %1.
	(avx512er_vmrcp28<mode><round_saeonly_name>,
	avx512er_vmrsqrt28<mode><round_saeonly_name>): Use %<iptr>1 instead of
	%1 for -masm=intel.
	(avx5124fmaddps_4fmaddps_mask, avx5124fmaddps_4fmaddss_mask,
	avx5124fmaddps_4fnmaddps_mask, avx5124fmaddps_4fnmaddss_mask,
	avx5124vnniw_vp4dpwssd_mask, avx5124vnniw_vp4dpwssds_mask): Swap order
	of %0 and %{%4%} for -masm=intel.
	(avx5124fmaddps_4fmaddps_maskz, avx5124fmaddps_4fmaddss_maskz,
	avx5124fmaddps_4fnmaddps_maskz, avx5124fmaddps_4fnmaddss_maskz,
	avx5124vnniw_vp4dpwssd_maskz, avx5124vnniw_vp4dpwssds_maskz): Swap
	order of %0 and %{%5%}%{z%} for -masm=intel.

From-SVN: r259430

2 files changed, 86 insertions, 46 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4ba0f0f..a086530 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,51 @@
+2018-04-17  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/85281
+	* config/i386/sse.md (reduces<mode><mask_scalar_name>,
+	avx512f_vmcmp<mode>3<round_saeonly_name>,
+	avx512f_vmcmp<mode>3_mask<round_saeonly_name>,
+	avx512f_sgetexp<mode><mask_scalar_name><round_saeonly_scalar_name>,
+	avx512f_rndscale<mode><round_saeonly_name>,
+	avx512dq_ranges<mode><mask_scalar_name><round_saeonly_scalar_name>,
+	avx512f_vgetmant<mode><mask_scalar_name><round_saeonly_scalar_name>):
+	Use %<iptr>2 instead of %2 for -masm=intel.
+	(avx512f_vcvtss2usi<round_name>, avx512f_vcvtss2usiq<round_name>,
+	avx512f_vcvttss2usi<round_saeonly_name>,
+	avx512f_vcvttss2usiq<round_saeonly_name>): Use %k1 instead of %1 for
+	-masm=intel.
+	(avx512f_vcvtsd2usi<round_name>, avx512f_vcvtsd2usiq<round_name>,
+	avx512f_vcvttsd2usi<round_saeonly_name>,
+	avx512f_vcvttsd2usiq<round_saeonly_name>, ufloatv2siv2df2<mask_name>):
+	Use %q1 instead of %1 for -masm=intel.
+	(avx512f_sfixupimm<mode><sd_maskz_name><round_saeonly_name>,
+	avx512f_sfixupimm<mode>_mask<round_saeonly_name>): Use %<iptr>3 instead
+	of %3 for -masm=intel.
+	(sse2_shufpd_v2df_mask): Fix a typo, change %{6%} to %{%6%} for
+	-masm=intel.
+	(*avx512vl_<code>v2div2qi2_store): Use %w0 instead of %0 for
+	-masm=intel.
+	(*avx512vl_<code><mode>v4qi2_store): Use %k0 instead of %0 for
+	-masm=intel.
+	(avx512vl_<code><mode>v4qi2_mask_store): Use a single pattern with
+	%k0 and %1 for -masm=intel rather than two patterns, one with %0 and
+	%g1.
+	(*avx512vl_<code><mode>v8qi2_store): Use %q0 instead of %0 for
+	-masm=intel.
+	(avx512vl_<code><mode>v8qi2_mask_store): Use a single pattern with
+	%q0 and %1 for -masm=intel rather than two patterns, one with %0 and
+	%g1 and one with %0 and %1.
+	(avx512er_vmrcp28<mode><round_saeonly_name>,
+	avx512er_vmrsqrt28<mode><round_saeonly_name>): Use %<iptr>1 instead of
+	%1 for -masm=intel.
+	(avx5124fmaddps_4fmaddps_mask, avx5124fmaddps_4fmaddss_mask,
+	avx5124fmaddps_4fnmaddps_mask, avx5124fmaddps_4fnmaddss_mask,
+	avx5124vnniw_vp4dpwssd_mask, avx5124vnniw_vp4dpwssds_mask): Swap order
+	of %0 and %{%4%} for -masm=intel.
