[llvm] [AMDGPU] Emit backend_stack_size PAL metadata (PR #72509)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Nov 16 04:45:40 PST 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Diana (rovka)
<details>
<summary>Changes</summary>
For chain functions, PAL uses a `backend_stack_size` metadata item, which at the moment has the same meaning as `stack_frame_size_in_bytes`. We emit both for now in order to simplify coordination with PAL.
The new item must be emitted in the `shader_functions` section, just as the metadata for other module entry functions. For simplicity, we mark chain functions as module entry functions and emit the same metadata for all of them.
---
Full diff: https://github.com/llvm/llvm-project/pull/72509.diff
4 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp (+1-1)
- (modified) llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp (+1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-callable.ll (+15)
- (added) llvm/test/CodeGen/AMDGPU/amdpal-chain-metadata.ll (+31)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
index a09abc639d7590f..fdc59281c50d0b3 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -1910,7 +1910,7 @@ bool isModuleEntryFunctionCC(CallingConv::ID CC) {
case CallingConv::AMDGPU_Gfx:
return true;
default:
- return isEntryFunctionCC(CC);
+ return isEntryFunctionCC(CC) || isChainCC(CC);
}
}
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
index 278341944c52305..48d0bde139d7728 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
@@ -244,6 +244,7 @@ void AMDGPUPALMetadata::setScratchSize(CallingConv::ID CC, unsigned Val) {
void AMDGPUPALMetadata::setFunctionScratchSize(StringRef FnName, unsigned Val) {
auto Node = getShaderFunction(FnName);
Node[".stack_frame_size_in_bytes"] = MsgPackDoc.getNode(Val);
+ Node[".backend_stack_size"] = MsgPackDoc.getNode(Val);
}
// Set the amount of LDS used in bytes in the metadata.
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-callable.ll b/llvm/test/CodeGen/AMDGPU/amdpal-callable.ll
index 0061c0a3118ad94..b7b2cb22c1b6269 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-callable.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-callable.ll
@@ -146,12 +146,14 @@ attributes #0 = { nounwind }
; GCN-NEXT: 0x2e13 (COMPUTE_PGM_RSRC2): 0x8001{{$}}
; GCN-NEXT: .shader_functions:
; GCN-NEXT: dynamic_stack:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x28{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x10{{$}}
; SDAG-NEXT: .vgpr_count: 0x2{{$}}
; GISEL-NEXT: .vgpr_count: 0x3{{$}}
; GCN-NEXT: dynamic_stack_loop:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; SDAG-NEXT: .sgpr_count: 0x25{{$}}
; GISEL-NEXT: .sgpr_count: 0x26{{$}}
@@ -159,71 +161,84 @@ attributes #0 = { nounwind }
; SDAG-NEXT: .vgpr_count: 0x3{{$}}
; GISEL-NEXT: .vgpr_count: 0x4{{$}}
; GCN-NEXT: multiple_stack:
+; GCN-NEXT: .backend_stack_size: 0x24{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x21{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x24{{$}}
; GCN-NEXT: .vgpr_count: 0x3{{$}}
; GCN-NEXT: no_stack:
+; GCN-NEXT: .backend_stack_size: 0{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x20{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0{{$}}
; GCN-NEXT: .vgpr_count: 0x1{{$}}
; GCN-NEXT: no_stack_call:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x25{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x10{{$}}
; GCN-NEXT: .vgpr_count: 0x3{{$}}
; GCN-NEXT: no_stack_extern_call:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GFX8-NEXT: .sgpr_count: 0x28{{$}}
; GFX9-NEXT: .sgpr_count: 0x2c{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x10{{$}}
; GCN-NEXT: .vgpr_count: 0x2b{{$}}
; GCN-NEXT: no_stack_extern_call_many_args:
+; GCN-NEXT: .backend_stack_size: 0x90{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GFX8-NEXT: .sgpr_count: 0x28{{$}}
; GFX9-NEXT: .sgpr_count: 0x2c{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x90{{$}}
; GCN-NEXT: .vgpr_count: 0x2b{{$}}
; GCN-NEXT: no_stack_indirect_call:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GFX8-NEXT: .sgpr_count: 0x28{{$}}
