[PATCH i386 4/8] [AVX512] [5/8] Add substed patterns: rounding subst.
Kirill Yukhin
kirill.yukhin@gmail.com
Wed Nov 6 07:24:00 GMT 2013
Hello,
On 14 Aug 11:44, Kirill Yukhin wrote:
> Rounding is implemented by adding a const_int value in parallel with the
> original pattern - however, that might be not the best approach. define_subst
> for this transformation are quite straightforward - we needed three of them to
> cover all patterns we need to transform. The most interesting part here is how
> to determine which operand corresponds to the rounding immediate. To somehow
> reflect this in the pattern, we allowed using attributes in other attributes,
> i.e. attributes nesting (that's already in the trunk). The problem here arises
> from the next: when subst for rounding is applied to a pattern after subst for
> masking, it's actually applied to two patterns with different number of
> operands. To find that number, we wrote next attributes: (define_subst_attr
> "round_mask_operand2" "mask" "%R2" "%R4") (define_subst_attr "round_mask_op2"
> "round" "" "<round_mask_operand2>") In result, we get either empty string (if
> rounding-subst isn't applied), or "%R2" or "%R4" depending on whether mask-subst
> was applied.
Corrsponding subst implementation is in the bottom.
Bootstrapped.
Is it ok for trunk?
--
Thanks, K
---
gcc/config/i386/i386.c | 32 +++
gcc/config/i386/i386.md | 10 +
gcc/config/i386/sse.md | 642 +++++++++++++++++++++++++----------------------
gcc/config/i386/subst.md | 41 +++
4 files changed, 426 insertions(+), 299 deletions(-)
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index a69e057..e172adf 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -14839,6 +14839,38 @@ ix86_print_operand (FILE *file, rtx x, int code)
fputs ("{z}", file);
return;
+ case 'R':
+ gcc_assert (CONST_INT_P (x));
+
+ if (ASSEMBLER_DIALECT == ASM_INTEL)
+ fputs (", ", file);
+
+ switch (INTVAL (x))
+ {
+ case ROUND_NEAREST_INT:
+ fputs ("{rn-sae}", file);
+ break;
+ case ROUND_NEG_INF:
+ fputs ("{rd-sae}", file);
+ break;
+ case ROUND_POS_INF:
+ fputs ("{ru-sae}", file);
+ break;
+ case ROUND_ZERO:
+ fputs ("{rz-sae}", file);
+ break;
+ case ROUND_SAE:
+ fputs ("{sae}", file);
+ break;
+ default:
+ gcc_unreachable ();
+ }
+
+ if (ASSEMBLER_DIALECT == ASM_ATT)
+ fputs (", ", file);
+
+ return;
+
case '*':
if (ASSEMBLER_DIALECT == ASM_ATT)
putc ('*', file);
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index c7ec0c1..344702b 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -246,6 +246,16 @@
(ROUND_NO_EXC 0x8)
])
+;; Constants to represent AVX512F embeded rounding
+(define_constants
+ [(ROUND_NEAREST_INT 0)
+ (ROUND_NEG_INF 1)
+ (ROUND_POS_INF 2)
+ (ROUND_ZERO 3)
+ (NO_ROUND 4)
+ (ROUND_SAE 5)
+ ])
+
;; Constants to represent pcomtrue/pcomfalse variants
(define_constants
[(PCOM_FALSE 0)
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 6b41060..61b96a1 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -1285,80 +1285,80 @@
}
[(set_attr "isa" "noavx,noavx,avx,avx")])
-(define_expand "<plusminus_insn><mode>3<mask_name>"
+(define_expand "<plusminus_insn><mode>3<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand")
(plusminus:VF
(match_operand:VF 1 "nonimmediate_operand")
(match_operand:VF 2 "nonimmediate_operand")))]
- "TARGET_SSE && <mask_mode512bit_condition>"
+ "TARGET_SSE && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
-(define_insn "*<plusminus_insn><mode>3<mask_name>"
+(define_insn "*<plusminus_insn><mode>3<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=x,v")
(plusminus:VF
(match_operand:VF 1 "nonimmediate_operand" "<comm>0,v")
- (match_operand:VF 2 "nonimmediate_operand" "xm,vm")))]
- "TARGET_SSE && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands) && <mask_mode512bit_condition>"
+ (match_operand:VF 2 "nonimmediate_operand" "xm,<round_constraint>")))]
+ "TARGET_SSE && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands) && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
<plusminus_mnemonic><ssemodesuffix>\t{%2, %0|%0, %2}
- v<plusminus_mnemonic><ssemodesuffix>\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ v<plusminus_mnemonic><ssemodesuffix>\t{<round_mask_op3>%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<round_mask_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sseadd")
(set_attr "prefix" "<mask_prefix3>")
(set_attr "mode" "<MODE>")])
-(define_insn "<sse>_vm<plusminus_insn><mode>3<mask_scalar_name>"
+(define_insn "<sse>_vm<plusminus_insn><mode>3<mask_scalar_name><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
(vec_merge:VF_128
(plusminus:VF_128
(match_operand:VF_128 1 "register_operand" "0,v")
- (match_operand:VF_128 2 "nonimmediate_operand" "xm,vm"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm,<round_constraint>"))
(match_dup 1)
(const_int 1)))]
"TARGET_SSE"
"@
<plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %0|%0, %<iptr>2}
- v<plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %<iptr>2}"
+ v<plusminus_mnemonic><ssescalarmodesuffix>\t{<round_mask_scalar_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %<iptr>2<round_mask_scalar_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sseadd")
(set_attr "prefix" "<mask_scalar_prefix>")
(set_attr "mode" "<ssescalarmode>")])
-(define_expand "mul<mode>3<mask_name>"
+(define_expand "mul<mode>3<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand")
(mult:VF
(match_operand:VF 1 "nonimmediate_operand")
(match_operand:VF 2 "nonimmediate_operand")))]
- "TARGET_SSE && <mask_mode512bit_condition>"
+ "TARGET_SSE && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);")
-(define_insn "*mul<mode>3<mask_name>"
+(define_insn "*mul<mode>3<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=x,v")
(mult:VF
(match_operand:VF 1 "nonimmediate_operand" "%0,v")
- (match_operand:VF 2 "nonimmediate_operand" "xm,vm")))]
- "TARGET_SSE && ix86_binary_operator_ok (MULT, <MODE>mode, operands) && <mask_mode512bit_condition>"
+ (match_operand:VF 2 "nonimmediate_operand" "xm,<round_constraint>")))]
+ "TARGET_SSE && ix86_binary_operator_ok (MULT, <MODE>mode, operands) && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
mul<ssemodesuffix>\t{%2, %0|%0, %2}
- vmul<ssemodesuffix>\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ vmul<ssemodesuffix>\t{<round_mask_op3>%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<round_mask_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "ssemul")
(set_attr "prefix" "<mask_prefix3>")
(set_attr "btver2_decode" "direct,double")
(set_attr "mode" "<MODE>")])
-(define_insn "<sse>_vm<multdiv_mnemonic><mode>3<mask_scalar_name>"
+(define_insn "<sse>_vm<multdiv_mnemonic><mode>3<mask_scalar_name><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
(vec_merge:VF_128
(multdiv:VF_128
(match_operand:VF_128 1 "register_operand" "0,v")
- (match_operand:VF_128 2 "nonimmediate_operand" "xm,vm"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm,<round_constraint>"))
(match_dup 1)
(const_int 1)))]
"TARGET_SSE"
"@
<multdiv_mnemonic><ssescalarmodesuffix>\t{%2, %0|%0, %<iptr>2}
- v<multdiv_mnemonic><ssescalarmodesuffix>\t{%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %<iptr>2}"
+ v<multdiv_mnemonic><ssescalarmodesuffix>\t{<round_mask_scalar_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %<iptr>2<round_mask_scalar_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sse<multdiv_mnemonic>")
(set_attr "prefix" "<mask_scalar_prefix>")
@@ -1391,15 +1391,15 @@
}
})
-(define_insn "<sse>_div<mode>3<mask_name>"
+(define_insn "<sse>_div<mode>3<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=x,v")
(div:VF
(match_operand:VF 1 "register_operand" "0,v")
- (match_operand:VF 2 "nonimmediate_operand" "xm,vm")))]
- "TARGET_SSE && <mask_mode512bit_condition>"
+ (match_operand:VF 2 "nonimmediate_operand" "xm,<round_constraint>")))]
+ "TARGET_SSE && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
div<ssemodesuffix>\t{%2, %0|%0, %2}
- vdiv<ssemodesuffix>\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ vdiv<ssemodesuffix>\t{<round_mask_op3>%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<round_mask_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "ssediv")
(set_attr "prefix" "<mask_prefix3>")
@@ -1482,28 +1482,28 @@
}
})
-(define_insn "<sse>_sqrt<mode>2<mask_name>"
+(define_insn "<sse>_sqrt<mode>2<mask_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=v")