+	(avx5124fmaddps_4fmaddps_maskz, avx5124fmaddps_4fmaddss_maskz,
+	avx5124fmaddps_4fnmaddps_maskz, avx5124fmaddps_4fnmaddss_maskz,
+	avx5124vnniw_vp4dpwssd_maskz, avx5124vnniw_vp4dpwssds_maskz): Swap
+	order of %0 and %{%5%}%{z%} for -masm=intel.
+
 2018-04-17  Jan Hubicka  <jh@suse.cz>
 
 	PR lto/85405
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index c3345d0..8b5f4c6 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2628,7 +2628,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_AVX512DQ"
-  "vreduce<ssescalarmodesuffix>\t{%3, %2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %2, %3}"
+  "vreduce<ssescalarmodesuffix>\t{%3, %2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %<iptr>2, %3}"
   [(set_attr "type" "sse")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<MODE>")])
@@ -2796,7 +2796,7 @@
 	    UNSPEC_PCMP)
 	  (const_int 1)))]
   "TARGET_AVX512F"
-  "vcmp<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %2<round_saeonly_op4>, %3}"
+  "vcmp<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %<iptr>2<round_saeonly_op4>, %3}"
   [(set_attr "type" "ssecmp")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
@@ -2814,7 +2814,7 @@
 	    (match_operand:<avx512fmaskmode> 4 "register_operand" "Yk")
 	    (const_int 1))))]
   "TARGET_AVX512F"
-  "vcmp<ssescalarmodesuffix>\t{%3, <round_saeonly_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_saeonly_op5>, %3}"
+  "vcmp<ssescalarmodesuffix>\t{%3, <round_saeonly_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %<iptr>2<round_saeonly_op5>, %3}"
   [(set_attr "type" "ssecmp")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
@@ -4805,7 +4805,7 @@
 	     (parallel [(const_int 0)]))]
 	  UNSPEC_UNSIGNED_FIX_NOTRUNC))]
   "TARGET_AVX512F"
-  "vcvtss2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
+  "vcvtss2usi\t{<round_op2>%1, %0|%0, %k1<round_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "SI")])
@@ -4818,7 +4818,7 @@
 	     (parallel [(const_int 0)]))]
 	  UNSPEC_UNSIGNED_FIX_NOTRUNC))]
   "TARGET_AVX512F && TARGET_64BIT"
-  "vcvtss2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
+  "vcvtss2usi\t{<round_op2>%1, %0|%0, %k1<round_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "DI")])
@@ -4830,7 +4830,7 @@
 	    (match_operand:V4SF 1 "<round_saeonly_nimm_scalar_predicate>" "<round_saeonly_constraint>")
 	    (parallel [(const_int 0)]))))]
   "TARGET_AVX512F"
-  "vcvttss2usi\t{<round_saeonly_op2>%1, %0|%0, %1<round_saeonly_op2>}"
+  "vcvttss2usi\t{<round_saeonly_op2>%1, %0|%0, %k1<round_saeonly_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "SI")])
@@ -4842,7 +4842,7 @@
 	    (match_operand:V4SF 1 "<round_saeonly_nimm_scalar_predicate>" "<round_saeonly_constraint>")
 	    (parallel [(const_int 0)]))))]
   "TARGET_AVX512F && TARGET_64BIT"
-  "vcvttss2usi\t{<round_saeonly_op2>%1, %0|%0, %1<round_saeonly_op2>}"
+  "vcvttss2usi\t{<round_saeonly_op2>%1, %0|%0, %k1<round_saeonly_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "DI")])
@@ -4855,7 +4855,7 @@
 	     (parallel [(const_int 0)]))]
 	  UNSPEC_UNSIGNED_FIX_NOTRUNC))]
   "TARGET_AVX512F"
-  "vcvtsd2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
+  "vcvtsd2usi\t{<round_op2>%1, %0|%0, %q1<round_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "SI")])
@@ -4868,7 +4868,7 @@
 	     (parallel [(const_int 0)]))]
 	  UNSPEC_UNSIGNED_FIX_NOTRUNC))]
   "TARGET_AVX512F && TARGET_64BIT"
-  "vcvtsd2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
+  "vcvtsd2usi\t{<round_op2>%1, %0|%0, %q1<round_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "DI")])
@@ -4880,7 +4880,7 @@
 	    (match_operand:V2DF 1 "<round_saeonly_nimm_scalar_predicate>" "<round_saeonly_constraint>")
