diff mbox

[i386] : Fix PR41484, Please add memory forms of pmovzx* (SSE4.1)

Message ID AANLkTimZGTumC6ByjD0FuaKjnZAHKKGD1Zz5HfAaFg-R@mail.gmail.com
State New
Headers show

Commit Message

Uros Bizjak Aug. 27, 2010, 4:58 p.m. UTC 
Hello!

As said in the PR:

This patch removes special (vec_duplicate ...) forms of zero/sign extension
instructions. This is similar to existing sse2_cvtps2pd pattern that access
full 128bit memory even if only low 64bits are used.

Also, current gcc generates:

        movdqa  (%rdi), %xmm0   # 6     *movv16qi_internal/2    [length = 4]
        pmovzxbd        %xmm0, %xmm0    # 7     sse4_1_zero_extendv4qiv4si2

which also access full 128bit 16byte aligned value. This is no better than:

        pmovzxbd        (%rdi), %xmm0   # 7     sse4_1_zero_extendv4qiv4si2

2010-08-27  Uros Bizjak  <ubizjak@gmail.com>

	PR target/41484
	* config/i386/sse.md (sse4_1_extendv8qiv8hi2): Also accept memory
	operands for operand 1.
	(sse4_1_extendv4qiv4si2): Ditto.
	(sse4_1_extendv2qiv2di2): Ditto.
	(sse4_1_extendv4hiv4si2): Ditto.
	(sse4_1_extendv2hiv2di2): Ditto.
	(sse4_1_extendv2siv2di2): Ditto.
	(sse4_1_zero_extendv8qiv8hi2): Ditto.
	(sse4_1_zero_extendv4qiv4si2): Ditto.
	(sse4_1_zero_extendv2qiv2di2): Ditto.
	(sse4_1_zero_extendv4hiv4si2): Ditto.
	(sse4_1_zero_extendv2hiv2di2): Ditto.
	(sse4_1_zero_extendv2siv2di2): Ditto.
	(*sse4_1_extendv8qiv8hi2): Remove insn pattern.
	(*sse4_1_extendv4qiv4si2): Ditto.
	(*sse4_1_extendv2qiv2di2): Ditto.
	(*sse4_1_extendv4hiv4si2): Ditto.
	(*sse4_1_extendv2hiv2di2): Ditto.
	(*sse4_1_extendv2siv2di2): Ditto.
	(*sse4_1_zero_extendv8qiv8hi2): Ditto.
	(*sse4_1_zero_extendv4qiv4si2): Ditto.
	(*sse4_1_zero_extendv2qiv2di2): Ditto.
	(*sse4_1_zero_extendv4hiv4si2): Ditto.
	(*sse4_1_zero_extendv2hiv2di2): Ditto.
	(*sse4_1_zero_extendv2siv2di2): Ditto.

Patch was bootstrapped on x86_64-pc-linux-gnu and regression tested by
H.J. on sse4.1 capable target.  Patch was committed to mainline, will
be backported to 4.4 and 4.5 branch.

