Skip to content

[AMDGPU] Mark cluster_workgroup_id_* intrinsics always uniform #159439

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

Jump to bottom
Merged
merged 1 commit into from
Sep 17, 2025
Merged

[AMDGPU] Mark cluster_workgroup_id_* intrinsics always uniform #159439

merged 1 commit into from
Sep 17, 2025

Conversation

rampitec
Copy link
Collaborator

No description provided.

@rampitec rampitec requested a review from shiltian September 17, 2025 19:54
@rampitec Graphite App
Copy link
Collaborator Author

This stack of pull requests is managed by Graphite. Learn more about stacking.

@rampitec rampitec marked this pull request as ready for review September 17, 2025 19:54
@llvmbot llvmbot added backend:AMDGPU llvm:analysis Includes value tracking, cost tables and constant folding labels Sep 17, 2025
@llvmbot
Copy link
Member

llvmbot commented Sep 17, 2025

@llvm/pr-subscribers-backend-amdgpu

Author: Stanislav Mekhanoshin (rampitec)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/159439.diff

2 Files Affected:

  • (modified) llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td (+8)
  • (modified) llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll (+72)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
index 7be18998ff6b0..2393346839707 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
@@ -398,6 +398,14 @@ def : AlwaysUniform<int_amdgcn_icmp>;
 def : AlwaysUniform<int_amdgcn_fcmp>;
 def : AlwaysUniform<int_amdgcn_ballot>;
 def : AlwaysUniform<int_amdgcn_if_break>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_x>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_y>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_z>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_flat_id>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_x>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_y>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_z>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_flat_id>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_x>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_y>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_z>;
diff --git a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
index 99d9e28425107..9ff670bee0f89 100644
--- a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
+++ b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
@@ -119,6 +119,70 @@ define void @s_getreg(ptr addrspace(1) inreg %out) {
   ret void
 }
 
+; CHECK-LABEL: for function 'cluster_workgroup_id_x':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_x(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.x()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_id_y':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_y(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.y()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_id_z':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_z(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.z()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_flat_id':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_flat_id(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.flat.id()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_x':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_x(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.x()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_y':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_y(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.y()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_z':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_z(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.z()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_flat_id':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_flat_id(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.flat.id()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
 ; CHECK-LABEL: for function 's_memtime':
 ; CHECK: ALL VALUES UNIFORM
 define void @s_memtime(ptr addrspace(1) inreg %out) {
@@ -144,6 +208,14 @@ declare i64 @llvm.amdgcn.ballot.i32(i1) #1
 declare i32 @llvm.amdgcn.workgroup.id.x() #0
 declare i32 @llvm.amdgcn.workgroup.id.y() #0
 declare i32 @llvm.amdgcn.workgroup.id.z() #0
+declare i32 @llvm.amdgcn.cluster.workgroup.id.x()
+declare i32 @llvm.amdgcn.cluster.workgroup.id.y()
+declare i32 @llvm.amdgcn.cluster.workgroup.id.z()
+declare i32 @llvm.amdgcn.cluster.workgroup.flat.id()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.x()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.y()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.z()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.flat.id()
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind readnone convergent }

@llvmbot
Copy link
Member

llvmbot commented Sep 17, 2025

@llvm/pr-subscribers-llvm-analysis

Author: Stanislav Mekhanoshin (rampitec)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/159439.diff

2 Files Affected:

  • (modified) llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td (+8)
  • (modified) llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll (+72)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
index 7be18998ff6b0..2393346839707 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
@@ -398,6 +398,14 @@ def : AlwaysUniform<int_amdgcn_icmp>;
 def : AlwaysUniform<int_amdgcn_fcmp>;
 def : AlwaysUniform<int_amdgcn_ballot>;
 def : AlwaysUniform<int_amdgcn_if_break>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_x>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_y>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_id_z>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_flat_id>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_x>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_y>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_id_z>;
+def : AlwaysUniform<int_amdgcn_cluster_workgroup_max_flat_id>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_x>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_y>;
 def : AlwaysUniform<int_amdgcn_workgroup_id_z>;
diff --git a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
index 99d9e28425107..9ff670bee0f89 100644
--- a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
+++ b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/always_uniform.ll
@@ -119,6 +119,70 @@ define void @s_getreg(ptr addrspace(1) inreg %out) {
   ret void
 }
 
+; CHECK-LABEL: for function 'cluster_workgroup_id_x':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_x(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.x()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_id_y':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_y(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.y()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_id_z':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_id_z(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.id.z()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_flat_id':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_flat_id(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.flat.id()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_x':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_x(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.x()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_y':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_y(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.y()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_id_z':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_id_z(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.id.z()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: for function 'cluster_workgroup_max_flat_id':
+; CHECK: ALL VALUES UNIFORM
+define void @cluster_workgroup_max_flat_id(ptr addrspace(1) inreg %out) {
+  %result = call i32 @llvm.amdgcn.cluster.workgroup.max.flat.id()
+  store i32 %result, ptr addrspace(1) %out, align 4
+  ret void
+}
+
 ; CHECK-LABEL: for function 's_memtime':
 ; CHECK: ALL VALUES UNIFORM
 define void @s_memtime(ptr addrspace(1) inreg %out) {
@@ -144,6 +208,14 @@ declare i64 @llvm.amdgcn.ballot.i32(i1) #1
 declare i32 @llvm.amdgcn.workgroup.id.x() #0
 declare i32 @llvm.amdgcn.workgroup.id.y() #0
 declare i32 @llvm.amdgcn.workgroup.id.z() #0
+declare i32 @llvm.amdgcn.cluster.workgroup.id.x()
+declare i32 @llvm.amdgcn.cluster.workgroup.id.y()
+declare i32 @llvm.amdgcn.cluster.workgroup.id.z()
+declare i32 @llvm.amdgcn.cluster.workgroup.flat.id()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.x()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.y()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.id.z()
+declare i32 @llvm.amdgcn.cluster.workgroup.max.flat.id()
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind readnone convergent }

@rampitec rampitec merged commit 4a8008c into main Sep 17, 2025
14 checks passed
@rampitec rampitec deleted the users/rampitec/09-17-_amdgpu_mark_cluster_workgroup_id__intrinsics_always_uniform branch September 17, 2025 21:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@shiltian shiltian shiltian approved these changes

Assignees
No one assigned
Labels
backend:AMDGPU llvm:analysis Includes value tracking, cost tables and constant folding
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@rampitec @llvmbot @shiltian