 	    (parallel [(const_int 0)]))))]
   "TARGET_AVX512F"
-  "vcvttsd2usi\t{<round_saeonly_op2>%1, %0|%0, %1<round_saeonly_op2>}"
+  "vcvttsd2usi\t{<round_saeonly_op2>%1, %0|%0, %q1<round_saeonly_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "SI")])
@@ -4892,7 +4892,7 @@
 	    (match_operand:V2DF 1 "<round_saeonly_nimm_scalar_predicate>" "<round_saeonly_constraint>")
 	    (parallel [(const_int 0)]))))]
   "TARGET_AVX512F && TARGET_64BIT"
-  "vcvttsd2usi\t{<round_saeonly_op2>%1, %0|%0, %1<round_saeonly_op2>}"
+  "vcvttsd2usi\t{<round_saeonly_op2>%1, %0|%0, %q1<round_saeonly_op2>}"
   [(set_attr "type" "sseicvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "DI")])
@@ -5099,7 +5099,7 @@
 	    (match_operand:V4SI 1 "nonimmediate_operand" "vm")
 	    (parallel [(const_int 0) (const_int 1)]))))]
   "TARGET_AVX512VL"
-  "vcvtudq2pd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+  "vcvtudq2pd\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
   [(set_attr "type" "ssecvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "V2DF")])
@@ -8504,7 +8504,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
    "TARGET_AVX512F"
-   "vgetexp<ssescalarmodesuffix>\t{<round_saeonly_scalar_mask_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %2<round_saeonly_scalar_mask_op3>}";
+   "vgetexp<ssescalarmodesuffix>\t{<round_saeonly_scalar_mask_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %<iptr>2<round_saeonly_scalar_mask_op3>}";
     [(set_attr "prefix" "evex")
      (set_attr "mode" "<ssescalarmode>")])
 
@@ -8624,7 +8624,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
    "TARGET_AVX512F"
-   "vfixupimm<ssescalarmodesuffix>\t{%4, <round_saeonly_sd_mask_op5>%3, %2, %0<sd_mask_op5>|%0<sd_mask_op5>, %2, %3<round_saeonly_sd_mask_op5>, %4}";
+   "vfixupimm<ssescalarmodesuffix>\t{%4, <round_saeonly_sd_mask_op5>%3, %2, %0<sd_mask_op5>|%0<sd_mask_op5>, %2, %<iptr>3<round_saeonly_sd_mask_op5>, %4}";
    [(set_attr "prefix" "evex")
    (set_attr "mode" "<ssescalarmode>")])
 
@@ -8643,7 +8643,7 @@
 	  (match_dup 1)
 	  (match_operand:<avx512fmaskmode> 5 "register_operand" "Yk")))]
   "TARGET_AVX512F"
-  "vfixupimm<ssescalarmodesuffix>\t{%4, <round_saeonly_op6>%3, %2, %0%{%5%}|%0%{%5%}, %2, %3<round_saeonly_op6>, %4}";
+  "vfixupimm<ssescalarmodesuffix>\t{%4, <round_saeonly_op6>%3, %2, %0%{%5%}|%0%{%5%}, %2, %<iptr>3<round_saeonly_op6>, %4}";
   [(set_attr "prefix" "evex")
    (set_attr "mode" "<ssescalarmode>")])
 
@@ -8670,7 +8670,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_AVX512F"
-  "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %2<round_saeonly_op4>, %3}"
+  "vrndscale<ssescalarmodesuffix>\t{%3, <round_saeonly_op4>%2, %1, %0|%0, %1, %<iptr>2<round_saeonly_op4>, %3}"
   [(set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<MODE>")])
@@ -8861,7 +8861,7 @@
   mask |= (INTVAL (operands[4]) - 2) << 1;
   operands[3] = GEN_INT (mask);
 
-  return "vshufpd\t{%3, %2, %1, %0%{%6%}%N5|%0%{6%}%N5, %1, %2, %3}";
+  return "vshufpd\t{%3, %2, %1, %0%{%6%}%N5|%0%{%6%}%N5, %1, %2, %3}";
 }
   [(set_attr "type" "sseshuf")
    (set_attr "length_immediate" "1")
@@ -9514,7 +9514,7 @@
                    (const_int 12) (const_int 13)
                    (const_int 14) (const_int 15)]))))]
   "TARGET_AVX512VL"
-  "vpmov<trunsuffix>qb\t{%1, %0|%0, %1}"
+  "vpmov<trunsuffix>qb\t{%1, %0|%w0, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "memory" "store")
    (set_attr "prefix" "evex")
@@ -9604,7 +9604,7 @@
                    (const_int 12) (const_int 13)
                    (const_int 14) (const_int 15)]))))]
   "TARGET_AVX512VL"
-  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0|%0, %1}"
