[i386] : Introduce uavg<mode>3_ceil for 64bit MMX modes
diff mbox series

Message ID CAFULd4adCWuy9=vxpRPZRWH3Ty_25ChTqwtv=7dwGjNmMZXeGA@mail.gmail.com
State New
Headers show
Series
  • [i386] : Introduce uavg<mode>3_ceil for 64bit MMX modes
Related show

Commit Message

Uros Bizjak Aug. 16, 2019, 2:32 p.m. UTC
Attached patch introduces uavg<mode>3_ceil for V8QI and V4HI modes for
TARGET_MMX_WITH_SSE targets.  Also, the patch fixes invalid RTX
generation for SSE and AVX uavg<mode>3 patterns.

2019-08-16  UroŇ° Bizjak  <ubizjak@gmail.com>

    * config/i386/mmx.md (mmxdoublemode): New mode attribute.
    (mmx_uavg<mode>3): Macroize expaner from mmx_uavgv8qi3 and
    mmx_uavgv4hi3 using MMXMODE12 mode iterator.
    (uavg<mode>3_ceil): New expander.
    * config/i386/sse.md (uavg<mode>3_ceil): Use ssedoublemode
    mode iterator when creating CONST1_RTX.
    (<sse2_avx2>_uavg<mode>3<mask_name>): Ditto.
    (*<sse2_avx2>_uavg<mode>3<mask_name>): Use ssedoublemode
    mode iterator for const1_operand predicate.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Committed to mainline SVN.

Uros.

Patch
diff mbox series

Index: config/i386/mmx.md
===================================================================
--- config/i386/mmx.md	(revision 274564)
+++ config/i386/mmx.md	(working copy)
@@ -58,6 +58,9 @@ 
 ;; Mapping from integer vector mode to mnemonic suffix
 (define_mode_attr mmxvecsize [(V8QI "b") (V4HI "w") (V2SI "d") (V1DI "q")])
 
+(define_mode_attr mmxdoublemode
+  [(V8QI "V8HI") (V4HI "V4SI")])
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
 ;; Move patterns
@@ -1948,24 +1951,24 @@ 
 ;;
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-(define_expand "mmx_uavgv8qi3"
-  [(set (match_operand:V8QI 0 "register_operand")
-	(truncate:V8QI
-	  (lshiftrt:V8HI
-	    (plus:V8HI
-	      (plus:V8HI
-		(zero_extend:V8HI
-		  (match_operand:V8QI 1 "register_mmxmem_operand"))
-		(zero_extend:V8HI
-		  (match_operand:V8QI 2 "register_mmxmem_operand")))
-	      (const_vector:V8HI [(const_int 1) (const_int 1)
-				  (const_int 1) (const_int 1)
-				  (const_int 1) (const_int 1)
-				  (const_int 1) (const_int 1)]))
+(define_expand "mmx_uavg<mode>3"
+  [(set (match_operand:MMXMODE12 0 "register_operand")
+	(truncate:MMXMODE12
+	  (lshiftrt:<mmxdoublemode>
+	    (plus:<mmxdoublemode>
+	      (plus:<mmxdoublemode>
+		(zero_extend:<mmxdoublemode>
+		  (match_operand:MMXMODE12 1 "register_mmxmem_operand"))
+		(zero_extend:<mmxdoublemode>
+		  (match_operand:MMXMODE12 2 "register_mmxmem_operand")))
+	      (match_dup 3))
 	    (const_int 1))))]
   "(TARGET_MMX || TARGET_MMX_WITH_SSE)
    && (TARGET_SSE || TARGET_3DNOW)"
-  "ix86_fixup_binary_operands_no_copy (PLUS, V8QImode, operands);")
+{
+  operands[3] = CONST1_RTX(<mmxdoublemode>mode);
+  ix86_fixup_binary_operands_no_copy (PLUS, <MODE>mode, operands);
+})
 
 (define_insn "*mmx_uavgv8qi3"
   [(set (match_operand:V8QI 0 "register_operand" "=y,x,Yv")
@@ -1984,7 +1987,7 @@ 
 	    (const_int 1))))]
   "(TARGET_MMX || TARGET_MMX_WITH_SSE)
    && (TARGET_SSE || TARGET_3DNOW)
-   && ix86_binary_operator_ok (PLUS, V8QImode, operands)"
+   && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
 {
   switch (which_alternative)
     {
@@ -2013,23 +2016,6 @@ 
        (const_string "*")))
    (set_attr "mode" "DI,TI,TI")])
 
