Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/asyncmark-max-pregfx12.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

283 lines
14 KiB
LLVM

; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s
; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck %s
; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s
; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s
; Loop body exceeds MaxAsyncMarkers on first iteration
; Preloop: 5 markers
; Loop body: 18 markers
; CHECK-LABEL: test_loop_exceeds_max_first_iteration:
; CHECK: ; wait_asyncmark(3)
; CHECK-NEXT: s_waitcnt vmcnt(3)
define void @test_loop_exceeds_max_first_iteration(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 %n, ptr addrspace(1) %out) {
entry:
; Preloop: 5 async LDS DMA operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %loop_header
loop_header:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop_body ]
%i.next = add i32 %i, 1
%cmp = icmp slt i32 %i, %n
br i1 %cmp, label %loop_body, label %exit
loop_body:
; Loop body with 18 async operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %loop_header
exit:
call void @llvm.amdgcn.wait.asyncmark(i16 3)
%lds_val = load i32, ptr addrspace(3) %lds
store i32 %lds_val, ptr addrspace(1) %out
ret void
}
; Loop body does not exceed MaxAsyncMarkers on first iteration
; Preloop: 5 markers
; Loop body: 5 markers
; CHECK-LABEL: test_loop_needs_more_iterations:
; CHECK: ; wait_asyncmark(3)
; CHECK-NEXT: s_waitcnt vmcnt(3)
define void @test_loop_needs_more_iterations(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 %n, ptr addrspace(1) %out) {
entry:
; Preloop: 5 async LDS DMA operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %loop_header
loop_header:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop_body ]
%i.next = add i32 %i, 1
%cmp = icmp slt i32 %i, %n
br i1 %cmp, label %loop_body, label %exit
loop_body:
; Loop body with 5 async operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %loop_header
exit:
call void @llvm.amdgcn.wait.asyncmark(i16 3)
%lds_val = load i32, ptr addrspace(3) %lds
store i32 %lds_val, ptr addrspace(1) %out
ret void
}
; Merge exceeds MaxAsyncMarkers
; CHECK-LABEL: max_when_merged:
; CHECK: ; wait_asyncmark(17)
; CHECK-NEXT: s_waitcnt vmcnt(15)
define void @max_when_merged(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 %n, ptr addrspace(1) %out) {
entry:
%cmp = icmp slt i32 0, %n
br i1 %cmp, label %then, label %else
then:
; 5 async operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %endif
else:
; 18 async operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
br label %endif
endif:
call void @llvm.amdgcn.wait.asyncmark(i16 17)
%lds_val = load i32, ptr addrspace(3) %lds
store i32 %lds_val, ptr addrspace(1) %out
ret void
}
; Straightline exceeds MaxAsyncMarkers
; CHECK-LABEL: no_max_in_straightline:
; CHECK: ; wait_asyncmark(17)
; CHECK-NEXT: s_waitcnt vmcnt(17)
define void @no_max_in_straightline(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 %n, ptr addrspace(1) %out) {
; 18 async operations
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) %in, ptr addrspace(3) %lds, i32 4, i32 0, i32 0)
call void @llvm.amdgcn.asyncmark()
call void @llvm.amdgcn.wait.asyncmark(i16 17)
%lds_val = load i32, ptr addrspace(3) %lds
store i32 %lds_val, ptr addrspace(1) %out
ret void
}