- (sqrt:VF (match_operand:VF 1 "nonimmediate_operand" "vm")))]
- "TARGET_SSE && <mask_mode512bit_condition>"
- "%vsqrt<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ (sqrt:VF (match_operand:VF 1 "nonimmediate_operand" "<round_constraint>")))]
+ "TARGET_SSE && <mask_mode512bit_condition> && <round_mode512bit_condition>"
+ "%vsqrt<ssemodesuffix>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "sse")
(set_attr "atom_sse_attr" "sqrt")
(set_attr "btver2_sse_attr" "sqrt")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<MODE>")])
-(define_insn "<sse>_vmsqrt<mode>2<mask_scalar_name>"
+(define_insn "<sse>_vmsqrt<mode>2<mask_scalar_name><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
(vec_merge:VF_128
(sqrt:VF_128
- (match_operand:VF_128 1 "nonimmediate_operand" "xm,vm"))
+ (match_operand:VF_128 1 "nonimmediate_operand" "xm,<round_constraint>"))
(match_operand:VF_128 2 "register_operand" "0,v")
(const_int 1)))]
"TARGET_SSE"
"@
sqrt<ssescalarmodesuffix>\t{%1, %0|%0, %<iptr>1}
- vsqrt<ssescalarmodesuffix>\t{%1, %2, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %2, %<iptr>1}"
+ vsqrt<ssescalarmodesuffix>\t{<round_mask_scalar_op3>%1, %2, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %2, %<iptr>1<round_mask_scalar_op3>}"
[(set_attr "isa" "noavx,avx")
(set_attr "type" "sse")
(set_attr "atom_sse_attr" "sqrt")
@@ -2752,210 +2752,224 @@
(match_operand:FMAMODE 3 "nonimmediate_operand")))]
"")
-(define_insn "<sd_mask_codefor>fma_fmadd_<mode><sd_maskz_name>"
+(define_expand "avx512f_fmadd_<mode>_maskz"
+ [(match_operand:VF_512 0 "register_operand")
+ (match_operand:VF_512 1 "nonimmediate_operand")
+ (match_operand:VF_512 2 "nonimmediate_operand")
+ (match_operand:VF_512 3 "nonimmediate_operand")
+ (match_operand:<avx512fmaskmode> 4 "register_operand")]
+ "TARGET_AVX512F"
+{
+ emit_insn (gen_fma_fmadd_<mode>_maskz_1 (
+ operands[0], operands[1], operands[2], operands[3],
+ CONST0_RTX (<MODE>mode), operands[4]));
+ DONE;
+})
+
+(define_insn "<sd_mask_codefor>fma_fmadd_<mode><sd_maskz_name><round_name>"
[(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
(fma:FMAMODE
- (match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x")
- (match_operand:FMAMODE 2 "nonimmediate_operand" "vm, v,vm, x,m")
- (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x")))]
- "<sd_mask_mode512bit_condition>"
- "@
- vfmadd132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfmadd213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfmadd231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ (match_operand:FMAMODE 1 "nonimmediate_operand" "%0,0,v,x,x")
+ (match_operand:FMAMODE 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
+ (match_operand:FMAMODE 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x")))]
+ "<sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
+ "@
+ vfmadd132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfmadd213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfmadd231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfmadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfmadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmadd_<mode>_mask"
+(define_insn "avx512f_fmadd_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(fma:VF_512
(match_operand:VF_512 1 "register_operand" "0,0")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm"))
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfmadd132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfmadd213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfmadd132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfmadd213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmadd_<mode>_mask3"
+(define_insn "avx512f_fmadd_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=x")
(vec_merge:VF_512
(fma:VF_512
(match_operand:VF_512 1 "register_operand" "x")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(match_operand:VF_512 3 "register_operand" "0"))
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfmadd231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfmadd231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "<sd_mask_codefor>fma_fmsub_<mode><sd_maskz_name>"
+(define_insn "<sd_mask_codefor>fma_fmsub_<mode><sd_maskz_name><round_name>"
[(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
(fma:FMAMODE
(match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x")
- (match_operand:FMAMODE 2 "nonimmediate_operand" "vm, v,vm, x,m")
+ (match_operand:FMAMODE 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
(neg:FMAMODE
- (match_operand:FMAMODE 3 "nonimmediate_operand" "" v,vm, 0,xm,x"))))]
- "<sd_mask_mode512bit_condition>"
+ (match_operand:FMAMODE 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x"))))]
+ "<sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
- vfmsub132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfmsub213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfmsub231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ vfmsub132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfmsub213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfmsub231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfmsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfmsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmsub_<mode>_mask"
+(define_insn "avx512f_fmsub_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(fma:VF_512
(match_operand:VF_512 1 "register_operand" "0,0")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_512
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfmsub132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfmsub213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfmsub132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfmsub213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmsub_<mode>_mask3"
+(define_insn "avx512f_fmsub_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(vec_merge:VF_512
(fma:VF_512
(match_operand:VF_512 1 "register_operand" "v")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(neg:VF_512
(match_operand:VF_512 3 "register_operand" "0")))
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfmsub231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfmsub231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "<sd_mask_codefor>fma_fnmadd_<mode><sd_maskz_name>"
+(define_insn "<sd_mask_codefor>fma_fnmadd_<mode><sd_maskz_name><round_name>"
[(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
(fma:FMAMODE
(neg:FMAMODE
- (match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x"))
- (match_operand:FMAMODE 2 "nonimmediate_operand" "vm, v,vm, x,m")
- (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x")))]
- "<sd_mask_mode512bit_condition>"
- "@
- vfnmadd132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfnmadd213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfnmadd231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ (match_operand:FMAMODE 1 "nonimmediate_operand" "%0,0,v,x,x"))
+ (match_operand:FMAMODE 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
+ (match_operand:FMAMODE 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x")))]
+ "<sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
+ "@
+ vfnmadd132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfnmadd213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfnmadd231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfnmadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfnmadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fnmadd_<mode>_mask"
+(define_insn "avx512f_fnmadd_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(fma:VF_512
(neg:VF_512
(match_operand:VF_512 1 "register_operand" "0,0"))
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm"))
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfnmadd132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfnmadd213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfnmadd132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfnmadd213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fnmadd_<mode>_mask3"
+(define_insn "avx512f_fnmadd_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(vec_merge:VF_512
(fma:VF_512
(neg:VF_512
(match_operand:VF_512 1 "register_operand" "v"))
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(match_operand:VF_512 3 "register_operand" "0"))
