Skip to content

[AMDGPU] Update pal metadata for v3.6 and fix v3.0 #135196

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Apr 28, 2025
Merged

[AMDGPU] Update pal metadata for v3.6 and fix v3.0 #135196

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2b30dc7
[AMDGPU] Update pal metadata for v3.6
dstutt Apr 10, 2025
83f642f
Address review comments
dstutt Apr 15, 2025
b843008
Address review comments 2
dstutt Apr 28, 2025
380e422
Address reviewer comments 3
dstutt Apr 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 11 additions & 7 deletions llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,13 +259,17 @@ void AMDGPUPALMetadata::setEntryPoint(unsigned CC, StringRef Name) {
getHwStage(CC)[".entry_point_symbol"] =
MsgPackDoc.getNode(Name, /*Copy=*/true);

// Set .entry_point which is defined
// to be _amdgpu_<stage> and _amdgpu_cs for non-shader functions
SmallString<16> EPName("_amdgpu_");
raw_svector_ostream EPNameOS(EPName);
EPNameOS << getStageName(CC) + 1;
getHwStage(CC)[".entry_point"] =
MsgPackDoc.getNode(EPNameOS.str(), /*Copy=*/true);
// For pal version 3.6 and above, entry_point is no longer required
if (getPALMajorVersion() < 3 ||
(getPALMajorVersion() == 3 && getPALMinorVersion() < 6)) {
// Set .entry_point which is defined
// to be _amdgpu_<stage>_main and _amdgpu_cs_main for non-shader functions
SmallString<16> EPName("_amdgpu_");
raw_svector_ostream EPNameOS(EPName);
EPNameOS << getStageName(CC) + 1 << "_main";
getHwStage(CC)[".entry_point"] =
MsgPackDoc.getNode(EPNameOS.str(), /*Copy=*/true);
}
}

