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
439 lines
17 KiB
LLVM
439 lines
17 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck --check-prefix=GFX9 %s
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 < %s | FileCheck --check-prefix=GFX10 %s
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 < %s | FileCheck --check-prefix=GFX11 %s
|
|
|
|
@gv = external addrspace(4) constant i32
|
|
|
|
define amdgpu_kernel void @kernel_dynamic_stackalloc_sgpr_align4(i32 %n) #0 {
|
|
; GFX9-LABEL: kernel_dynamic_stackalloc_sgpr_align4:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dword s5, s[8:9], 0x0
|
|
; GFX9-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX9-NEXT: s_movk_i32 s32, 0x400
|
|
; GFX9-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX9-NEXT: s_mov_b32 s4, s32
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s5, s5, 15
|
|
; GFX9-NEXT: s_and_b32 s5, s5, -16
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX9-NEXT: s_lshl_b32 s5, s5, 6
|
|
; GFX9-NEXT: s_mov_b32 s33, 0
|
|
; GFX9-NEXT: s_add_u32 s32, s4, s5
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: kernel_dynamic_stackalloc_sgpr_align4:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dword s5, s[8:9], 0x0
|
|
; GFX10-NEXT: s_movk_i32 s32, 0x200
|
|
; GFX10-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX10-NEXT: s_mov_b32 s4, s32
|
|
; GFX10-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX10-NEXT: s_mov_b32 s33, 0
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s5, s5, 15
|
|
; GFX10-NEXT: s_and_b32 s5, s5, -16
|
|
; GFX10-NEXT: s_lshl_b32 s5, s5, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s4, s5
|
|
; GFX10-NEXT: s_endpgm
|
|
;
|
|
; GFX11-LABEL: kernel_dynamic_stackalloc_sgpr_align4:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_load_b32 s1, s[4:5], 0x0
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_mov_b32 s32, 16
|
|
; GFX11-NEXT: s_mov_b32 s33, 0
|
|
; GFX11-NEXT: s_mov_b32 s0, s32
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s0
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s1, s1, 15
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_b32 s1, s1, -16
|
|
; GFX11-NEXT: s_add_u32 s32, s0, s1
|
|
; GFX11-NEXT: s_endpgm
|
|
%alloca = alloca i32, i32 %n, align 4, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
define void @func_dynamic_stackalloc_sgpr_align4() #0 {
|
|
; GFX9-LABEL: func_dynamic_stackalloc_sgpr_align4:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: s_mov_b32 s7, s33
|
|
; GFX9-NEXT: s_mov_b32 s33, s32
|
|
; GFX9-NEXT: s_addk_i32 s32, 0x400
|
|
; GFX9-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX9-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX9-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX9-NEXT: s_mov_b32 s6, s32
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX9-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX9-NEXT: s_lshl_b32 s4, s4, 6
|
|
; GFX9-NEXT: s_add_u32 s32, s6, s4
|
|
; GFX9-NEXT: s_mov_b32 s32, s33
|
|
; GFX9-NEXT: s_mov_b32 s33, s7
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX10-LABEL: func_dynamic_stackalloc_sgpr_align4:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_mov_b32 s7, s33
|
|
; GFX10-NEXT: s_mov_b32 s33, s32
|
|
; GFX10-NEXT: s_addk_i32 s32, 0x200
|
|
; GFX10-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX10-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX10-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX10-NEXT: s_mov_b32 s6, s32
|
|
; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX10-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX10-NEXT: s_lshl_b32 s4, s4, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s6, s4
|
|
; GFX10-NEXT: s_mov_b32 s32, s33
|
|
; GFX10-NEXT: s_mov_b32 s33, s7
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-LABEL: func_dynamic_stackalloc_sgpr_align4:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-NEXT: s_mov_b32 s3, s33
|
|
; GFX11-NEXT: s_mov_b32 s33, s32
|
|
; GFX11-NEXT: s_add_i32 s32, s32, 16
|
|
; GFX11-NEXT: s_getpc_b64 s[0:1]
|
|
; GFX11-NEXT: s_add_u32 s0, s0, gv@gotpcrel32@lo+4
|
|
; GFX11-NEXT: s_addc_u32 s1, s1, gv@gotpcrel32@hi+12
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_load_b64 s[0:1], s[0:1], 0x0
|
|
; GFX11-NEXT: s_mov_b32 s2, s32
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s2
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_load_b32 s0, s[0:1], 0x0
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s0, s0, 15
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_b32 s0, s0, -16
|
|
; GFX11-NEXT: s_add_u32 s32, s2, s0
|
|
; GFX11-NEXT: s_mov_b32 s32, s33
|
|
; GFX11-NEXT: s_mov_b32 s33, s3
|
|
; GFX11-NEXT: s_setpc_b64 s[30:31]