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfnmadd231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfnmadd231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "<sd_mask_codefor>fma_fnmsub_<mode><sd_maskz_name>"
+(define_insn "<sd_mask_codefor>fma_fnmsub_<mode><sd_maskz_name><round_name>"
[(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
(fma:FMAMODE
(neg:FMAMODE
- (match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x"))
- (match_operand:FMAMODE 2 "nonimmediate_operand" "vm, v,vm, x,m")
+ (match_operand:FMAMODE 1 "nonimmediate_operand" "%0,0,v,x,x"))
+ (match_operand:FMAMODE 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
(neg:FMAMODE
- (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x"))))]
- "<sd_mask_mode512bit_condition>"
+ (match_operand:FMAMODE 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x"))))]
+ "<sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
- vfnmsub132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfnmsub213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfnmsub231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ vfnmsub132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfnmsub213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfnmsub231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfnmsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfnmsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fnmsub_<mode>_mask"
+(define_insn "avx512f_fnmsub_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(fma:VF_512
(neg:VF_512
(match_operand:VF_512 1 "register_operand" "0,0"))
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_512
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfnmsub132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfnmsub213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfnmsub132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfnmsub213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fnmsub_<mode>_mask3"
+(define_insn "avx512f_fnmsub_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(vec_merge:VF_512
(fma:VF_512
(neg:VF_512
(match_operand:VF_512 1 "register_operand" "v"))
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(neg:VF_512
(match_operand:VF_512 3 "register_operand" "0")))
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfnmsub231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfnmsub231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
@@ -2994,109 +3008,109 @@
DONE;
})
-(define_insn "<sd_mask_codefor>fma_fmaddsub_<mode><sd_maskz_name>"
+(define_insn "<sd_mask_codefor>fma_fmaddsub_<mode><sd_maskz_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=v,v,v,x,x")
(unspec:VF
- [(match_operand:VF 1 "nonimmediate_operand" "%0, 0, v, x,x")
- (match_operand:VF 2 "nonimmediate_operand" "vm, v,vm, x,m")
- (match_operand:VF 3 "nonimmediate_operand" " v,vm, 0,xm,x")]
+ [(match_operand:VF 1 "nonimmediate_operand" "%0,0,v,x,x")
+ (match_operand:VF 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
+ (match_operand:VF 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x")]
UNSPEC_FMADDSUB))]
- "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F) && <sd_mask_mode512bit_condition>"
+ "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F) && <sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
- vfmaddsub132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfmaddsub213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfmaddsub231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ vfmaddsub132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfmaddsub213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfmaddsub231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfmaddsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfmaddsub<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmaddsub_<mode>_mask"
+(define_insn "avx512f_fmaddsub_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(unspec:VF_512
[(match_operand:VF_512 1 "register_operand" "0,0")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm")]
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>")]
UNSPEC_FMADDSUB)
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfmaddsub132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfmaddsub213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfmaddsub132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfmaddsub213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmaddsub_<mode>_mask3"
+(define_insn "avx512f_fmaddsub_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(vec_merge:VF_512
(unspec:VF_512
[(match_operand:VF_512 1 "register_operand" "v")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(match_operand:VF_512 3 "register_operand" "0")]
UNSPEC_FMADDSUB)
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfmaddsub231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfmaddsub231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "<sd_mask_codefor>fma_fmsubadd_<mode><sd_maskz_name>"
+(define_insn "<sd_mask_codefor>fma_fmsubadd_<mode><sd_maskz_name><round_name>"
[(set (match_operand:VF 0 "register_operand" "=v,v,v,x,x")
(unspec:VF
- [(match_operand:VF 1 "nonimmediate_operand" "%0, 0, v, x,x")
- (match_operand:VF 2 "nonimmediate_operand" "vm, v,vm, x,m")
+ [(match_operand:VF 1 "nonimmediate_operand" "%0,0,v,x,x")
+ (match_operand:VF 2 "nonimmediate_operand" "<round_constraint>,v,<round_constraint>,x,m")
(neg:VF
- (match_operand:VF 3 "nonimmediate_operand" " v,vm, 0,xm,x"))]
+ (match_operand:VF 3 "nonimmediate_operand" "v,<round_constraint>,0,xm,x"))]
UNSPEC_FMADDSUB))]
- "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F) && <sd_mask_mode512bit_condition>"
+ "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F) && <sd_mask_mode512bit_condition> && <round_mode512bit_condition>"
"@
- vfmsubadd132<ssemodesuffix>\t{%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2}
- vfmsubadd213<ssemodesuffix>\t{%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3}
- vfmsubadd231<ssemodesuffix>\t{%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2}
+ vfmsubadd132<ssemodesuffix>\t{<round_sd_mask_op4>%2, %3, %0<sd_mask_op4>|%0<sd_mask_op4>, %3, %2<round_sd_mask_op4>}
+ vfmsubadd213<ssemodesuffix>\t{<round_sd_mask_op4>%3, %2, %0<sd_mask_op4>|%0<sd_mask_op4>, %2, %3<round_sd_mask_op4>}
+ vfmsubadd231<ssemodesuffix>\t{<round_sd_mask_op4>%2, %1, %0<sd_mask_op4>|%0<sd_mask_op4>, %1, %2<round_sd_mask_op4>}
vfmsubadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}
vfmsubadd<ssemodesuffix>\t{%3, %2, %1, %0|%0, %1, %2, %3}"
[(set_attr "isa" "fma_avx512f,fma_avx512f,fma_avx512f,fma4,fma4")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmsubadd_<mode>_mask"
+(define_insn "avx512f_fmsubadd_<mode>_mask<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v,v")
(vec_merge:VF_512
(unspec:VF_512
[(match_operand:VF_512 1 "register_operand" "0,0")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm,v")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_512
- (match_operand:VF_512 3 "nonimmediate_operand" "v,vm"))]
+ (match_operand:VF_512 3 "nonimmediate_operand" "v,<round_constraint>"))]
UNSPEC_FMADDSUB)
(match_dup 1)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k,k")))]
"TARGET_AVX512F"
"@
- vfmsubadd132<ssemodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %3, %2}
- vfmsubadd213<ssemodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %2, %3}"
+ vfmsubadd132<ssemodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfmsubadd213<ssemodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "isa" "fma_avx512f,fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "avx512f_fmsubadd_<mode>_mask3"
+(define_insn "avx512f_fmsubadd_<mode>_mask3<round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(vec_merge:VF_512
(unspec:VF_512
[(match_operand:VF_512 1 "register_operand" "v")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")
(neg:VF_512
(match_operand:VF_512 3 "register_operand" "0"))]
UNSPEC_FMADDSUB)
(match_dup 3)
(match_operand:<avx512fmaskmode> 4 "register_operand" "k")))]
"TARGET_AVX512F"
- "vfmsubadd231<ssemodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %1, %2}"
+ "vfmsubadd231<ssemodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "isa" "fma_avx512f")
(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
@@ -3104,7 +3118,22 @@
;; FMA3 floating point scalar intrinsics. These merge result with
;; high-order elements from the destination register.
