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
198 lines
7.9 KiB
LLVM
198 lines
7.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; gfx8 required knowing no overflow happened to fold the addressing mode
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 < %s | FileCheck -check-prefix=GFX8 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
|
|
|
|
define void @gep_noflags_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_noflags_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_noflags_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_inbounds_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_inbounds_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_inbounds_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr inbounds [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_nuw_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_nuw_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_nuw_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr nuw [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_nusw_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_nusw_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_nusw_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr nusw [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_inbounds_nuw_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_inbounds_nuw_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_inbounds_nuw_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr inbounds nuw [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_nusw_nuw_alloca(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_nusw_nuw_alloca:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_nusw_nuw_alloca:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 2, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [32 x i32], addrspace(5)
|
|
%gep0 = getelementptr nusw nuw [32 x i32], ptr addrspace(5) %alloca, i32 0, i32 %idx
|
|
%gep1 = getelementptr i32, ptr addrspace(5) %gep0, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1
|
|
ret void
|
|
}
|
|
|
|
define void @gep_inbounds_nuw_alloca_nonpow2_scale(i32 %idx, i32 %val) #0 {
|
|
; GFX8-LABEL: gep_inbounds_nuw_alloca_nonpow2_scale:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX8-NEXT: s_movk_i32 s4, 0x84
|
|
; GFX8-NEXT: v_mul_lo_u32 v0, v0, s4
|
|
; GFX8-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, v0, v2
|
|
; GFX8-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; GFX8-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX9-LABEL: gep_inbounds_nuw_alloca_nonpow2_scale:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: s_movk_i32 s4, 0x84
|
|
; GFX9-NEXT: v_mul_lo_u32 v0, v0, s4
|
|
; GFX9-NEXT: v_lshrrev_b32_e64 v2, 6, s32
|
|
; GFX9-NEXT: v_add_u32_e32 v0, v0, v2
|
|
; GFX9-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen offset:16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
%alloca = alloca [5 x [33 x i32]], align 4, addrspace(5)
|
|
%gep1 = getelementptr inbounds nuw [5 x [33 x i32]], ptr addrspace(5) %alloca, i32 0, i32 %idx, i32 4
|
|
store volatile i32 %val, ptr addrspace(5) %gep1, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|