|
|
%n = load i32, ptr addrspace(4) @gv, align 4
|
|
%alloca = alloca i32, i32 %n, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel_dynamic_stackalloc_sgpr_align16(i32 %n) #0 {
|
|
; GFX9-LABEL: kernel_dynamic_stackalloc_sgpr_align16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dword s5, s[8:9], 0x0
|
|
; GFX9-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX9-NEXT: s_movk_i32 s32, 0x400
|
|
; GFX9-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX9-NEXT: s_mov_b32 s4, s32
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s5, s5, 15
|
|
; GFX9-NEXT: s_and_b32 s5, s5, -16
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX9-NEXT: s_lshl_b32 s5, s5, 6
|
|
; GFX9-NEXT: s_mov_b32 s33, 0
|
|
; GFX9-NEXT: s_add_u32 s32, s4, s5
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: kernel_dynamic_stackalloc_sgpr_align16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dword s5, s[8:9], 0x0
|
|
; GFX10-NEXT: s_movk_i32 s32, 0x200
|
|
; GFX10-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX10-NEXT: s_mov_b32 s4, s32
|
|
; GFX10-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX10-NEXT: s_mov_b32 s33, 0
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s5, s5, 15
|
|
; GFX10-NEXT: s_and_b32 s5, s5, -16
|
|
; GFX10-NEXT: s_lshl_b32 s5, s5, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s4, s5
|
|
; GFX10-NEXT: s_endpgm
|
|
;
|
|
; GFX11-LABEL: kernel_dynamic_stackalloc_sgpr_align16:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_load_b32 s1, s[4:5], 0x0
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_mov_b32 s32, 16
|
|
; GFX11-NEXT: s_mov_b32 s33, 0
|
|
; GFX11-NEXT: s_mov_b32 s0, s32
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s0
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s1, s1, 15
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_b32 s1, s1, -16
|
|
; GFX11-NEXT: s_add_u32 s32, s0, s1
|
|
; GFX11-NEXT: s_endpgm
|
|
%alloca = alloca i32, i32 %n, align 16, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
define void @func_dynamic_stackalloc_sgpr_align16() #0 {
|
|
; GFX9-LABEL: func_dynamic_stackalloc_sgpr_align16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: s_mov_b32 s7, s33
|
|
; GFX9-NEXT: s_mov_b32 s33, s32
|
|
; GFX9-NEXT: s_addk_i32 s32, 0x400
|
|
; GFX9-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX9-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX9-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX9-NEXT: s_mov_b32 s6, s32
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX9-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX9-NEXT: s_lshl_b32 s4, s4, 6
|
|
; GFX9-NEXT: s_add_u32 s32, s6, s4
|
|
; GFX9-NEXT: s_mov_b32 s32, s33
|
|
; GFX9-NEXT: s_mov_b32 s33, s7
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX10-LABEL: func_dynamic_stackalloc_sgpr_align16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_mov_b32 s7, s33
|
|
; GFX10-NEXT: s_mov_b32 s33, s32
|
|
; GFX10-NEXT: s_addk_i32 s32, 0x200
|
|
; GFX10-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX10-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX10-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX10-NEXT: s_mov_b32 s6, s32
|
|
; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s6
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX10-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX10-NEXT: s_lshl_b32 s4, s4, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s6, s4
|
|
; GFX10-NEXT: s_mov_b32 s32, s33
|
|
; GFX10-NEXT: s_mov_b32 s33, s7
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-LABEL: func_dynamic_stackalloc_sgpr_align16:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-NEXT: s_mov_b32 s3, s33
|
|
; GFX11-NEXT: s_mov_b32 s33, s32
|
|
; GFX11-NEXT: s_add_i32 s32, s32, 16
|
|
; GFX11-NEXT: s_getpc_b64 s[0:1]
|
|
; GFX11-NEXT: s_add_u32 s0, s0, gv@gotpcrel32@lo+4
|
|
; GFX11-NEXT: s_addc_u32 s1, s1, gv@gotpcrel32@hi+12
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_load_b64 s[0:1], s[0:1], 0x0
|
|
; GFX11-NEXT: s_mov_b32 s2, s32
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s2
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_load_b32 s0, s[0:1], 0x0
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s0, s0, 15
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_b32 s0, s0, -16
|
|
; GFX11-NEXT: s_add_u32 s32, s2, s0
|
|
; GFX11-NEXT: s_mov_b32 s32, s33
|
|
; GFX11-NEXT: s_mov_b32 s33, s3
|
|
; GFX11-NEXT: s_setpc_b64 s[30:31]
|
|
%n = load i32, ptr addrspace(4) @gv, align 16
|
|
%alloca = alloca i32, i32 %n, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel_dynamic_stackalloc_sgpr_align32(i32 %n) #0 {
|
|