-(define_expand "fmai_vmfmadd_<mode>"
+(define_expand "fmai_vmfmadd_<mode>_maskz<round_name>"
+ [(set (match_operand:VF_128 0 "register_operand")
+ (vec_merge:VF_128
+ (vec_merge:VF_128
+ (fma:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand")
+ (match_operand:VF_128 2 "nonimmediate_operand")
+ (match_operand:VF_128 3 "nonimmediate_operand"))
+ (match_dup <round_opnum>)
+ (match_operand:QI 4 "register_operand"))
+ (match_dup 1)
+ (const_int 1)))]
+ "TARGET_AVX512F"
+ "operands[<round_opnum>] = CONST0_RTX (<MODE>mode);")
+
+(define_expand "fmai_vmfmadd_<mode><round_name>"
[(set (match_operand:VF_128 0 "register_operand")
(vec_merge:VF_128
(fma:VF_128
@@ -3115,207 +3144,222 @@
(const_int 1)))]
"TARGET_FMA")
-(define_insn "*fmai_fmadd_<mode>"
- [(set (match_operand:VF_128 0 "register_operand" "=v,v")
- (vec_merge:VF_128
- (fma:VF_128
- (match_operand:VF_128 1 "nonimmediate_operand" " 0, 0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm, v")
- (match_operand:VF_128 3 "nonimmediate_operand" " v,vm"))
- (match_dup 1)
- (const_int 1)))]
- "TARGET_FMA || TARGET_AVX512F"
- "@
- vfmadd132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
- vfmadd213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
- [(set_attr "type" "ssemuladd")
- (set_attr "mode" "<MODE>")])
-
-(define_insn "*fmai_fmsub_<mode>_mask"
+(define_insn "fmai_vmfmadd_<mode>_mask<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" " 0, 0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm, v")
- (neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>, v")
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_dup 1)
(match_operand:QI 4 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2}
- vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3}"
+ vfmadd132<ssescalarmodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %3, %2<round_op5>}
+ vfmadd213<ssescalarmodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %2, %3<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "fmai_vmfmsub_<mode>_mask3"
+(define_insn "fmai_vmfmadd_<mode>_mask3<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "%v")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm")
- (neg:VF_128
- (match_operand:VF_128 3 "register_operand" "0")))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>")
+ (match_operand:VF_128 3 "register_operand" "0"))
(match_dup 3)
(match_operand:QI 4 "register_operand" "k"))
(match_dup 3)
(const_int 1)))]
"TARGET_AVX512F"
- "vfmsub231<ssescalarmodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2}"
+ "vfmadd231<ssescalarmodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %1, %2<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fmsub_<mode>_maskz"
+(define_insn "*fmai_fmadd_<mode>_maskz<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v")
- (neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v")
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_operand:VF_128 4 "const0_operand")
(match_operand:QI 5 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2}
- vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3}"
+ vfmadd132<ssescalarmodesuffix>\t{<round_op6>%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %3, %2<round_op6>}
+ vfmadd213<ssescalarmodesuffix>\t{<round_op6>%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %2, %3<round_op6>}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "*fmai_fmadd_<mode><round_name>"
+ [(set (match_operand:VF_128 0 "register_operand" "=v,v")
+ (vec_merge:VF_128
+ (fma:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "0,0")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v")
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
+ (match_dup 1)
+ (const_int 1)))]
+ "TARGET_FMA || TARGET_AVX512F"
+ "@
+ vfmadd132<ssescalarmodesuffix>\t{<round_op4>%2, %3, %0|%0, %<iptr>3, %<iptr>2<round_op4>}
+ vfmadd213<ssescalarmodesuffix>\t{<round_op4>%3, %2, %0|%0, %<iptr>2, %<iptr>3<round_op4>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fmsub_<mode>_mask"
+(define_insn "*fmai_fmsub_<mode>_mask<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_dup 1)
(match_operand:QI 4 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2}
- vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3}"
+ vfmsub132<ssescalarmodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2<round_op5>}
+ vfmsub213<ssescalarmodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3<round_op5>}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "fmai_vmfmsub_<mode>_mask3<round_name>"
+ [(set (match_operand:VF_128 0 "register_operand" "=v")
+ (vec_merge:VF_128
+ (vec_merge:VF_128
+ (fma:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "%v")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>")
+ (neg:VF_128
+ (match_operand:VF_128 3 "register_operand" "0")))
+ (match_dup 3)
+ (match_operand:QI 4 "register_operand" "k"))
+ (match_dup 3)
+ (const_int 1)))]
+ "TARGET_AVX512F"
+ "vfmsub231<ssescalarmodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fmsub_<mode>_maskz"
+(define_insn "*fmai_fmsub_<mode>_maskz<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_operand:VF_128 4 "const0_operand")
(match_operand:QI 5 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2}
- vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3}"
+ vfmsub132<ssescalarmodesuffix>\t{<round_op6>%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2<round_op6>}
+ vfmsub213<ssescalarmodesuffix>\t{<round_op6>%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3<round_op6>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_vmfnmadd_<mode>_mask"
+(define_insn "*fmai_vmfnmadd_<mode>_mask<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v"))
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm"))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_dup 1)
(match_operand:QI 4 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfnmadd132<ssescalarmodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2}
- vfnmadd213<ssescalarmodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3}"
+ vfnmadd132<ssescalarmodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2<round_op5>}
+ vfnmadd213<ssescalarmodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_vmfnmadd_<mode>_mask3"
+(define_insn "*fmai_vmfnmadd_<mode>_mask3<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "%v"))
- (match_operand:VF_128 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>")
(match_operand:VF_128 3 "register_operand" "0"))
(match_dup 3)