// Set the number of used vgprs in the metadata. This is an optional
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-cs.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .cs:
; GCN-NEXT: .entry_point: _amdgpu_cs
; GCN-NEXT: .entry_point: _amdgpu_cs_main
; GCN-NEXT: .entry_point_symbol: cs_amdpal
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-es.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .es:
; GCN-NEXT: .entry_point: _amdgpu_es
; GCN-NEXT: .entry_point: _amdgpu_es_main
; GCN-NEXT: .entry_point_symbol: es_amdpal
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-gs.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .gs:
; GCN-NEXT: .entry_point: _amdgpu_gs
; GCN-NEXT: .entry_point: _amdgpu_gs_main
; GCN-NEXT: .entry_point_symbol: gs_amdpal
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-ls.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .ls:
; GCN-NEXT: .entry_point: _amdgpu_ls
; GCN-NEXT: .entry_point: _amdgpu_ls_main
; GCN-NEXT: .entry_point_symbol: ls_amdpal
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .ps:
; GCN-NEXT: .entry_point: _amdgpu_ps
; GCN-NEXT: .entry_point: _amdgpu_ps_main
; GCN-NEXT: .entry_point_symbol: amdpal_psenable
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal-vs.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .vs:
; GCN-NEXT: .entry_point: _amdgpu_vs
; GCN-NEXT: .entry_point: _amdgpu_vs_main
; GCN-NEXT: .entry_point_symbol: vs_amdpal
; GCN-NEXT: .scratch_memory_size: 0
; GCN: .registers:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/amdpal.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ declare void @llvm.amdgcn.raw.ptr.buffer.store.f32(float, ptr addrspace(8), i32,
; PAL-NEXT: amdpal.pipelines:
; PAL-NEXT: - .hardware_stages:
; PAL-NEXT: .cs:
; PAL-NEXT: .entry_point: _amdgpu_cs
; PAL-NEXT: .entry_point: _amdgpu_cs_main
; PAL-NEXT: .entry_point_symbol: scratch2_cs
; PAL-NEXT: .scratch_memory_size: 0x10
; PAL-NEXT: .sgpr_count: 0x
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/elf-notes.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@
; OSABI-PAL-ELF: amdpal.pipelines:
; OSABI-PAL-ELF: - .hardware_stages:
; OSABI-PAL-ELF: .cs:
; OSABI-PAL-ELF: .entry_point: _amdgpu_cs
; OSABI-PAL-ELF: .entry_point: _amdgpu_cs_main
; OSABI-PAL-ELF: .entry_point_symbol: elf_notes
; OSABI-PAL-ELF: .scratch_memory_size: 0
; OSABI-PAL-ELF: .sgpr_count: 96
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@
; CHECK-NEXT: .checksum_value: 0x9444d7d0
; CHECK-NEXT: .debug_mode: false
; DVGPR-NEXT: .dynamic_vgpr_saved_count: 0x70
; CHECK-NEXT: .entry_point: _amdgpu_cs
; CHECK-NEXT: .entry_point: _amdgpu_cs_main
; CHECK-NEXT: .entry_point_symbol: _amdgpu_cs_main
; CHECK-NEXT: .excp_en: 0
; CHECK-NEXT: .float_mode: 0xc0
Expand Down Expand Up @@ -116,7 +116,7 @@
; CHECK-NEXT: .wgp_mode: false
; CHECK-NEXT: .gs:
; CHECK-NEXT: .debug_mode: false
; CHECK-NEXT: .entry_point: _amdgpu_gs
; CHECK-NEXT: .entry_point: _amdgpu_gs_main
; CHECK-NEXT: .entry_point_symbol: gs_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0x200
Expand All @@ -128,7 +128,7 @@
; CHECK-NEXT: .wgp_mode: true
; CHECK-NEXT: .hs:
; CHECK-NEXT: .debug_mode: false
; CHECK-NEXT: .entry_point: _amdgpu_hs
; CHECK-NEXT: .entry_point: _amdgpu_hs_main
; CHECK-NEXT: .entry_point_symbol: hs_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0x1000
Expand All @@ -140,7 +140,7 @@
; CHECK-NEXT: .wgp_mode: true
; CHECK-NEXT: .ps:
; CHECK-NEXT: .debug_mode: false
; CHECK-NEXT: .entry_point: _amdgpu_ps
; CHECK-NEXT: .entry_point: _amdgpu_ps_main
; CHECK-NEXT: .entry_point_symbol: ps_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0
Expand Down
213 changes: 213 additions & 0 deletions llvm/test/CodeGen/AMDGPU/pal-metadata-3.6.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,213 @@
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1100 <%s | FileCheck %s --check-prefixes=CHECK,GFX11,NODVGPR
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 <%s | FileCheck %s --check-prefixes=CHECK,NODVGPR
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1200 -mattr=+dynamic-vgpr <%s | FileCheck %s --check-prefixes=CHECK,DVGPR