; GFX9-NEXT: .sgpr_count: 0x2c{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x10{{$}}
; GCN-NEXT: .vgpr_count: 0x2b{{$}}
; GCN-NEXT: simple_lds:
+; GCN-NEXT: .backend_stack_size: 0{{$}}
; GCN-NEXT: .lds_size: 0x100{{$}}
; GCN-NEXT: .sgpr_count: 0x20{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0{{$}}
; GCN-NEXT: .vgpr_count: 0x1{{$}}
; GCN-NEXT: simple_lds_recurse:
+; GCN-NEXT: .backend_stack_size: 0x10{{$}}
; GCN-NEXT: .lds_size: 0x100{{$}}
; GCN-NEXT: .sgpr_count: 0x28{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x10{{$}}
; GCN-NEXT: .vgpr_count: 0x29{{$}}
; GCN-NEXT: simple_stack:
+; GCN-NEXT: .backend_stack_size: 0x14{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x21{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x14{{$}}
; GCN-NEXT: .vgpr_count: 0x2{{$}}
; GCN-NEXT: simple_stack_call:
+; GCN-NEXT: .backend_stack_size: 0x20{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x25{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x20{{$}}
; GCN-NEXT: .vgpr_count: 0x4{{$}}
; GCN-NEXT: simple_stack_extern_call:
+; GCN-NEXT: .backend_stack_size: 0x20{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GFX8-NEXT: .sgpr_count: 0x28{{$}}
; GFX9-NEXT: .sgpr_count: 0x2c{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x20{{$}}
; GCN-NEXT: .vgpr_count: 0x2b{{$}}
; GCN-NEXT: simple_stack_indirect_call:
+; GCN-NEXT: .backend_stack_size: 0x20{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GFX8-NEXT: .sgpr_count: 0x28{{$}}
; GFX9-NEXT: .sgpr_count: 0x2c{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x20{{$}}
; GCN-NEXT: .vgpr_count: 0x2b{{$}}
; GCN-NEXT: simple_stack_recurse:
+; GCN-NEXT: .backend_stack_size: 0x20{{$}}
; GCN-NEXT: .lds_size: 0{{$}}
; GCN-NEXT: .sgpr_count: 0x28{{$}}
; GCN-NEXT: .stack_frame_size_in_bytes: 0x20{{$}}
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-chain-metadata.ll b/llvm/test/CodeGen/AMDGPU/amdpal-chain-metadata.ll
new file mode 100644
index 000000000000000..044abe15c5d8cdd
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-chain-metadata.ll
@@ -0,0 +1,31 @@
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1100 <%s | FileCheck %s
+
+; CHECK-LABEL: {{^}}amdgpu_cs_chain_func:
+; CHECK: .amdgpu_pal_metadata
+; CHECK-NEXT: ---
+; CHECK-NEXT: amdpal.pipelines:
+; CHECK-NEXT: - .api: Vulkan
+; CHECK: .shader_functions:
+; CHECK-NEXT: amdgpu_cs_chain_func:
+; CHECK: .backend_stack_size: 0x10{{$}}
+; CHECK: .stack_frame_size_in_bytes: 0x10{{$}}
+; CHECK:amdpal.version:
+; CHECK-NEXT: - 0x3
+; CHECK-NEXT: - 0
+; CHECK-NEXT:...
+; CHECK-NEXT: .end_amdgpu_pal_metadata
+
+define amdgpu_cs_chain void @amdgpu_cs_chain_func(<40 x i32> %should_spill) {
+.entry:
+ %v = alloca [3 x i32], addrspace(5)
+ store i32 42, ptr addrspace(5) %v
+ call amdgpu_gfx void @use(<40 x i32> %should_spill, ptr addrspace(5) %v)
+ ret void
+}
+
+declare amdgpu_gfx void @use(...)
+
+!amdgpu.pal.metadata.msgpack = !{!0}
+
+!0 = !{!"\82\B0amdpal.pipelines\91\8A\A4.api\A6Vulkan\B2.compute_registers\85\AB.tg_size_en\C3\AA.tgid_x_en\C2\AA.tgid_y_en\C2\AA.tgid_z_en\C2\AF.tidig_comp_cnt\01\B0.hardware_stages\81\A3.cs\8C\AF.checksum_value\CE\94D\D7\D0\AB.debug_mode\00\AB.float_mode\CC\C0\A9.image_op\C2\AC.mem_ordered\C3\AB.sgpr_limitj\B7.threadgroup_dimensions\93\01\CD\04\00\01\AD.trap_present\00\B2.user_data_reg_map\DC\00 \CE\10\00\00\00\CE\FF\FF\FF\FF\00\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\CE\FF\FF\FF\FF\AB.user_sgprs\03\AB.vgpr_limit\CD\01\00\AF.wavefront_size@\B7.internal_pipeline_hash\92\CF\E7\10k\A6:\A6%\F7\CF\B2\1F\1A\D4{\DA\E1T\AA.registers\80\A8.shaders\81\A8.compute\82\B0.api_shader_hash\92\CF\E9Zn7}\1E\B9\E7\00\B1.hardware_mapping\91\A3.cs\B0.spill_threshold\CE\FF\FF\FF\FF\A5.type\A2Cs\B0.user_data_limit\01\AF.xgl_cache_info\82\B3.128_bit_cache_hash\92\CF\B4X\B8\11[\A4\88P\CF\A0;\B0\AF\FF\B4\BE\C0\AD.llpc_version\A461.1\AEamdpal.version\92\03\00"}
+!1 = !{i32 7}
``````````
</details>
https://github.com/llvm/llvm-project/pull/72509
More information about the llvm-commits
mailing list