(match_operand:QI 4 "register_operand" "k"))
(match_dup 3)
(const_int 1)))]
"TARGET_AVX512F"
- "vfnmadd231<ssescalarmodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2}"
+ "vfnmadd231<ssescalarmodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_vmfnmadd_<mode>_maskz"
+(define_insn "*fmai_vmfnmadd_<mode>_maskz<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v"))
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm"))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_operand:VF_128 4 "const0_operand")
(match_operand:QI 5 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfnmadd132<ssescalarmodesuffix>\t{%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2}
- vfnmadd213<ssescalarmodesuffix>\t{%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3}"
+ vfnmadd132<ssescalarmodesuffix>\t{<round_op6>%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2<round_op6>}
+ vfnmadd213<ssescalarmodesuffix>\t{<round_op6>%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3<round_op6>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fnmsub_<mode>_mask"
+(define_insn "*fmai_fnmsub_<mode>_mask<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v"))
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_dup 1)
(match_operand:QI 4 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfnmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2}
- vfnmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3}"
+ vfnmsub132<ssescalarmodesuffix>\t{<round_op5>%2, %3, %0%{%4%}|%0%{%4%}, %<iptr>3, %<iptr>2<round_op5>}
+ vfnmsub213<ssescalarmodesuffix>\t{<round_op5>%3, %2, %0%{%4%}|%0%{%4%}, %<iptr>2, %<iptr>3<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fnmsub_<mode>_mask3"
+(define_insn "*fmai_fnmsub_<mode>_mask3<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
(match_operand:VF_128 1 "nonimmediate_operand" "%v"))
- (match_operand:VF_128 2 "nonimmediate_operand" "vm")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>")
(neg:VF_128
(match_operand:VF_128 3 "register_operand" "0")))
(match_dup 3)
@@ -3323,80 +3367,80 @@
(match_dup 3)
(const_int 1)))]
"TARGET_AVX512F"
- "vfnmsub231<ssescalarmodesuffix>\t{%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2}"
+ "vfnmsub231<ssescalarmodesuffix>\t{<round_op5>%2, %1, %0%{%4%}|%0%{%4%}, %<iptr>1, %<iptr>2<round_op5>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fnmsub_<mode>_maskz"
+(define_insn "*fmai_fnmsub_<mode>_maskz<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm,v"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v"))
(match_operand:VF_128 1 "nonimmediate_operand" "0,0")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" "v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>")))
(match_operand:VF_128 4 "const0_operand")
(match_operand:QI 5 "register_operand" "k,k"))
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
"@
- vfnmsub132<ssescalarmodesuffix>\t{%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2}
- vfnmsub213<ssescalarmodesuffix>\t{%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3}"
+ vfnmsub132<ssescalarmodesuffix>\t{<round_op6>%2, %3, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>3, %<iptr>2<round_op6>}
+ vfnmsub213<ssescalarmodesuffix>\t{<round_op6>%3, %2, %0%{%5%}%N4|%0%{%5%}%N4, %<iptr>2, %<iptr>3<round_op6>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fmsub_<mode>"
+(define_insn "*fmai_fmsub_<mode><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(fma:VF_128
- (match_operand:VF_128 1 "nonimmediate_operand" " 0, 0")
- (match_operand:VF_128 2 "nonimmediate_operand" "vm, v")
+ (match_operand:VF_128 1 "nonimmediate_operand" "0,0")
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" " v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" " v,<round_constraint>")))
(match_dup 1)
(const_int 1)))]
"TARGET_FMA || TARGET_AVX512F"
"@
- vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
- vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
+ vfmsub132<ssescalarmodesuffix>\t{<round_op4>%2, %3, %0|%0, %<iptr>3, %<iptr>2<round_op4>}
+ vfmsub213<ssescalarmodesuffix>\t{<round_op4>%3, %2, %0|%0, %<iptr>2, %<iptr>3<round_op4>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fnmadd_<mode>"
+(define_insn "*fmai_fnmadd_<mode><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm, v"))
- (match_operand:VF_128 1 "nonimmediate_operand" " 0, 0")
- (match_operand:VF_128 3 "nonimmediate_operand" " v,vm"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>,v"))
+ (match_operand:VF_128 1 "nonimmediate_operand" "0,0")
+ (match_operand:VF_128 3 "nonimmediate_operand" "v,<round_constraint>"))
(match_dup 1)
(const_int 1)))]
"TARGET_FMA || TARGET_AVX512F"
"@
- vfnmadd132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
- vfnmadd213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
+ vfnmadd132<ssescalarmodesuffix>\t{<round_op4>%2, %3, %0|%0, %<iptr>3, %<iptr>2<round_op4>}
+ vfnmadd213<ssescalarmodesuffix>\t{<round_op4>%3, %2, %0|%0, %<iptr>2, %<iptr>3<round_op4>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
-(define_insn "*fmai_fnmsub_<mode>"
+(define_insn "*fmai_fnmsub_<mode><round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v,v")
(vec_merge:VF_128
(fma:VF_128
(neg:VF_128
- (match_operand:VF_128 2 "nonimmediate_operand" "vm, v"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>, v"))
(match_operand:VF_128 1 "nonimmediate_operand" " 0, 0")
(neg:VF_128
- (match_operand:VF_128 3 "nonimmediate_operand" " v,vm")))
+ (match_operand:VF_128 3 "nonimmediate_operand" " v,<round_constraint>")))
(match_dup 1)
(const_int 1)))]
"TARGET_FMA || TARGET_AVX512F"
"@
- vfnmsub132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
- vfnmsub213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
+ vfnmsub132<ssescalarmodesuffix>\t{<round_op4>%2, %3, %0|%0, %<iptr>3, %<iptr>2<round_op4>}
+ vfnmsub213<ssescalarmodesuffix>\t{<round_op4>%3, %2, %0|%0, %<iptr>2, %<iptr>3<round_op4>}"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
@@ -3517,18 +3561,18 @@
(set_attr "prefix_rep" "0")
(set_attr "mode" "SF")])
-(define_insn "sse_cvtsi2ss"
+(define_insn "sse_cvtsi2ss<round_name>"
[(set (match_operand:V4SF 0 "register_operand" "=x,x,v")
(vec_merge:V4SF
(vec_duplicate:V4SF
- (float:SF (match_operand:SI 2 "nonimmediate_operand" "r,m,rm")))
+ (float:SF (match_operand:SI 2 "nonimmediate_operand" "r,m,<round_constraint3>")))
(match_operand:V4SF 1 "register_operand" "0,0,v")
(const_int 1)))]
"TARGET_SSE"
"@
