AMDGPU/SI: Add latency for export instructions

[nhaehnle]

LGTM

llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td

class EXPCommon : InstSI<
   (outs),
   (ins i32imm:$en, i32imm:$tgt, i32imm:$compr, i32imm:$done, i32imm:$vm,
        VGPR_32:$src0, VGPR_32:$src1, VGPR_32:$src2, VGPR_32:$src3),
   "exp $en, $tgt, $compr, $done, $vm, $src0, $src1, $src2, $src3",
   [] > {
 
   let EXP_CNT = 1;
   let Uses = [EXEC];
+  let SchedRW = [WriteExport];
 }
 
 multiclass EXP_m {
 
   let isPseudo = 1, isCodeGenOnly = 1 in {
     def "" : EXPCommon, SIMCInstr <"exp", SISubtarget.NONE> ;
   }
 

llvm/trunk/test/CodeGen/AMDGPU/ret.ll

define amdgpu_vs {float, float} @vgpr([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
   call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %3, float %3, float %3, float %3)
   %x = fadd float %3, 1.0
   %a = insertvalue {float, float} undef, float %x, 0
   %b = insertvalue {float, float} %a, float %3, 1
   ret {float, float} %b
 }
 
 ; GCN-LABEL: {{^}}vgpr_literal:
-; GCN: v_mov_b32_e32 v4, v0
+; GCN: exp 15, 0, 1, 1, 1, v0, v0, v0, v0
+; GCN: s_waitcnt expcnt(0)
 ; GCN-DAG: v_mov_b32_e32 v0, 1.0
 ; GCN-DAG: v_mov_b32_e32 v1, 2.0
 ; GCN-DAG: v_mov_b32_e32 v2, 4.0
 ; GCN-DAG: v_mov_b32_e32 v3, -1.0
-; GCN: exp 15, 0, 1, 1, 1, v4, v4, v4, v4
-; GCN: s_waitcnt expcnt(0)
 ; GCN-NOT: s_endpgm
 define amdgpu_vs {float, float, float, float} @vgpr_literal([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
   call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %3, float %3, float %3, float %3)
   ret {float, float, float, float} {float 1.0, float 2.0, float 4.0, float -1.0}
 }
 
 
 ; GCN: .long 165580
define amdgpu_vs {float, i32, float, i32, i32} @both([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
   %a2 = insertvalue {float, i32, float, i32, i32} %a1, float %3, 2
   %a3 = insertvalue {float, i32, float, i32, i32} %a2, i32 %1, 3
   %a4 = insertvalue {float, i32, float, i32, i32} %a3, i32 %2, 4
   ret {float, i32, float, i32, i32} %a4
 }
 
 
 ; GCN-LABEL: {{^}}structure_literal:
-; GCN: v_mov_b32_e32 v3, v0
+; GCN: exp 15, 0, 1, 1, 1, v0, v0, v0, v0
+; GCN: s_waitcnt expcnt(0)
 ; GCN-DAG: v_mov_b32_e32 v0, 1.0
 ; GCN-DAG: s_mov_b32 s0, 2
 ; GCN-DAG: s_mov_b32 s1, 3
 ; GCN-DAG: v_mov_b32_e32 v1, 2.0
 ; GCN-DAG: v_mov_b32_e32 v2, 4.0
-; GCN-DAG: exp 15, 0, 1, 1, 1, v3, v3, v3, v3
 define amdgpu_vs {{float, i32}, {i32, <2 x float>}} @structure_literal([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
   call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %3, float %3, float %3, float %3)
   ret {{float, i32}, {i32, <2 x float>}} {{float, i32} {float 1.0, i32 2}, {i32, <2 x float>} {i32 3, <2 x float> <float 2.0, float 4.0>}}
 }