[PATCH] D97670: [AMDGPU] New intrinsic void llvm.amdgcn.s.sethalt(i32)

[Jay Foad via Phabricator via llvm-commits]

foad created this revision.
foad added reviewers: dstuttard, piotr, rampitec, arsenm.
Herald added subscribers: kerbowa, hiraditya, t-tye, tpr, yaxunl, nhaehnle, jvesely, kzhuravl.
foad requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

The expected use case is for frontends to insert this into
shaders that are to be run under a debugger. The shader can
then be resumed or single stepped from the point of the call
under debugger control.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D97670

Files:
  llvm/include/llvm/IR/IntrinsicsAMDGPU.td
  llvm/lib/Target/AMDGPU/SOPInstructions.td
  llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll


Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll
@@ -0,0 +1,28 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -global-isel < %s | FileCheck -check-prefix=GCN %s
+
+define amdgpu_kernel void @test_s_sethalt() {
+; GCN-LABEL: test_s_sethalt:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_sethalt 0
+; GCN-NEXT:    s_sethalt 1
+; GCN-NEXT:    s_sethalt 2
+; GCN-NEXT:    s_sethalt 3
+; GCN-NEXT:    s_sethalt 4
+; GCN-NEXT:    s_sethalt 5
+; GCN-NEXT:    s_sethalt 6
+; GCN-NEXT:    s_sethalt 7
+; GCN-NEXT:    s_endpgm
+  call void @llvm.amdgcn.s.sethalt(i32 0)
+  call void @llvm.amdgcn.s.sethalt(i32 1)
+  call void @llvm.amdgcn.s.sethalt(i32 2)
+  call void @llvm.amdgcn.s.sethalt(i32 3)
+  call void @llvm.amdgcn.s.sethalt(i32 4)
+  call void @llvm.amdgcn.s.sethalt(i32 5)
+  call void @llvm.amdgcn.s.sethalt(i32 6)
+  call void @llvm.amdgcn.s.sethalt(i32 7)
+  ret void
+}
+
+declare void @llvm.amdgcn.s.sethalt(i32)
Index: llvm/lib/Target/AMDGPU/SOPInstructions.td
===================================================================
--- llvm/lib/Target/AMDGPU/SOPInstructions.td
+++ llvm/lib/Target/AMDGPU/SOPInstructions.td
@@ -1228,7 +1228,8 @@
 let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
 def S_WAITCNT : SOPP_Pseudo <"s_waitcnt" , (ins WAIT_FLAG:$simm16), "$simm16",
     [(int_amdgcn_s_waitcnt timm:$simm16)]>;
-def S_SETHALT : SOPP_Pseudo <"s_sethalt" , (ins i16imm:$simm16), "$simm16">;
+def S_SETHALT : SOPP_Pseudo <"s_sethalt" , (ins i32imm:$simm16), "$simm16",
+    [(int_amdgcn_s_sethalt timm:$simm16)]>;
 def S_SETKILL : SOPP_Pseudo <"s_setkill" , (ins i16imm:$simm16), "$simm16">;
 
 // On SI the documentation says sleep for approximately 64 * low 2
Index: llvm/include/llvm/IR/IntrinsicsAMDGPU.td
===================================================================
--- llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -1283,6 +1283,10 @@
                                 IntrHasSideEffects, IntrWillReturn]> {
 }
 
+def int_amdgcn_s_sethalt :
+  Intrinsic<[], [llvm_i32_ty], [ImmArg<ArgIndex<0>>, IntrNoMem,
+                                IntrHasSideEffects, IntrWillReturn]>;
+
 def int_amdgcn_s_getreg :
   GCCBuiltin<"__builtin_amdgcn_s_getreg">,
   Intrinsic<[llvm_i32_ty], [llvm_i32_ty],


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D97670.327057.patch
Type: text/x-patch
Size: 2598 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210301/7083db49/attachment.bin>