cvtsi2ss\t{%2, %0|%0, %2}
cvtsi2ss\t{%2, %0|%0, %2}
- vcvtsi2ss\t{%2, %1, %0|%0, %1, %2}"
+ vcvtsi2ss\t{<round_op3>%2, %1, %0|%0, %1, %2<round_op3>}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "vector,double,*")
@@ -3538,18 +3582,18 @@
(set_attr "prefix" "orig,orig,maybe_evex")
(set_attr "mode" "SF")])
-(define_insn "sse_cvtsi2ssq"
+(define_insn "sse_cvtsi2ssq<round_name>"
[(set (match_operand:V4SF 0 "register_operand" "=x,x,v")
(vec_merge:V4SF
(vec_duplicate:V4SF
- (float:SF (match_operand:DI 2 "nonimmediate_operand" "r,m,rm")))
+ (float:SF (match_operand:DI 2 "nonimmediate_operand" "r,m,<round_constraint3>")))
(match_operand:V4SF 1 "register_operand" "0,0,v")
(const_int 1)))]
"TARGET_SSE && TARGET_64BIT"
"@
cvtsi2ssq\t{%2, %0|%0, %2}
cvtsi2ssq\t{%2, %0|%0, %2}
- vcvtsi2ssq\t{%2, %1, %0|%0, %1, %2}"
+ vcvtsi2ssq\t{<round_op3>%2, %1, %0|%0, %1, %2<round_op3>}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "vector,double,*")
@@ -3561,15 +3605,15 @@
(set_attr "prefix" "orig,orig,maybe_evex")
(set_attr "mode" "SF")])
-(define_insn "sse_cvtss2si"
+(define_insn "sse_cvtss2si<round_name>"
[(set (match_operand:SI 0 "register_operand" "=r,r")
(unspec:SI
[(vec_select:SF
- (match_operand:V4SF 1 "nonimmediate_operand" "v,m")
+ (match_operand:V4SF 1 "nonimmediate_operand" "v,<round_constraint2>")
(parallel [(const_int 0)]))]
UNSPEC_FIX_NOTRUNC))]
"TARGET_SSE"
- "%vcvtss2si\t{%1, %0|%0, %k1}"
+ "%vcvtss2si\t{<round_op2>%1, %0|%0, %k1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "double,vector")
(set_attr "bdver1_decode" "double,double")
@@ -3591,15 +3635,15 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "SI")])
-(define_insn "sse_cvtss2siq"
+(define_insn "sse_cvtss2siq<round_name>"
[(set (match_operand:DI 0 "register_operand" "=r,r")
(unspec:DI
[(vec_select:SF
- (match_operand:V4SF 1 "nonimmediate_operand" "v,m")
+ (match_operand:V4SF 1 "nonimmediate_operand" "v,<round_constraint2>")
(parallel [(const_int 0)]))]
UNSPEC_FIX_NOTRUNC))]
"TARGET_SSE && TARGET_64BIT"
- "%vcvtss2si{q}\t{%1, %0|%0, %k1}"
+ "%vcvtss2si{q}\t{<round_op2>%1, %0|%0, %k1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "double,vector")
(set_attr "bdver1_decode" "double,double")
@@ -3653,50 +3697,50 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "DI")])
-(define_insn "cvtusi2<ssescalarmodesuffix>32"
+(define_insn "cvtusi2<ssescalarmodesuffix>32<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(vec_duplicate:VF_128
(unsigned_float:<ssescalarmode>
- (match_operand:SI 2 "nonimmediate_operand" "rm")))
+ (match_operand:SI 2 "nonimmediate_operand" "<round_constraint3>")))
(match_operand:VF_128 1 "register_operand" "v")
(const_int 1)))]
- "TARGET_AVX512F"
- "vcvtusi2<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "TARGET_AVX512F && <round_modev4sf_condition>"
+ "vcvtusi2<ssescalarmodesuffix>\t{<round_op3>%2, %1, %0|%0, %1, %2<round_op3>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "<ssescalarmode>")])
-(define_insn "cvtusi2<ssescalarmodesuffix>64"
+(define_insn "cvtusi2<ssescalarmodesuffix>64<round_name>"
[(set (match_operand:VF_128 0 "register_operand" "=v")
(vec_merge:VF_128
(vec_duplicate:VF_128
(unsigned_float:<ssescalarmode>
- (match_operand:DI 2 "nonimmediate_operand" "rm")))
+ (match_operand:DI 2 "nonimmediate_operand" "<round_constraint3>")))
(match_operand:VF_128 1 "register_operand" "v")
(const_int 1)))]
"TARGET_AVX512F && TARGET_64BIT"
- "vcvtusi2<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ "vcvtusi2<ssescalarmodesuffix>\t{<round_op3>%2, %1, %0|%0, %1, %2<round_op3>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "<ssescalarmode>")])
-(define_insn "float<sseintvecmodelower><mode>2<mask_name>"
+(define_insn "float<sseintvecmodelower><mode>2<mask_name><round_name>"
[(set (match_operand:VF1 0 "register_operand" "=v")
(float:VF1
- (match_operand:<sseintvecmode> 1 "nonimmediate_operand" "vm")))]
- "TARGET_SSE2 && <mask_mode512bit_condition>"
- "%vcvtdq2ps\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ (match_operand:<sseintvecmode> 1 "nonimmediate_operand" "<round_constraint>")))]
+ "TARGET_SSE2 && <mask_mode512bit_condition> && <round_mode512bit_condition>"
+ "%vcvtdq2ps\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<sseinsnmode>")])
-(define_insn "ufloatv16siv16sf2<mask_name>"
+(define_insn "ufloatv16siv16sf2<mask_name><round_name>"
[(set (match_operand:V16SF 0 "register_operand" "=v")
(unsigned_float:V16SF
- (match_operand:V16SI 1 "nonimmediate_operand" "vm")))]
+ (match_operand:V16SI 1 "nonimmediate_operand" "<round_constraint>")))]
"TARGET_AVX512F"
- "vcvtudq2ps\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtudq2ps\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "V16SF")])
@@ -3731,24 +3775,24 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<sseinsnmode>")])
-(define_insn "<mask_codefor>avx512f_fix_notruncv16sfv16si<mask_name>"
+(define_insn "<mask_codefor>avx512f_fix_notruncv16sfv16si<mask_name><round_name>"
[(set (match_operand:V16SI 0 "register_operand" "=v")
(unspec:V16SI
- [(match_operand:V16SF 1 "nonimmediate_operand" "vm")]
+ [(match_operand:V16SF 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtps2dq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtps2dq\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
-(define_insn "<mask_codefor>avx512f_ufix_notruncv16sfv16si<mask_name>"
+(define_insn "<mask_codefor>avx512f_ufix_notruncv16sfv16si<mask_name><round_name>"
[(set (match_operand:V16SI 0 "register_operand" "=v")
(unspec:V16SI
- [(match_operand:V16SF 1 "nonimmediate_operand" "vm")]
+ [(match_operand:V16SF 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtps2udq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtps2udq\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
@@ -3866,18 +3910,18 @@
(set_attr "prefix" "orig,orig,vex")
(set_attr "mode" "DF")])
-(define_insn "sse2_cvtsi2sdq"
+(define_insn "sse2_cvtsi2sdq<round_name>"
[(set (match_operand:V2DF 0 "register_operand" "=x,x,v")
(vec_merge:V2DF
(vec_duplicate:V2DF
- (float:DF (match_operand:DI 2 "nonimmediate_operand" "r,m,rm")))
+ (float:DF (match_operand:DI 2 "nonimmediate_operand" "r,m,<round_constraint3>")))
(match_operand:V2DF 1 "register_operand" "0,0,v")
(const_int 1)))]
"TARGET_SSE2 && TARGET_64BIT"
"@
cvtsi2sdq\t{%2, %0|%0, %2}
cvtsi2sdq\t{%2, %0|%0, %2}
- vcvtsi2sdq\t{%2, %1, %0|%0, %1, %2}"
+ vcvtsi2sdq\t{<round_op3>%2, %1, %0|%0, %1, %2<round_op3>}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "double,direct,*")
