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
103 lines
4.1 KiB
LLVM
103 lines
4.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefix=SDAG %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefix=GISEL %s
|
|
|
|
; Check that in strict OOB mode for buffers ("amdgpu.buffer.oob.mode" module flag not set) the underaligned loads and stores get split.
|
|
; FIXME: The loads/stores do not get split (extend amdgpu-lower-buffer-fat-pointers?).
|
|
|
|
define amdgpu_ps void @split_underaligned_load(ptr addrspace(7) inreg %p, ptr addrspace(7) inreg %p2) #0 {
|
|
; CHECK-LABEL: split_underaligned_load:
|
|
; CHECK: ; %bb.0: ; %entry
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, s4
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, s9
|
|
; CHECK-NEXT: s_mov_b32 s15, s8
|
|
; CHECK-NEXT: s_mov_b32 s14, s7
|
|
; CHECK-NEXT: s_mov_b32 s13, s6
|
|
; CHECK-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; CHECK-NEXT: s_mov_b32 s12, s5
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; CHECK-NEXT: s_endpgm
|
|
; SDAG-LABEL: split_underaligned_load:
|
|
; SDAG: ; %bb.0: ; %entry
|
|
; SDAG-NEXT: v_mov_b32_e32 v0, s4
|
|
; SDAG-NEXT: v_mov_b32_e32 v2, s9
|
|
; SDAG-NEXT: s_mov_b32 s15, s8
|
|
; SDAG-NEXT: s_mov_b32 s14, s7
|
|
; SDAG-NEXT: s_mov_b32 s13, s6
|
|
; SDAG-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; SDAG-NEXT: s_mov_b32 s12, s5
|
|
; SDAG-NEXT: s_waitcnt vmcnt(0)
|
|
; SDAG-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; SDAG-NEXT: s_endpgm
|
|
;
|
|
; GISEL-LABEL: split_underaligned_load:
|
|
; GISEL: ; %bb.0: ; %entry
|
|
; GISEL-NEXT: v_mov_b32_e32 v0, s4
|
|
; GISEL-NEXT: v_mov_b32_e32 v2, s9
|
|
; GISEL-NEXT: s_mov_b32 s12, s5
|
|
; GISEL-NEXT: s_mov_b32 s13, s6
|
|
; GISEL-NEXT: s_mov_b32 s14, s7
|
|
; GISEL-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; GISEL-NEXT: s_mov_b32 s15, s8
|
|
; GISEL-NEXT: s_waitcnt vmcnt(0)
|
|
; GISEL-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; GISEL-NEXT: s_endpgm
|
|
entry:
|
|
%gep = getelementptr i8, ptr addrspace(7) %p, i32 0
|
|
%ld = load i64, ptr addrspace(7) %gep, align 4
|
|
|
|
%gep2 = getelementptr i8, ptr addrspace(7) %p2, i32 0
|
|
store i64 %ld, ptr addrspace(7) %gep2, align 4
|
|
ret void
|
|
}
|
|
|
|
; Check that in strict OOB mode for buffers ("amdgpu.buffer.oob.mode" module flag not set) the naturally aligned loads and stores do not get split.
|
|
|
|
define amdgpu_ps void @do_not_split_aligned_load(ptr addrspace(7) inreg %p, ptr addrspace(7) inreg %p2) #0 {
|
|
; CHECK-LABEL: do_not_split_aligned_load:
|
|
; CHECK: ; %bb.0: ; %entry
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, s4
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, s9
|
|
; CHECK-NEXT: s_mov_b32 s15, s8
|
|
; CHECK-NEXT: s_mov_b32 s14, s7
|
|
; CHECK-NEXT: s_mov_b32 s13, s6
|
|
; CHECK-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; CHECK-NEXT: s_mov_b32 s12, s5
|
|
; CHECK-NEXT: s_waitcnt vmcnt(0)
|
|
; CHECK-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; CHECK-NEXT: s_endpgm
|
|
; SDAG-LABEL: do_not_split_aligned_load:
|
|
; SDAG: ; %bb.0: ; %entry
|
|
; SDAG-NEXT: v_mov_b32_e32 v0, s4
|
|
; SDAG-NEXT: v_mov_b32_e32 v2, s9
|
|
; SDAG-NEXT: s_mov_b32 s15, s8
|
|
; SDAG-NEXT: s_mov_b32 s14, s7
|
|
; SDAG-NEXT: s_mov_b32 s13, s6
|
|
; SDAG-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; SDAG-NEXT: s_mov_b32 s12, s5
|
|
; SDAG-NEXT: s_waitcnt vmcnt(0)
|
|
; SDAG-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; SDAG-NEXT: s_endpgm
|
|
;
|
|
; GISEL-LABEL: do_not_split_aligned_load:
|
|
; GISEL: ; %bb.0: ; %entry
|
|
; GISEL-NEXT: v_mov_b32_e32 v0, s4
|
|
; GISEL-NEXT: v_mov_b32_e32 v2, s9
|
|
; GISEL-NEXT: s_mov_b32 s12, s5
|
|
; GISEL-NEXT: s_mov_b32 s13, s6
|
|
; GISEL-NEXT: s_mov_b32 s14, s7
|
|
; GISEL-NEXT: buffer_load_b64 v[0:1], v0, s[0:3], 0 offen
|
|
; GISEL-NEXT: s_mov_b32 s15, s8
|
|
; GISEL-NEXT: s_waitcnt vmcnt(0)
|
|
; GISEL-NEXT: buffer_store_b64 v[0:1], v2, s[12:15], 0 offen
|
|
; GISEL-NEXT: s_endpgm
|
|
entry:
|
|
%gep = getelementptr i8, ptr addrspace(7) %p, i32 0
|
|
%ld = load i64, ptr addrspace(7) %gep, align 8
|
|
|
|
%gep2 = getelementptr i8, ptr addrspace(7) %p2, i32 0
|
|
store i64 %ld, ptr addrspace(7) %gep2, align 8
|
|
ret void
|
|
}
|