Skip to content

[AMDGPU] Update tests for last-use in global/scratch/flat/buffer load… #94975

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 2 commits into from
Jun 11, 2024
Merged

[AMDGPU] Update tests for last-use in global/scratch/flat/buffer load… #94975

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7af3fee
[AMDGPU] Update tests for last-use in global/scratch/flat/buffer load…
mariusz-sikora-at-amd May 23, 2024
91161a8
Update test
mariusz-sikora-at-amd Jun 10, 2024
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
27 changes: 27 additions & 0 deletions llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load-last-use.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
;RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-enable-delay-alu=0 -verify-machineinstrs | FileCheck %s --check-prefix=GCN
;RUN: llc < %s -global-isel -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-enable-delay-alu=0 -verify-machineinstrs | FileCheck %s --check-prefix=GCN

define amdgpu_ps float @raw_buffer_load(<4 x i32> inreg) {
; GCN-LABEL: raw_buffer_load:
; GCN: ; %bb.0: ; %main_body
; GCN-NEXT: buffer_load_b32 v0, off, s[0:3], null th:TH_LOAD_LU
; GCN-NEXT: s_wait_loadcnt 0x0
; GCN-NEXT: ; return to shader part epilog
main_body:
%data = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %0, i32 0, i32 0, i32 3)
ret float %data
}

define amdgpu_ps float @struct_buffer_load(<4 x i32> inreg) {
; GCN-LABEL: struct_buffer_load:
; GCN: ; %bb.0: ; %main_body
; GCN-NEXT: v_mov_b32_e32 v0, 0
; GCN-NEXT: buffer_load_b32 v0, v0, s[0:3], null idxen th:TH_LOAD_LU
; GCN-NEXT: s_wait_loadcnt 0x0
; GCN-NEXT: ; return to shader part epilog
main_body:
%data = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 3)
ret float %data
}

7 changes: 2 additions & 5 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-lastuse.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12,GFX12-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12,GFX12-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefix=GFX12 %s

define amdgpu_kernel void @flat_last_use_load_0(ptr %in, ptr %out) {
; GFX12-LABEL: flat_last_use_load_0:
Expand Down Expand Up @@ -107,6 +107,3 @@ entry:

!0 = !{i32 1}
declare i32 @llvm.amdgcn.workitem.id.x()
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GFX12-CU: {{.*}}
; GFX12-WGP: {{.*}}
7 changes: 2 additions & 5 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-global-lastuse.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12,GFX12-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12,GFX12-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefix=GFX12 %s

define amdgpu_kernel void @global_last_use_load_0(ptr addrspace(1) %in, ptr addrspace(1) %out) {
; GFX12-LABEL: global_last_use_load_0:
Expand Down Expand Up @@ -92,6 +92,3 @@ entry:
}
!0 = !{i32 1}
declare i32 @llvm.amdgcn.workitem.id.x()
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GFX12-CU: {{.*}}
; GFX12-WGP: {{.*}}
7 changes: 2 additions & 5 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-private-lastuse.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12,GFX12-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12,GFX12-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefix=GFX12 %s

define amdgpu_kernel void @private_last_use_load_0(ptr addrspace(5) %in, ptr addrspace(1) %out) {
; GFX12-LABEL: private_last_use_load_0:
Expand Down Expand Up @@ -85,6 +85,3 @@ entry:

!0 = !{i32 1}
declare i32 @llvm.amdgcn.workitem.id.x()
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GFX12-CU: {{.*}}
; GFX12-WGP: {{.*}}
Loading