@@ -3888,28 +3932,28 @@
(set_attr "prefix" "orig,orig,maybe_evex")
(set_attr "mode" "DF")])
-(define_insn "avx512f_vcvtss2usi"
+(define_insn "avx512f_vcvtss2usi<round_name>"
[(set (match_operand:SI 0 "register_operand" "=r")
(unspec:SI
[(vec_select:SF
- (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (match_operand:V4SF 1 "nonimmediate_operand" "<round_constraint>")
(parallel [(const_int 0)]))]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtss2usi\t{%1, %0|%0, %1}"
+ "vcvtss2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "SI")])
-(define_insn "avx512f_vcvtss2usiq"
+(define_insn "avx512f_vcvtss2usiq<round_name>"
[(set (match_operand:DI 0 "register_operand" "=r")
(unspec:DI
[(vec_select:SF
- (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (match_operand:V4SF 1 "nonimmediate_operand" "<round_constraint>")
(parallel [(const_int 0)]))]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F && TARGET_64BIT"
- "vcvtss2usi\t{%1, %0|%0, %1}"
+ "vcvtss2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "DI")])
@@ -3938,28 +3982,28 @@
(set_attr "prefix" "evex")
(set_attr "mode" "DI")])
-(define_insn "avx512f_vcvtsd2usi"
+(define_insn "avx512f_vcvtsd2usi<round_name>"
[(set (match_operand:SI 0 "register_operand" "=r")
(unspec:SI
[(vec_select:DF
- (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (match_operand:V2DF 1 "nonimmediate_operand" "<round_constraint>")
(parallel [(const_int 0)]))]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtsd2usi\t{%1, %0|%0, %1}"
+ "vcvtsd2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "SI")])
-(define_insn "avx512f_vcvtsd2usiq"
+(define_insn "avx512f_vcvtsd2usiq<round_name>"
[(set (match_operand:DI 0 "register_operand" "=r")
(unspec:DI
[(vec_select:DF
- (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (match_operand:V2DF 1 "nonimmediate_operand" "<round_constraint>")
(parallel [(const_int 0)]))]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F && TARGET_64BIT"
- "vcvtsd2usi\t{%1, %0|%0, %1}"
+ "vcvtsd2usi\t{<round_op2>%1, %0|%0, %1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "prefix" "evex")
(set_attr "mode" "DI")])
@@ -3988,15 +4032,15 @@
(set_attr "prefix" "evex")
(set_attr "mode" "DI")])
-(define_insn "sse2_cvtsd2si"
+(define_insn "sse2_cvtsd2si<round_name>"
[(set (match_operand:SI 0 "register_operand" "=r,r")
(unspec:SI
[(vec_select:DF
- (match_operand:V2DF 1 "nonimmediate_operand" "v,m")
+ (match_operand:V2DF 1 "nonimmediate_operand" "v,<round_constraint2>")
(parallel [(const_int 0)]))]
UNSPEC_FIX_NOTRUNC))]
"TARGET_SSE2"
- "%vcvtsd2si\t{%1, %0|%0, %q1}"
+ "%vcvtsd2si\t{<round_op2>%1, %0|%0, %q1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "double,vector")
(set_attr "bdver1_decode" "double,double")
@@ -4019,15 +4063,15 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "SI")])
-(define_insn "sse2_cvtsd2siq"
+(define_insn "sse2_cvtsd2siq<round_name>"
[(set (match_operand:DI 0 "register_operand" "=r,r")
(unspec:DI
[(vec_select:DF
- (match_operand:V2DF 1 "nonimmediate_operand" "v,m")
+ (match_operand:V2DF 1 "nonimmediate_operand" "v,<round_constraint2>")
(parallel [(const_int 0)]))]
UNSPEC_FIX_NOTRUNC))]
"TARGET_SSE2 && TARGET_64BIT"
- "%vcvtsd2si{q}\t{%1, %0|%0, %q1}"
+ "%vcvtsd2si{q}\t{<round_op2>%1, %0|%0, %q1<round_op2>}"
[(set_attr "type" "sseicvt")
(set_attr "athlon_decode" "double,vector")
(set_attr "bdver1_decode" "double,double")
@@ -4147,13 +4191,13 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "V2DF")])
-(define_insn "<mask_codefor>avx512f_cvtpd2dq512<mask_name>"
+(define_insn "<mask_codefor>avx512f_cvtpd2dq512<mask_name><round_name>"
[(set (match_operand:V8SI 0 "register_operand" "=v")
(unspec:V8SI
- [(match_operand:V8DF 1 "nonimmediate_operand" "vm")]
+ [(match_operand:V8DF 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtpd2dq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtpd2dq\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "OI")])
@@ -4221,13 +4265,13 @@
(set_attr "athlon_decode" "vector")
(set_attr "bdver1_decode" "double")])
-(define_insn "avx512f_ufix_notruncv8dfv8si<mask_name>"
+(define_insn "avx512f_ufix_notruncv8dfv8si<mask_name><round_name>"
[(set (match_operand:V8SI 0 "register_operand" "=v")
(unspec:V8SI
- [(match_operand:V8DF 1 "nonimmediate_operand" "vm")]
+ [(match_operand:V8DF 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_UNSIGNED_FIX_NOTRUNC))]
"TARGET_AVX512F"
- "vcvtpd2udq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtpd2udq\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "OI")])
@@ -4298,19 +4342,19 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
-(define_insn "sse2_cvtsd2ss<mask_scalar_name>"
+(define_insn "sse2_cvtsd2ss<mask_scalar_name><round_name>"
[(set (match_operand:V4SF 0 "register_operand" "=x,x,v")
(vec_merge:V4SF
(vec_duplicate:V4SF
(float_truncate:V2SF
- (match_operand:V2DF 2 "nonimmediate_operand" "x,m,vm")))
+ (match_operand:V2DF 2 "nonimmediate_operand" "x,m,<round_constraint>")))
(match_operand:V4SF 1 "register_operand" "0,0,v")
(const_int 1)))]
"TARGET_SSE2"
"@
cvtsd2ss\t{%2, %0|%0, %2}
cvtsd2ss\t{%2, %0|%0, %q2}
- vcvtsd2ss\t{%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %q2}"
+ vcvtsd2ss\t{<round_mask_scalar_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %q2<round_mask_scalar_op3>}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssecvt")
(set_attr "athlon_decode" "vector,double,*")
@@ -4343,12 +4387,12 @@
(set_attr "prefix" "orig,orig,<mask_scalar_prefix2>")
(set_attr "mode" "DF")])
-(define_insn "<mask_codefor>avx512f_cvtpd2ps512<mask_name>"
+(define_insn "<mask_codefor>avx512f_cvtpd2ps512<mask_name><round_name>"
[(set (match_operand:V8SF 0 "register_operand" "=v")
(float_truncate:V8SF
- (match_operand:V8DF 1 "nonimmediate_operand" "vm")))]
+ (match_operand:V8DF 1 "nonimmediate_operand" "<round_constraint>")))]
"TARGET_AVX512F"
- "vcvtpd2ps\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vcvtpd2ps\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "V8SF")])
@@ -6695,28 +6739,28 @@
operands[1] = adjust_address (operands[1], DFmode, INTVAL (operands[2]) * 8);
})
-(define_insn "<mask_scalar_codefor>avx512f_vmscalef<mode><mask_scalar_name>"
+(define_insn "<mask_scalar_codefor>avx512f_vmscalef<mode><mask_scalar_name><round_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 "nonimmediate_operand" "vm")]
+ (match_operand:VF_128 2 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_SCALEF)