-(define_expand "mmx_uavgv4hi3"
-  [(set (match_operand:V4HI 0 "register_operand")
-	(truncate:V4HI
-	  (lshiftrt:V4SI
-	    (plus:V4SI
-	      (plus:V4SI
-		(zero_extend:V4SI
-		  (match_operand:V4HI 1 "register_mmxmem_operand"))
-		(zero_extend:V4SI
-		  (match_operand:V4HI 2 "register_mmxmem_operand")))
-	      (const_vector:V4SI [(const_int 1) (const_int 1)
-				  (const_int 1) (const_int 1)]))
-	    (const_int 1))))]
-  "(TARGET_MMX || TARGET_MMX_WITH_SSE)
-   && (TARGET_SSE || TARGET_3DNOW_A)"
-  "ix86_fixup_binary_operands_no_copy (PLUS, V4HImode, operands);")
-
 (define_insn "*mmx_uavgv4hi3"
   [(set (match_operand:V4HI 0 "register_operand" "=y,x,Yv")
 	(truncate:V4HI
@@ -2045,7 +2031,7 @@ 
 	    (const_int 1))))]
   "(TARGET_MMX || TARGET_MMX_WITH_SSE)
    && (TARGET_SSE || TARGET_3DNOW_A)
-   && ix86_binary_operator_ok (PLUS, V4HImode, operands)"
+   && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
   "@
    pavgw\t{%2, %0|%0, %2}
    pavgw\t{%2, %0|%0, %2}
@@ -2055,6 +2041,24 @@ 
    (set_attr "type" "mmxshft,sseiadd,sseiadd")
    (set_attr "mode" "DI,TI,TI")])
 
+(define_expand "uavg<mode>3_ceil"
+  [(set (match_operand:MMXMODE12 0 "register_operand")
+	(truncate:MMXMODE12
+	  (lshiftrt:<mmxdoublemode>
+	    (plus:<mmxdoublemode>
+	      (plus:<mmxdoublemode>
+		(zero_extend:<mmxdoublemode>
+		  (match_operand:MMXMODE12 1 "register_operand"))
+		(zero_extend:<mmxdoublemode>
+		  (match_operand:MMXMODE12 2 "register_operand")))
+	      (match_dup 3))
+	    (const_int 1))))]
+  "TARGET_MMX_WITH_SSE"
+{
+  operands[3] = CONST1_RTX(<mmxdoublemode>mode);
+  ix86_fixup_binary_operands_no_copy (PLUS, <MODE>mode, operands);
+})
+
 (define_insn "mmx_psadbw"
   [(set (match_operand:V1DI 0 "register_operand" "=y,x,Yv")
         (unspec:V1DI [(match_operand:V8QI 1 "register_operand" "0,0,Yv")
Index: config/i386/sse.md
===================================================================
--- config/i386/sse.md	(revision 274564)
+++ config/i386/sse.md	(working copy)
@@ -11900,7 +11900,7 @@ 
 	    (const_int 1))))]
   "TARGET_SSE2"
 {
-  operands[3] = CONST1_RTX(<MODE>mode);
+  operands[3] = CONST1_RTX(<ssedoublemode>mode);
   ix86_fixup_binary_operands_no_copy (PLUS, <MODE>mode, operands);
 })
 
@@ -15641,7 +15641,7 @@ 
 	    (const_int 1))))]
   "TARGET_SSE2 && <mask_mode512bit_condition> && <mask_avx512bw_condition>"
 {
-  operands[<mask_expand_op3>] = CONST1_RTX(<MODE>mode);
+  operands[<mask_expand_op3>] = CONST1_RTX(<ssedoublemode>mode);
   ix86_fixup_binary_operands_no_copy (PLUS, <MODE>mode, operands);
 })
 
@@ -15655,7 +15655,7 @@ 
 		  (match_operand:VI12_AVX2 1 "vector_operand" "%0,v"))
 		(zero_extend:<ssedoublemode>
 		  (match_operand:VI12_AVX2 2 "vector_operand" "xBm,vm")))
-	      (match_operand:VI12_AVX2 <mask_expand_op3> "const1_operand"))
+	      (match_operand:<ssedoublemode> <mask_expand_op3> "const1_operand"))
 	    (const_int 1))))]
   "TARGET_SSE2 && <mask_mode512bit_condition> && <mask_avx512bw_condition>
    && !(MEM_P (operands[1]) && MEM_P (operands[2]))"