Uros.
diff mbox

Patch

Index: sse.md
===================================================================
--- sse.md	(revision 163580)
+++ sse.md	(working copy)
@@ -9596,7 +9596,7 @@ 
   [(set (match_operand:V8HI 0 "register_operand" "=x")
 	(sign_extend:V8HI
 	  (vec_select:V8QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9612,32 +9612,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv8qiv8hi2"
-  [(set (match_operand:V8HI 0 "register_operand" "=x")
-	(sign_extend:V8HI
-	  (vec_select:V8QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V8QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)
-		       (const_int 4)
-		       (const_int 5)
-		       (const_int 6)
-		       (const_int 7)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxbw\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_extendv4qiv4si2"
   [(set (match_operand:V4SI 0 "register_operand" "=x")
 	(sign_extend:V4SI
 	  (vec_select:V4QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9649,28 +9628,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv4qiv4si2"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(sign_extend:V4SI
-	  (vec_select:V4QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V4QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxbd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_extendv2qiv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(sign_extend:V2DI
 	  (vec_select:V2QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9680,26 +9642,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv2qiv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(sign_extend:V2DI
-	  (vec_select:V2QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V2QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxbq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_extendv4hiv4si2"
   [(set (match_operand:V4SI 0 "register_operand" "=x")
 	(sign_extend:V4SI
 	  (vec_select:V4HI
-	    (match_operand:V8HI 1 "register_operand" "x")
+	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9711,28 +9658,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv4hiv4si2"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(sign_extend:V4SI
-	  (vec_select:V4HI
-	    (vec_duplicate:V8HI
-	      (match_operand:V2HI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxwd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_extendv2hiv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(sign_extend:V2DI
 	  (vec_select:V2HI
-	    (match_operand:V8HI 1 "register_operand" "x")
+	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9742,26 +9672,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv2hiv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(sign_extend:V2DI
-	  (vec_select:V2HI
-	    (vec_duplicate:V8HI
-	      (match_operand:V8HI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxwq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_extendv2siv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(sign_extend:V2DI
 	  (vec_select:V2SI
-	    (match_operand:V4SI 1 "register_operand" "x")
+	    (match_operand:V4SI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9771,26 +9686,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_extendv2siv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(sign_extend:V2DI
-	  (vec_select:V2SI
-	    (vec_duplicate:V4SI
-	      (match_operand:V2SI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovsxdq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv8qiv8hi2"
   [(set (match_operand:V8HI 0 "register_operand" "=x")
 	(zero_extend:V8HI
 	  (vec_select:V8QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9806,32 +9706,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv8qiv8hi2"
-  [(set (match_operand:V8HI 0 "register_operand" "=x")
-	(zero_extend:V8HI
-	  (vec_select:V8QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V8QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)
-		       (const_int 4)
-		       (const_int 5)
-		       (const_int 6)
-		       (const_int 7)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxbw\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv4qiv4si2"
   [(set (match_operand:V4SI 0 "register_operand" "=x")
 	(zero_extend:V4SI
 	  (vec_select:V4QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9843,28 +9722,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv4qiv4si2"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(zero_extend:V4SI
-	  (vec_select:V4QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V4QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxbd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv2qiv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(zero_extend:V2DI
 	  (vec_select:V2QI
-	    (match_operand:V16QI 1 "register_operand" "x")
+	    (match_operand:V16QI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9874,26 +9736,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv2qiv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(zero_extend:V2DI
-	  (vec_select:V2QI
-	    (vec_duplicate:V16QI
-	      (match_operand:V2QI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxbq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv4hiv4si2"
   [(set (match_operand:V4SI 0 "register_operand" "=x")
 	(zero_extend:V4SI
 	  (vec_select:V4HI
-	    (match_operand:V8HI 1 "register_operand" "x")
+	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)
 		       (const_int 2)
@@ -9905,28 +9752,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv4hiv4si2"
-  [(set (match_operand:V4SI 0 "register_operand" "=x")
-	(zero_extend:V4SI
-	  (vec_select:V4HI
-	    (vec_duplicate:V8HI
-	      (match_operand:V4HI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)
-		       (const_int 2)
-		       (const_int 3)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxwd\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv2hiv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(zero_extend:V2DI
 	  (vec_select:V2HI
-	    (match_operand:V8HI 1 "register_operand" "x")
+	    (match_operand:V8HI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9936,26 +9766,11 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv2hiv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(zero_extend:V2DI
-	  (vec_select:V2HI
-	    (vec_duplicate:V8HI
-	      (match_operand:V2HI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxwq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 (define_insn "sse4_1_zero_extendv2siv2di2"
   [(set (match_operand:V2DI 0 "register_operand" "=x")
 	(zero_extend:V2DI
 	  (vec_select:V2SI
-	    (match_operand:V4SI 1 "register_operand" "x")
+	    (match_operand:V4SI 1 "nonimmediate_operand" "xm")
 	    (parallel [(const_int 0)
 		       (const_int 1)]))))]
   "TARGET_SSE4_1"
@@ -9965,21 +9780,6 @@ 
    (set_attr "prefix" "maybe_vex")
    (set_attr "mode" "TI")])
 
-(define_insn "*sse4_1_zero_extendv2siv2di2"
-  [(set (match_operand:V2DI 0 "register_operand" "=x")
-	(zero_extend:V2DI
-	  (vec_select:V2SI
-	    (vec_duplicate:V4SI
-	      (match_operand:V2SI 1 "nonimmediate_operand" "xm"))
-	    (parallel [(const_int 0)
-		       (const_int 1)]))))]
-  "TARGET_SSE4_1"
-  "%vpmovzxdq\t{%1, %0|%0, %1}"
-  [(set_attr "type" "ssemov")
-   (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "maybe_vex")
-   (set_attr "mode" "TI")])
-
 ;; ptestps/ptestpd are very similar to comiss and ucomiss when
 ;; setting FLAGS_REG. But it is not a really compare instruction.
 (define_insn "avx_vtest<ssemodesuffix><avxmodesuffix>"