[llvm] r303859 - [AMDGPU] add intrinsic for s_getpc

[Tim Corringham via llvm-commits]

Author: timcorringham
Date: Thu May 25 09:04:14 2017
New Revision: 303859

URL: http://llvm.org/viewvc/llvm-project?rev=303859&view=rev
Log:
[AMDGPU] add intrinsic for s_getpc

Summary: The s_getpc instruction is exposed as intrinsic llvm.amdgcn.s.getpc.

Reviewers: arsenm

Reviewed By: arsenm

Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye

Differential Revision: https://reviews.llvm.org/D32862

Added:
    llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll
Modified:
    llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td
    llvm/trunk/lib/Target/AMDGPU/SOPInstructions.td

Modified: llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td?rev=303859&r1=303858&r2=303859&view=diff
==============================================================================
--- llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td (original)
+++ llvm/trunk/include/llvm/IR/IntrinsicsAMDGPU.td Thu May 25 09:04:14 2017
@@ -566,6 +566,16 @@ def int_amdgcn_s_getreg :
   [IntrReadMem, IntrSpeculatable]
 >;
 
+// int_amdgcn_s_getpc is provided to allow a specific style of position
+// independent code to determine the high part of its address when it is
+// known (through convention) that the code and any data of interest does
+// not cross a 4Gb address boundary. Use for any other purpose may not
+// produce the desired results as optimizations may cause code movement,
+// especially as we explicitly use IntrNoMem to allow optimizations.
+def int_amdgcn_s_getpc :
+  GCCBuiltin<"__builtin_amdgcn_s_getpc">,
+  Intrinsic<[llvm_i64_ty], [], [IntrNoMem, IntrSpeculatable]>;
+
 // __builtin_amdgcn_interp_mov <param>, <attr_chan>, <attr>, <m0>
 // param values: 0 = P10, 1 = P20, 2 = P0
 def int_amdgcn_interp_mov :

Modified: llvm/trunk/lib/Target/AMDGPU/SOPInstructions.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SOPInstructions.td?rev=303859&r1=303858&r2=303859&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SOPInstructions.td (original)
+++ llvm/trunk/lib/Target/AMDGPU/SOPInstructions.td Thu May 25 09:04:14 2017
@@ -184,7 +184,9 @@ def S_BITSET0_B32 : SOP1_32    <"s_bitse
 def S_BITSET0_B64 : SOP1_64_32 <"s_bitset0_b64">;
 def S_BITSET1_B32 : SOP1_32    <"s_bitset1_b32">;
 def S_BITSET1_B64 : SOP1_64_32 <"s_bitset1_b64">;
-def S_GETPC_B64 : SOP1_64_0  <"s_getpc_b64">;
+def S_GETPC_B64 : SOP1_64_0  <"s_getpc_b64",
+  [(set i64:$sdst, (int_amdgcn_s_getpc))]
+>;
 
 let isTerminator = 1, isBarrier = 1, SchedRW = [WriteBranch] in {
 

Added: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll?rev=303859&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll (added)
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll Thu May 25 09:04:14 2017
@@ -0,0 +1,15 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+declare i64 @llvm.amdgcn.s.getpc() #0
+
+; GCN-LABEL: {{^}}test_s_getpc:
+; GCN: s_load_dwordx2
+; GCN-DAG: s_getpc_b64 s{{\[[0-9]+:[0-9]+\]}}
+; GCN: buffer_store_dwordx2
+define void @test_s_getpc(i64 addrspace(1)* %out) #0 {
+  %tmp = call i64 @llvm.amdgcn.s.getpc() #1
+  store volatile i64 %tmp, i64 addrspace(1)* %out, align 8
+  ret void
+}
+
+attributes #0 = { nounwind readnone speculatable }