(match_dup 1)
(const_int 1)))]
"TARGET_AVX512F"
- "%vscalef<ssescalarmodesuffix>\t{%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %2}"
+ "%vscalef<ssescalarmodesuffix>\t{<round_mask_scalar_op3>%2, %1, %0<mask_scalar_operand3>|%0<mask_scalar_operand3>, %1, %2<round_mask_scalar_op3>}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<ssescalarmode>")])
-(define_insn "avx512f_scalef<mode><mask_name>"
+(define_insn "avx512f_scalef<mode><mask_name><round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(unspec:VF_512
[(match_operand:VF_512 1 "register_operand" "v")
- (match_operand:VF_512 2 "nonimmediate_operand" "vm")]
+ (match_operand:VF_512 2 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_SCALEF))]
"TARGET_AVX512F"
- "%vscalef<ssemodesuffix>\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ "%vscalef<ssemodesuffix>\t{<round_mask_op3>%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<round_mask_op3>}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
@@ -8446,22 +8490,22 @@
[(set_attr "prefix" "evex")
(set_attr "mode" "<sseinsnmode>")])
-(define_expand "<code><mode>3<mask_name>"
+(define_expand "<code><mode>3<mask_name><round_name>"
[(set (match_operand:VI124_256_48_512 0 "register_operand")
(maxmin:VI124_256_48_512
(match_operand:VI124_256_48_512 1 "nonimmediate_operand")
(match_operand:VI124_256_48_512 2 "nonimmediate_operand")))]
- "TARGET_AVX2 && <mask_mode512bit_condition>"
+ "TARGET_AVX2 && <mask_mode512bit_condition> && <round_mode512bit_condition>"
"ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
-(define_insn "*avx2_<code><mode>3<mask_name>"
+(define_insn "*avx2_<code><mode>3<mask_name><round_name>"
[(set (match_operand:VI124_256_48_512 0 "register_operand" "=v")
(maxmin:VI124_256_48_512
(match_operand:VI124_256_48_512 1 "nonimmediate_operand" "%v")
- (match_operand:VI124_256_48_512 2 "nonimmediate_operand" "vm")))]
+ (match_operand:VI124_256_48_512 2 "nonimmediate_operand" "<round_constraint>")))]
"TARGET_AVX2 && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)
- && <mask_mode512bit_condition>"
- "vp<maxmin_int><ssemodesuffix>\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
+ && <mask_mode512bit_condition> && <round_mode512bit_condition>"
+ "vp<maxmin_int><ssemodesuffix>\t{<round_mask_op3>%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<round_mask_op3>}"
[(set_attr "type" "sseiadd")
(set_attr "prefix_extra" "1")
(set_attr "prefix" "maybe_evex")
@@ -12743,33 +12787,33 @@
(set_attr "prefix" "evex")
(set_attr "mode" "XI")])
-(define_insn "avx512er_exp2<mode><mask_name>"
+(define_insn "avx512er_exp2<mode><mask_name><round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(unspec:VF_512
- [(match_operand:VF_512 1 "nonimmediate_operand" "vm")]
+ [(match_operand:VF_512 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_EXP2))]
"TARGET_AVX512ER"
- "vexp2<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vexp2<ssemodesuffix>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
-(define_insn "<mask_codefor>avx512er_rcp28<mode><mask_name>"
+(define_insn "<mask_codefor>avx512er_rcp28<mode><mask_name><round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(unspec:VF_512
- [(match_operand:VF_512 1 "nonimmediate_operand" "vm")]
+ [(match_operand:VF_512 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_RCP28))]
"TARGET_AVX512ER"
- "vrcp28<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vrcp28<ssemodesuffix>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
-(define_insn "<mask_codefor>avx512er_rsqrt28<mode><mask_name>"
+(define_insn "<mask_codefor>avx512er_rsqrt28<mode><mask_name><round_name>"
[(set (match_operand:VF_512 0 "register_operand" "=v")
(unspec:VF_512
- [(match_operand:VF_512 1 "nonimmediate_operand" "vm")]
+ [(match_operand:VF_512 1 "nonimmediate_operand" "<round_constraint>")]
UNSPEC_RSQRT28))]
"TARGET_AVX512ER"
- "vrsqrt28<ssemodesuffix>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+ "vrsqrt28<ssemodesuffix>\t{<round_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
[(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
diff --git a/gcc/config/i386/subst.md b/gcc/config/i386/subst.md
index f81741f..3e6e788 100644
--- a/gcc/config/i386/subst.md
+++ b/gcc/config/i386/subst.md
@@ -30,6 +30,16 @@
(define_mode_iterator SUBST_S
[QI HI SI DI])
+(define_mode_iterator SUBST_A
+ [V16QI
+ V16HI V8HI
+ V16SI V8SI V4SI
+ V8DI V4DI V2DI
+ V16SF V8SF V4SF
+ V8DF V4DF V2DF
+ QI HI SI DI SF DF
+ CCFP CCFPU])
+
(define_subst_attr "mask_name" "mask" "" "_mask")
(define_subst_attr "mask_applied" "mask" "false" "true")
(define_subst_attr "mask_operand2" "mask" "" "%{%3%}%N2")
@@ -110,3 +120,34 @@
(match_operand:SUBST_V 2 "const0_operand" "C")
(match_operand:<avx512fmaskmode> 3 "register_operand" "k")))
])
+
+(define_subst_attr "round_name" "round" "" "_round")
+(define_subst_attr "round_mask_operand2" "mask" "%R2" "%R4")
+(define_subst_attr "round_mask_operand3" "mask" "%R3" "%R5")
+(define_subst_attr "round_mask_scalar_operand3" "mask_scalar" "%R3" "%R5")
+(define_subst_attr "round_sd_mask_operand4" "sd" "%R4" "%R6")
+(define_subst_attr "round_op2" "round" "" "%R2")
+(define_subst_attr "round_op3" "round" "" "%R3")
+(define_subst_attr "round_op4" "round" "" "%R4")
+(define_subst_attr "round_op5" "round" "" "%R5")
+(define_subst_attr "round_op6" "round" "" "%R6")
+(define_subst_attr "round_mask_op2" "round" "" "<round_mask_operand2>")
+(define_subst_attr "round_mask_op3" "round" "" "<round_mask_operand3>")
+(define_subst_attr "round_mask_scalar_op3" "round" "" "<round_mask_scalar_operand3>")
+(define_subst_attr "round_sd_mask_op4" "round" "" "<round_sd_mask_operand4>")
+(define_subst_attr "round_constraint" "round" "vm" "v")
+(define_subst_attr "round_constraint2" "round" "m" "v")
+(define_subst_attr "round_constraint3" "round" "rm" "r")
+(define_subst_attr "round_mode512bit_condition" "round" "1" "(GET_MODE (operands[0]) == V16SFmode || GET_MODE (operands[0]) == V8DFmode)")
+(define_subst_attr "round_modev4sf_condition" "round" "1" "(GET_MODE (operands[0]) == V4SFmode)")
+(define_subst_attr "round_codefor" "round" "*" "")
+(define_subst_attr "round_opnum" "round" "5" "6")
+
+(define_subst "round"
+ [(set (match_operand:SUBST_A 0)
+ (match_operand:SUBST_A 1))]
+ "TARGET_AVX512F"
+ [(parallel[
+ (set (match_dup 0)
+ (match_dup 1))
+ (unspec [(match_operand:SI 2 "const_0_to_4_operand")] UNSPEC_EMBEDDED_ROUNDING)])])
More information about the Gcc-patches
mailing list