amdgcn: Don't clobber VCC if we don't need to

This is a hold-over from GCN3 where v_add always wrote to the condition
register, whether you wanted it or not.  This hasn't been true since GCN5, and
we dropped support for GCN3 a little while ago, so let's fix it.

There was actually a latent bug here because some other post-reload splitters
were generating v_add instructions without declaring the VCC clobber (at least
mul did this), so this should fix some wrong-code bugs also.

gcc/ChangeLog:

	* config/gcn/gcn-valu.md (add<mode>3<exec_clobber>): Rename ...
	(add<mode>3<exec>): ... to this, remove the clobber, and change the
	instruction from v_add_co_u32 to v_add_u32.
	(add<mode>3_dup<exec_clobber>): Rename ...
	(add<mode>3_dup<exec>): ... to this, and likewise.
	(sub<mode>3<exec_clobber>): Rename ...
	(sub<mode>3<exec>): ... to this, and likewise
	* config/gcn/gcn.md (addsi3): Remove the DI clobber, and change the
	instruction from v_add_co_u32 to v_add_u32.
	(addsi3_scc): Likewise.
	(subsi3): Likewise, but for v_sub_co_u32.
	(muldi3): Likewise.

diff --git a/gcc/config/gcn/gcn-valu.md b/gcc/config/gcn/gcn-valu.md
index 4b21302e82c2a8a781b32447508830ff8a2f8ce2..f49c1ed0b6dea5b62b8de3c4a7c5f9a2b2ac6057 100644 (file)
--- a/gcc/config/gcn/gcn-valu.md
+++ b/gcc/config/gcn/gcn-valu.md
@@ -1455,28 +1455,26 @@
 ;; }}}
 ;; {{{ ALU special case: add/sub
 
-(define_insn "add<mode>3<exec_clobber>"
+(define_insn "add<mode>3<exec>"
   [(set (match_operand:V_INT_1REG 0 "register_operand")
        (plus:V_INT_1REG
          (match_operand:V_INT_1REG 1 "register_operand")
-         (match_operand:V_INT_1REG 2 "gcn_alu_operand")))
-   (clobber (reg:DI VCC_REG))]
+         (match_operand:V_INT_1REG 2 "gcn_alu_operand")))]
   ""
   {@ [cons: =0, %1, 2; attrs: type, length]
-  [v,v,vSvA;vop2,4] v_add_co_u32\t%0, vcc, %2, %1
+  [v,v,vSvA;vop2,4] {v_add_u32|v_add_nc_u32}\t%0, %2, %1
   [v,v,vSvB;vop2,8] ^
   })
 
-(define_insn "add<mode>3_dup<exec_clobber>"
+(define_insn "add<mode>3_dup<exec>"
   [(set (match_operand:V_INT_1REG 0 "register_operand")
        (plus:V_INT_1REG
          (vec_duplicate:V_INT_1REG
            (match_operand:<SCALAR_MODE> 2 "gcn_alu_operand"))
-         (match_operand:V_INT_1REG 1 "register_operand")))
-   (clobber (reg:DI VCC_REG))]
+         (match_operand:V_INT_1REG 1 "register_operand")))]
   ""
   {@ [cons: =0, 1, 2; attrs: type, length]
-  [v,v,SvA;vop2,4] v_add_co_u32\t%0, vcc, %2, %1
+  [v,v,SvA;vop2,4] {v_add_u32|v_add_nc_u32}\t%0, %2, %1
   [v,v,SvB;vop2,8] ^
   })
 
@@ -1551,16 +1549,15 @@
   [(set_attr "type" "vop2,vop3b")
    (set_attr "length" "4,8")])
 
-(define_insn "sub<mode>3<exec_clobber>"
+(define_insn "sub<mode>3<exec>"
   [(set (match_operand:V_INT_1REG 0 "register_operand"  "=  v,   v")
        (minus:V_INT_1REG
          (match_operand:V_INT_1REG 1 "gcn_alu_operand" "vSvB,   v")
-         (match_operand:V_INT_1REG 2 "gcn_alu_operand" "   v,vSvB")))
-   (clobber (reg:DI VCC_REG))]
+         (match_operand:V_INT_1REG 2 "gcn_alu_operand" "   v,vSvB")))]
   ""
   "@
-   v_sub_co_u32\t%0, vcc, %1, %2
-   v_subrev_co_u32\t%0, vcc, %2, %1"
+   {v_sub_u32|v_sub_nc_u32}\t%0, %1, %2
+   {v_subrev_u32|v_subrev_nc_u32}\t%0, %2, %1"
   [(set_attr "type" "vop2")
    (set_attr "length" "8,8")])
 

