On Thu, Sep 13, 2012 at 07:42:17PM +0200, Uros Bizjak wrote:
> Can we introduce additional "*fmai_fmadd_<mode>_1" pattern (and
> others) that would cover missing 231 alternative?
Here is the patch for that. But, I don't see how it would ever match
(unless perhaps x is equal to z, but then the other insns could do the right
job too).
2012-09-13 Jakub Jelinek <ja...@redhat.com>
PR target/54564
* config/i386/sse.md (*fmai_fmadd_<mode>_1, *fmai_fmsub_<mode>_1,
*fmai_fnmadd_<mode>_1, *fmai_fnmsub_<mode>_1): New patterns.
--- gcc/config/i386/sse.md.jj 2012-09-13 19:58:42.000000000 +0200
+++ gcc/config/i386/sse.md 2012-09-13 20:07:15.181214004 +0200
@@ -2092,6 +2092,20 @@ (define_insn "*fmai_fmadd_<mode>"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
+(define_insn "*fmai_fmadd_<mode>_1"
+ [(set (match_operand:VF_128 0 "register_operand" "=x")
+ (vec_merge:VF_128
+ (fma:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "%x")
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm")
+ (match_operand:VF_128 3 "nonimmediate_operand" " 0"))
+ (match_dup 3)
+ (const_int 1)))]
+ "TARGET_FMA"
+ "vfmadd231<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "*fmai_fmsub_<mode>"
[(set (match_operand:VF_128 0 "register_operand" "=x,x")
(vec_merge:VF_128
@@ -2109,6 +2123,21 @@ (define_insn "*fmai_fmsub_<mode>"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
+(define_insn "*fmai_fmsub_<mode>_1"
+ [(set (match_operand:VF_128 0 "register_operand" "=x")
+ (vec_merge:VF_128
+ (fma:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "%x")
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm")
+ (neg:VF_128
+ (match_operand:VF_128 3 "nonimmediate_operand" " 0")))
+ (match_dup 3)
+ (const_int 1)))]
+ "TARGET_FMA"
+ "vfmsub231<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "*fmai_fnmadd_<mode>"
[(set (match_operand:VF_128 0 "register_operand" "=x,x")
(vec_merge:VF_128
@@ -2126,6 +2155,21 @@ (define_insn "*fmai_fnmadd_<mode>"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
+(define_insn "*fmai_fnmadd_<mode>_1"
+ [(set (match_operand:VF_128 0 "register_operand" "=x")
+ (vec_merge:VF_128
+ (fma:VF_128
+ (neg:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "%x"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm")
+ (match_operand:VF_128 3 "nonimmediate_operand" " 0"))
+ (match_dup 3)
+ (const_int 1)))]
+ "TARGET_FMA"
+ "vfnmadd231<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
(define_insn "*fmai_fnmsub_<mode>"
[(set (match_operand:VF_128 0 "register_operand" "=x,x")
(vec_merge:VF_128
@@ -2144,6 +2188,22 @@ (define_insn "*fmai_fnmsub_<mode>"
[(set_attr "type" "ssemuladd")
(set_attr "mode" "<MODE>")])
+(define_insn "*fmai_fnmsub_<mode>_1"
+ [(set (match_operand:VF_128 0 "register_operand" "=x")
+ (vec_merge:VF_128
+ (fma:VF_128
+ (neg:VF_128
+ (match_operand:VF_128 1 "nonimmediate_operand" "%x"))
+ (match_operand:VF_128 2 "nonimmediate_operand" "xm")
+ (neg:VF_128
+ (match_operand:VF_128 3 "nonimmediate_operand" " 0")))
+ (match_dup 3)
+ (const_int 1)))]
+ "TARGET_FMA"
+ "vfnmsub231<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "ssemuladd")
+ (set_attr "mode" "<MODE>")])
+
;; FMA4 floating point scalar intrinsics. These write the
;; entire destination register, with the high-order elements zeroed.
Jakub
