[llvm] [AMDGPU] Update pal metadata for v3.6 (PR #135196)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Apr 10 08:07:27 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: David Stuttard (dstutt)
<details>
<summary>Changes</summary>
Update entry_point for all pal versions below 3.6
3.6 and above removes entry_point
---
Full diff: https://github.com/llvm/llvm-project/pull/135196.diff
12 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp (+11-7)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-cs.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-es.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-gs.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-ls.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal-vs.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/amdpal.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/elf-notes.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll (+4-4)
- (added) llvm/test/CodeGen/AMDGPU/pal-metadata-3.6.ll (+213)
- (modified) llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll (+1-1)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
index cdd6cb8fdd6fc..247371f27d5ef 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
@@ -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
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-cs.ll b/llvm/test/CodeGen/AMDGPU/amdpal-cs.ll
index 96775f4763e34..d06f397c00d77 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-cs.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-cs.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-es.ll b/llvm/test/CodeGen/AMDGPU/amdpal-es.ll
index 1379246c32573..fce918cb3e49a 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-es.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-es.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-gs.ll b/llvm/test/CodeGen/AMDGPU/amdpal-gs.ll
index 1fba34a50094f..02a235345cee1 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-gs.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-gs.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-ls.ll b/llvm/test/CodeGen/AMDGPU/amdpal-ls.ll
index ebe753134a42d..0897489231a53 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-ls.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-ls.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll b/llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll
index 32f19e2af32ec..a289e04ebcb0c 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-vs.ll b/llvm/test/CodeGen/AMDGPU/amdpal-vs.ll
index 853d221ee3aab..77456962a4ea0 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal-vs.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-vs.ll
@@ -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:
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal.ll b/llvm/test/CodeGen/AMDGPU/amdpal.ll
index fd9227d2f4319..2e47b0163aa8c 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal.ll
@@ -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
diff --git a/llvm/test/CodeGen/AMDGPU/elf-notes.ll b/llvm/test/CodeGen/AMDGPU/elf-notes.ll
index b205678bd9085..22d699a8f4809 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-notes.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-notes.ll
@@ -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
diff --git a/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll
index 5748f6b188acf..01d0ca6767d5e 100644
--- a/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll
+++ b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.ll
@@ -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
@@ -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
@@ -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
@@ -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
diff --git a/llvm/test/CodeGen/AMDGPU/pal-metadata-3.6.ll b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.6.ll
new file mode 100644
index 0000000000000..baff6660f42cd
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/pal-metadata-3.6.ll
@@ -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
+}
+
+ at 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
+}
+
+ at 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"}
+!1 = !{i32 7}
diff --git a/llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll b/llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll
index fdc1e6abb051f..a798dc158a8f4 100644
--- a/llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll
+++ b/llvm/test/CodeGen/AMDGPU/wave_dispatch_regs.ll
@@ -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
``````````
</details>
https://github.com/llvm/llvm-project/pull/135196
More information about the llvm-commits
mailing list