diff --git a/gcc/config/gcn/gcn.md b/gcc/config/gcn/gcn.md
index 2ce2e054fbf0a7b478142977f45d38843e6ee5e0..9193461ed49a7396f1cdde1933a5cced5fe7b1f4 100644 (file)
--- a/gcc/config/gcn/gcn.md
+++ b/gcc/config/gcn/gcn.md
@@ -1136,14 +1136,13 @@
   [(set (match_operand:SI 0 "register_operand"         "= Sg, Sg, Sg,   v")
         (plus:SI (match_operand:SI 1 "gcn_alu_operand" "%SgA,  0,SgA,   v")
                 (match_operand:SI 2 "gcn_alu_operand" " SgA,SgJ,  B,vBSv")))
-   (clobber (match_scratch:BI 3                               "= cs, cs, cs,   X"))
-   (clobber (match_scratch:DI 4                               "=  X,  X,  X,  cV"))]
+   (clobber (match_scratch:BI 3                               "= cs, cs, cs,   X"))]
   ""
   "@
    s_add_i32\t%0, %1, %2
    s_addk_i32\t%0, %2
    s_add_i32\t%0, %1, %2
-   v_add_co_u32\t%0, vcc, %2, %1"
+   {v_add_u32|v_add_nc_u32}\t%0, %2, %1"
   [(set_attr "type" "sop2,sopk,sop2,vop2")
    (set_attr "length" "4,4,8,8")])
 
@@ -1151,8 +1150,7 @@
   [(parallel [(set (match_operand:SI 0 "register_operand")
                   (plus:SI (match_operand:SI 1 "gcn_alu_operand")
                            (match_operand:SI 2 "gcn_alu_operand")))
-             (clobber (reg:BI SCC_REG))
-             (clobber (scratch:DI))])]
+             (clobber (reg:BI SCC_REG))])]
   ""
   {})
 
@@ -1332,14 +1330,13 @@
   [(set (match_operand:SI 0 "register_operand"          "=Sg, Sg,    v,   v")
        (minus:SI (match_operand:SI 1 "gcn_alu_operand" "SgA,SgA,    v,vBSv")
                  (match_operand:SI 2 "gcn_alu_operand" "SgA,  B, vBSv,   v")))
-   (clobber (match_scratch:BI 3                                "=cs, cs,    X,   X"))
-   (clobber (match_scratch:DI 4                                "= X,  X,   cV,  cV"))]
+   (clobber (match_scratch:BI 3                                "=cs, cs,    X,   X"))]
   ""
   "@
    s_sub_i32\t%0, %1, %2
    s_sub_i32\t%0, %1, %2
-   v_subrev_co_u32\t%0, vcc, %2, %1
-   v_sub_co_u32\t%0, vcc, %1, %2"
+   {v_subrev_u32|v_subrev_nc_u32}\t%0, %2, %1
+   {v_sub_u32|v_sub_nc_u32}\t%0, %1, %2"
   [(set_attr "type" "sop2,sop2,vop2,vop2")
    (set_attr "length" "4,8,8,8")])
 
@@ -1569,8 +1566,7 @@
        (mult:DI (match_operand:DI 1 "register_operand" "%Sg, Sg,  v, v")
                 (match_operand:DI 2 "nonmemory_operand" "Sg,  i,vSv, A")))
    (clobber (match_scratch:SI 3 "=&Sg,&Sg,&v,&v"))
-   (clobber (match_scratch:BI 4  "=cs, cs, X, X"))
-   (clobber (match_scratch:DI 5   "=X,  X,cV,cV"))]
+   (clobber (match_scratch:BI 4  "=cs, cs, X, X"))]
   ""
   "#"
   "reload_completed"
@@ -1585,15 +1581,13 @@
     emit_insn (gen_umulsidi3 (operands[0], op1lo, op2lo));
     emit_insn (gen_mulsi3 (tmp, op1lo, op2hi));
     rtx add = gen_rtx_SET (dsthi, gen_rtx_PLUS (SImode, dsthi, tmp));
-    rtx clob1 = gen_rtx_CLOBBER (VOIDmode, operands[4]);
-    rtx clob2 = gen_rtx_CLOBBER (VOIDmode, operands[5]);
-    add = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (3, add, clob1, clob2));
+    rtx clob = gen_rtx_CLOBBER (VOIDmode, operands[4]);
+    add = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (2, add, clob));
     emit_insn (add);
     emit_insn (gen_mulsi3 (tmp, op1hi, op2lo));
     add = gen_rtx_SET (dsthi, gen_rtx_PLUS (SImode, dsthi, tmp));
-    clob1 = gen_rtx_CLOBBER (VOIDmode, operands[4]);
-    clob2 = gen_rtx_CLOBBER (VOIDmode, operands[5]);
-    add = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (3, add, clob1, clob2));
+    clob = gen_rtx_CLOBBER (VOIDmode, operands[4]);
+    add = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (2, add, clob));
     emit_insn (add);
     DONE;
   })