[llvm] 796a60d - [AMDGPU] New intrinsic void llvm.amdgcn.s.sethalt(i32)
Jay Foad via llvm-commits
llvm-commits at lists.llvm.org
Mon Mar 1 06:30:31 PST 2021
Author: Jay Foad
Date: 2021-03-01T14:30:23Z
New Revision: 796a60d2ea32320f298f91beb04f015934598821
URL: https://github.com/llvm/llvm-project/commit/796a60d2ea32320f298f91beb04f015934598821
DIFF: https://github.com/llvm/llvm-project/commit/796a60d2ea32320f298f91beb04f015934598821.diff
LOG: [AMDGPU] New intrinsic void llvm.amdgcn.s.sethalt(i32)
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.
Differential Revision: https://reviews.llvm.org/D97670
Added:
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll
Modified:
llvm/include/llvm/IR/IntrinsicsAMDGPU.td
llvm/lib/Target/AMDGPU/SOPInstructions.td
Removed:
################################################################################
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 088aadcfad25..d122aca33143 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -1283,6 +1283,10 @@ def int_amdgcn_s_decperflevel :
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],
diff --git a/llvm/lib/Target/AMDGPU/SOPInstructions.td b/llvm/lib/Target/AMDGPU/SOPInstructions.td
index 50725dea2e15..115aff6cc7f8 100644
--- a/llvm/lib/Target/AMDGPU/SOPInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SOPInstructions.td
@@ -1228,7 +1228,8 @@ def S_WAKEUP : SOPP_Pseudo <"s_wakeup", (ins) > {
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
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.sethalt.ll
new file mode 100644
index 000000000000..bc2900aa2661
--- /dev/null
+++ b/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 -global-isel -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %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)
More information about the llvm-commits
mailing list