+  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0|%k0, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "memory" "store")
    (set_attr "prefix" "evex")
@@ -9674,11 +9674,7 @@
                    (const_int 12) (const_int 13)
                    (const_int 14) (const_int 15)]))))]
   "TARGET_AVX512VL"
-{
-  if (GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) == 8)
-    return "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%k0%{%2%}, %1}";
-  return "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%0%{%2%}, %g1}";
-}
+  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%k0%{%2%}, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "memory" "store")
    (set_attr "prefix" "evex")
@@ -9699,7 +9695,7 @@
                    (const_int 12) (const_int 13)
                    (const_int 14) (const_int 15)]))))]
   "TARGET_AVX512VL"
-  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0|%0, %1}"
+  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0|%q0, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "memory" "store")
    (set_attr "prefix" "evex")
@@ -9769,11 +9765,7 @@
                    (const_int 12) (const_int 13)
                    (const_int 14) (const_int 15)]))))]
   "TARGET_AVX512VL"
-{
-  if (GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) == 4)
-    return "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%0%{%2%}, %g1}";
-  return "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%0%{%2%}, %1}";
-}
+  "vpmov<trunsuffix><pmov_suff_3>\t{%1, %0%{%2%}|%q0%{%2%}, %1}"
   [(set_attr "type" "ssemov")
    (set_attr "memory" "store")
    (set_attr "prefix" "evex")
@@ -16426,7 +16418,7 @@
 	  (match_operand:VF_128 2 "register_operand" "v")
 	  (const_int 1)))]
   "TARGET_AVX512ER"
-  "vrcp28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %1<round_saeonly_op3>}"
+  "vrcp28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %<iptr>1<round_saeonly_op3>}"
   [(set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
    (set_attr "type" "sse")
@@ -16452,7 +16444,7 @@
 	  (match_operand:VF_128 2 "register_operand" "v")
 	  (const_int 1)))]
   "TARGET_AVX512ER"
-  "vrsqrt28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %1<round_saeonly_op3>}"
+  "vrsqrt28<ssescalarmodesuffix>\t{<round_saeonly_op3>%1, %2, %0|%0, %2, %<iptr>1<round_saeonly_op3>}"
   [(set_attr "length_immediate" "1")
    (set_attr "type" "sse")
    (set_attr "prefix" "evex")
@@ -19595,7 +19587,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
   "TARGET_AVX512DQ"
-  "vrange<ssescalarmodesuffix>\t{%3, <round_saeonly_scalar_mask_op4>%2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %2<round_saeonly_scalar_mask_op4>, %3}"
+  "vrange<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 "type" "sse")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<MODE>")])
@@ -19650,7 +19642,7 @@
 	  (match_dup 1)
 	  (const_int 1)))]
    "TARGET_AVX512F"
-   "vgetmant<ssescalarmodesuffix>\t{%3, <round_saeonly_scalar_mask_op4>%2, %1, %0<mask_scalar_operand4>|%0<mask_scalar_operand4>, %1, %2<round_saeonly_scalar_mask_op4>, %3}";
+   "vgetmant<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 "prefix" "evex")
    (set_attr "mode" "<ssescalarmode>")])
 
@@ -19942,7 +19934,7 @@
 	  (match_operand:V16SF 3 "register_operand" "0")
 	  (match_operand:HI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fmaddps\t{%2, %g1, %0%{%4%}|%{%4%}%0, %g1, %2}"
+  "v4fmaddps\t{%2, %g1, %0%{%4%}|%0%{%4%}, %g1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("V16SF"))])
@@ -19957,7 +19949,7 @@
 	  (match_operand:V16SF 4 "const0_operand" "C")