; CHECK-LABEL: {{^}}_amdgpu_cs_main:
; NODVGPR: ; TotalNumSgprs: 4
; DVGPR: ; TotalNumSgprs: 34
; CHECK: ; NumVgprs: 2
; CHECK: .amdgpu_pal_metadata
; CHECK-NEXT: ---
; CHECK-NEXT: amdpal.pipelines:
; CHECK-NEXT: - .api: Vulkan
; CHECK-NEXT: .compute_registers:
; DVGPR-NEXT: .dynamic_vgpr_en: true
; CHECK-NEXT: .tg_size_en: true
; CHECK-NEXT: .tgid_x_en: false
; CHECK-NEXT: .tgid_y_en: false
; CHECK-NEXT: .tgid_z_en: false
; CHECK-NEXT: .tidig_comp_cnt: 0x1
; CHECK-NEXT: .graphics_registers:
; CHECK-NEXT: .ps_extra_lds_size: 0
; CHECK-NEXT: .spi_ps_input_addr:
; CHECK-NEXT: .ancillary_ena: false
; CHECK-NEXT: .front_face_ena: true
; CHECK-NEXT: .line_stipple_tex_ena: false
; CHECK-NEXT: .linear_center_ena: true
; CHECK-NEXT: .linear_centroid_ena: true
; CHECK-NEXT: .linear_sample_ena: true
; CHECK-NEXT: .persp_center_ena: true
; CHECK-NEXT: .persp_centroid_ena: true
; CHECK-NEXT: .persp_pull_model_ena: false
; CHECK-NEXT: .persp_sample_ena: true
; CHECK-NEXT: .pos_fixed_pt_ena: true
; CHECK-NEXT: .pos_w_float_ena: false
; CHECK-NEXT: .pos_x_float_ena: false
; CHECK-NEXT: .pos_y_float_ena: false
; CHECK-NEXT: .pos_z_float_ena: false
; CHECK-NEXT: .sample_coverage_ena: false
; CHECK-NEXT: .spi_ps_input_ena:
; CHECK-NEXT: .ancillary_ena: false
; CHECK-NEXT: .front_face_ena: false
; CHECK-NEXT: .line_stipple_tex_ena: false
; CHECK-NEXT: .linear_center_ena: false
; CHECK-NEXT: .linear_centroid_ena: false
; CHECK-NEXT: .linear_sample_ena: false
; CHECK-NEXT: .persp_center_ena: false
; CHECK-NEXT: .persp_centroid_ena: false
; CHECK-NEXT: .persp_pull_model_ena: false
; CHECK-NEXT: .persp_sample_ena: true
; CHECK-NEXT: .pos_fixed_pt_ena: false
; CHECK-NEXT: .pos_w_float_ena: false
; CHECK-NEXT: .pos_x_float_ena: false
; CHECK-NEXT: .pos_y_float_ena: false
; CHECK-NEXT: .pos_z_float_ena: false
; CHECK-NEXT: .sample_coverage_ena: false
; CHECK-NEXT: .hardware_stages:
; CHECK-NEXT: .cs:
; CHECK-NEXT: .checksum_value: 0x9444d7d0
; CHECK-NEXT: .debug_mode: false
; DVGPR-NEXT: .dynamic_vgpr_saved_count: 0x70
; CHECK-NOT: .entry_point: _amdgpu_cs_main
; CHECK-NEXT: .entry_point_symbol: _amdgpu_cs_main
; CHECK-NEXT: .excp_en: 0
; CHECK-NEXT: .float_mode: 0xc0
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .image_op: false
; CHECK-NEXT: .lds_size: 0
; CHECK-NEXT: .mem_ordered: true
; CHECK-NEXT: .scratch_en: false
; CHECK-NEXT: .scratch_memory_size: 0
; NODVGPR-NEXT: .sgpr_count: 0x4
; DVGPR-NEXT: .sgpr_count: 0x22
; CHECK-NEXT: .sgpr_limit: 0x6a
; CHECK-NEXT: .threadgroup_dimensions:
; CHECK-NEXT: - 0x1
; CHECK-NEXT: - 0x400
; CHECK-NEXT: - 0x1
; CHECK-NEXT: .trap_present: false
; CHECK-NEXT: .user_data_reg_map:
; CHECK-NEXT: - 0x10000000
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: - 0xffffffff
; CHECK-NEXT: .user_sgprs: 0x3
; CHECK-NEXT: .vgpr_count: 0x2
; CHECK-NEXT: .vgpr_limit: 0x100
; CHECK-NEXT: .wavefront_size: 0x40
; CHECK-NEXT: .wgp_mode: false
; CHECK-NEXT: .gs:
; CHECK-NEXT: .debug_mode: false
; CHECK-NOT: .entry_point: _amdgpu_gs_main
; CHECK-NEXT: .entry_point_symbol: gs_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0x200
; CHECK-NEXT: .mem_ordered: true
; CHECK-NEXT: .scratch_en: false
; CHECK-NEXT: .scratch_memory_size: 0
; CHECK-NEXT: .sgpr_count: 0x1
; CHECK-NEXT: .vgpr_count: 0x1
; CHECK-NEXT: .wgp_mode: true
; CHECK-NEXT: .hs:
; CHECK-NEXT: .debug_mode: false
; CHECK-NOT: .entry_point: _amdgpu_hs_main
; CHECK-NEXT: .entry_point_symbol: hs_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0x1000
; CHECK-NEXT: .mem_ordered: true
; CHECK-NEXT: .scratch_en: false
; CHECK-NEXT: .scratch_memory_size: 0
; CHECK-NEXT: .sgpr_count: 0x1
; CHECK-NEXT: .vgpr_count: 0x1
; CHECK-NEXT: .wgp_mode: true
; CHECK-NEXT: .ps:
; CHECK-NEXT: .debug_mode: false
; CHECK-NOT: .entry_point: _amdgpu_ps_main
; CHECK-NEXT: .entry_point_symbol: ps_shader
; GFX11-NEXT: .ieee_mode: false
; CHECK-NEXT: .lds_size: 0
; CHECK-NEXT: .mem_ordered: true
; CHECK-NEXT: .scratch_en: false
; CHECK-NEXT: .scratch_memory_size: 0
; CHECK-NEXT: .sgpr_count: 0x1
; CHECK-NEXT: .vgpr_count: 0x1
; CHECK-NEXT: .wgp_mode: true
; CHECK: .registers: {}
; CHECK:amdpal.version:
; CHECK-NEXT: - 0x3
; CHECK-NEXT: - 0x6
; CHECK-NEXT:...
; CHECK-NEXT: .end_amdgpu_pal_metadata