 	  (match_operand:HI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fmaddps\t{%3, %g2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %g2, %3}"
+  "v4fmaddps\t{%3, %g2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %g2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("V16SF"))])
@@ -19983,7 +19975,7 @@
 	  (match_operand:V4SF 3 "register_operand" "0")
 	  (match_operand:QI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fmaddss\t{%2, %x1, %0%{%4%}|%{%4%}%0, %x1, %2}"
+  "v4fmaddss\t{%2, %x1, %0%{%4%}|%0%{%4%}, %x1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("SF"))])
@@ -19998,7 +19990,7 @@
 	  (match_operand:V4SF 4 "const0_operand" "C")
 	  (match_operand:QI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fmaddss\t{%3, %x2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %x2, %3}"
+  "v4fmaddss\t{%3, %x2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %x2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("SF"))])
@@ -20024,7 +20016,7 @@
 	  (match_operand:V16SF 3 "register_operand" "0")
 	  (match_operand:HI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fnmaddps\t{%2, %g1, %0%{%4%}|%{%4%}%0, %g1, %2}"
+  "v4fnmaddps\t{%2, %g1, %0%{%4%}|%0%{%4%}, %g1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("V16SF"))])
@@ -20039,7 +20031,7 @@
 	  (match_operand:V16SF 4 "const0_operand" "C")
 	  (match_operand:HI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fnmaddps\t{%3, %g2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %g2, %3}"
+  "v4fnmaddps\t{%3, %g2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %g2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("V16SF"))])
@@ -20065,7 +20057,7 @@
 	  (match_operand:V4SF 3 "register_operand" "0")
 	  (match_operand:QI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fnmaddss\t{%2, %x1, %0%{%4%}|%{%4%}%0, %x1, %2}"
+  "v4fnmaddss\t{%2, %x1, %0%{%4%}|%0%{%4%}, %x1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("SF"))])
@@ -20080,7 +20072,7 @@
 	  (match_operand:V4SF 4 "const0_operand" "C")
 	  (match_operand:QI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124FMAPS"
-  "v4fnmaddss\t{%3, %x2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %x2, %3}"
+  "v4fnmaddss\t{%3, %x2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %x2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("SF"))])
@@ -20106,7 +20098,7 @@
 	  (match_operand:V16SI 3 "register_operand" "0")
 	  (match_operand:HI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124VNNIW"
-  "vp4dpwssd\t{%2, %g1, %0%{%4%}|%{%4%}%0, %g1, %2}"
+  "vp4dpwssd\t{%2, %g1, %0%{%4%}|%0%{%4%}, %g1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("TI"))])
@@ -20121,7 +20113,7 @@
 	  (match_operand:V16SI 4 "const0_operand" "C")
 	  (match_operand:HI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124VNNIW"
-  "vp4dpwssd\t{%3, %g2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %g2, %3}"
+  "vp4dpwssd\t{%3, %g2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %g2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("TI"))])
@@ -20147,7 +20139,7 @@
 	  (match_operand:V16SI 3 "register_operand" "0")
 	  (match_operand:HI 4 "register_operand" "Yk")))]
   "TARGET_AVX5124VNNIW"
-  "vp4dpwssds\t{%2, %g1, %0%{%4%}|%{%4%}%0, %g1, %2}"
+  "vp4dpwssds\t{%2, %g1, %0%{%4%}|%0%{%4%}, %g1, %2}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("TI"))])
@@ -20162,7 +20154,7 @@
 	  (match_operand:V16SI 4 "const0_operand" "C")
 	  (match_operand:HI 5 "register_operand" "Yk")))]
   "TARGET_AVX5124VNNIW"
-  "vp4dpwssds\t{%3, %g2, %0%{%5%}%{z%}|%{%5%}%{z%}%0, %g2, %3}"
+  "vp4dpwssds\t{%3, %g2, %0%{%5%}%{z%}|%0%{%5%}%{z%}, %g2, %3}"
    [(set_attr ("type") ("ssemuladd"))
     (set_attr ("prefix") ("evex"))
     (set_attr ("mode") ("TI"))])