define dllexport amdgpu_cs void @_amdgpu_cs_main(i32 inreg %arg1, i32 %arg2) #0 !lgc.shaderstage !1 {
.entry:
%i = call i64 @llvm.amdgcn.s.getpc()
%i1 = and i64 %i, -4294967296
%i2 = zext i32 %arg1 to i64
%i3 = or i64 %i1, %i2
%i4 = inttoptr i64 %i3 to ptr addrspace(4)
%i5 = and i32 %arg2, 1023
%i6 = lshr i32 %arg2, 10
%i7 = and i32 %i6, 1023
%i8 = add nuw nsw i32 %i7, %i5
%i9 = load <4 x i32>, ptr addrspace(4) %i4, align 16
%.idx = shl nuw nsw i32 %i8, 2
call void @llvm.amdgcn.raw.buffer.store.i32(i32 1, <4 x i32> %i9, i32 %.idx, i32 0, i32 0)
ret void
}

define dllexport amdgpu_ps void @ps_shader() #1 {
ret void
}

@LDS.GS = external addrspace(3) global [1 x i32], align 4

define dllexport amdgpu_gs void @gs_shader() #2 {
%ptr = getelementptr i32, ptr addrspace(3) @LDS.GS, i32 0
store i32 0, ptr addrspace(3) %ptr, align 4
ret void
}

@LDS.HS = external addrspace(3) global [1024 x i32], align 4

define dllexport amdgpu_hs void @hs_shader() #2 {
%ptr = getelementptr i32, ptr addrspace(3) @LDS.HS, i32 0
store i32 0, ptr addrspace(3) %ptr, align 4
ret void
}

!amdgpu.pal.metadata.msgpack = !{!0}

; Function Attrs: nounwind willreturn memory(none)
declare ptr addrspace(7) @lgc.buffer.desc.to.ptr(<4 x i32>) #1

; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
declare i64 @llvm.amdgcn.s.getpc() #2

; Function Attrs: nocallback nofree nosync nounwind willreturn memory(write)
declare void @llvm.amdgcn.raw.buffer.store.i32(i32, <4 x i32>, i32, i32, i32 immarg) #3

attributes #0 = { nounwind memory(readwrite) "amdgpu-flat-work-group-size"="1024,1024" "amdgpu-memory-bound"="false" "amdgpu-unroll-threshold"="700" "amdgpu-wave-limiter"="false" "amdgpu-work-group-info-arg-no"="4" "denormal-fp-math-f32"="preserve-sign" "target-features"=",+wavefrontsize64,+cumode" }

attributes #1 = { nounwind memory(readwrite) "InitialPSInputAddr"="36983" }

!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\06"}
Copy link
Contributor

@jayfoad jayfoad Apr 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This can be reduced to: !0 = !{!"\81\AEamdpal.version\92\03\06"}

In future I wonder if we should have a command line argument as a more readable way of specifying what PAL metadata version we want the compiler to generate? Also I wonder if it should always default to generating the latest supported version?

Copy link
Collaborator Author

@dstutt dstutt Apr 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd prefer the leave the metadata as-is for this test. It's more representative of what the front end would pass in.

!1 = !{i32 7}
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
; GCN-NEXT: amdpal.pipelines:
; GCN-NEXT: - .hardware_stages:
; GCN-NEXT: .cs:
; GCN-NEXT: .entry_point: _amdgpu_cs
; GCN-NEXT: .entry_point: _amdgpu_cs_main
; GCN-NEXT: .entry_point_symbol: _amdgpu_cs_main
; GCN-NEXT: .scratch_memory_size: 0
; SI-NEXT: .sgpr_count: 0x11
Expand Down