; GFX9-LABEL: kernel_dynamic_stackalloc_sgpr_align32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dword s4, s[8:9], 0x0
|
|
; GFX9-NEXT: s_movk_i32 s32, 0x800
|
|
; GFX9-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX9-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX9-NEXT: s_add_u32 s5, s32, 0x7ff
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX9-NEXT: s_and_b32 s5, s5, 0xfffff800
|
|
; GFX9-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX9-NEXT: s_lshl_b32 s4, s4, 6
|
|
; GFX9-NEXT: s_mov_b32 s33, 0
|
|
; GFX9-NEXT: s_add_u32 s32, s5, s4
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: kernel_dynamic_stackalloc_sgpr_align32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dword s4, s[8:9], 0x0
|
|
; GFX10-NEXT: s_movk_i32 s32, 0x400
|
|
; GFX10-NEXT: s_add_u32 s0, s0, s17
|
|
; GFX10-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX10-NEXT: s_add_u32 s5, s32, 0x3ff
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: s_and_b32 s5, s5, 0xfffffc00
|
|
; GFX10-NEXT: s_mov_b32 s33, 0
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX10-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX10-NEXT: s_lshl_b32 s4, s4, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s5, s4
|
|
; GFX10-NEXT: s_endpgm
|
|
;
|
|
; GFX11-LABEL: kernel_dynamic_stackalloc_sgpr_align32:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_load_b32 s0, s[4:5], 0x0
|
|
; GFX11-NEXT: s_mov_b32 s32, 32
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_add_u32 s1, s32, 31
|
|
; GFX11-NEXT: s_mov_b32 s33, 0
|
|
; GFX11-NEXT: s_and_not1_b32 s1, s1, 31
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s1
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s0, s0, 15
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_b32 s0, s0, -16
|
|
; GFX11-NEXT: s_add_u32 s32, s1, s0
|
|
; GFX11-NEXT: s_endpgm
|
|
%alloca = alloca i32, i32 %n, align 32, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
define void @func_dynamic_stackalloc_sgpr_align32(ptr addrspace(1) %out) #0 {
|
|
; GFX9-LABEL: func_dynamic_stackalloc_sgpr_align32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX9-NEXT: s_mov_b32 s6, s33
|
|
; GFX9-NEXT: s_add_i32 s33, s32, 0x7c0
|
|
; GFX9-NEXT: s_and_b32 s33, s33, 0xfffff800
|
|
; GFX9-NEXT: s_mov_b32 s7, s34
|
|
; GFX9-NEXT: s_mov_b32 s34, s32
|
|
; GFX9-NEXT: s_addk_i32 s32, 0x1000
|
|
; GFX9-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX9-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX9-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: s_mov_b32 s33, s6
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX9-NEXT: s_add_u32 s5, s32, 0x7ff
|
|
; GFX9-NEXT: s_and_b32 s5, s5, 0xfffff800
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX9-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX9-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX9-NEXT: s_lshl_b32 s4, s4, 6
|
|
; GFX9-NEXT: s_add_u32 s32, s5, s4
|
|
; GFX9-NEXT: s_mov_b32 s32, s34
|
|
; GFX9-NEXT: s_mov_b32 s34, s7
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX10-LABEL: func_dynamic_stackalloc_sgpr_align32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX10-NEXT: s_mov_b32 s6, s33
|
|
; GFX10-NEXT: s_add_i32 s33, s32, 0x3e0
|
|
; GFX10-NEXT: s_mov_b32 s7, s34
|
|
; GFX10-NEXT: s_and_b32 s33, s33, 0xfffffc00
|
|
; GFX10-NEXT: s_mov_b32 s34, s32
|
|
; GFX10-NEXT: s_addk_i32 s32, 0x800
|
|
; GFX10-NEXT: s_getpc_b64 s[4:5]
|
|
; GFX10-NEXT: s_add_u32 s4, s4, gv@gotpcrel32@lo+4
|
|
; GFX10-NEXT: s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
|
|
; GFX10-NEXT: s_mov_b32 s33, s6
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_load_dword s4, s[4:5], 0x0
|
|
; GFX10-NEXT: s_add_u32 s5, s32, 0x3ff
|
|
; GFX10-NEXT: s_and_b32 s5, s5, 0xfffffc00
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX10-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_lshl2_add_u32 s4, s4, 15
|
|
; GFX10-NEXT: s_and_b32 s4, s4, -16
|
|
; GFX10-NEXT: s_lshl_b32 s4, s4, 5
|
|
; GFX10-NEXT: s_add_u32 s32, s5, s4
|
|
; GFX10-NEXT: s_mov_b32 s32, s34
|
|
; GFX10-NEXT: s_mov_b32 s34, s7
|
|
; GFX10-NEXT: s_setpc_b64 s[30:31]
|
|
;
|
|
; GFX11-LABEL: func_dynamic_stackalloc_sgpr_align32:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX11-NEXT: s_mov_b32 s2, s33
|
|
; GFX11-NEXT: s_add_i32 s33, s32, 31
|
|
; GFX11-NEXT: s_mov_b32 s3, s34
|
|
; GFX11-NEXT: s_and_not1_b32 s33, s33, 31
|
|
; GFX11-NEXT: s_mov_b32 s34, s32
|
|
; GFX11-NEXT: s_add_i32 s32, s32, 64
|
|
; GFX11-NEXT: s_getpc_b64 s[0:1]
|
|
; GFX11-NEXT: s_add_u32 s0, s0, gv@gotpcrel32@lo+4
|
|
; GFX11-NEXT: s_addc_u32 s1, s1, gv@gotpcrel32@hi+12
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX11-NEXT: s_load_b64 s[0:1], s[0:1], 0x0
|
|
; GFX11-NEXT: s_mov_b32 s33, s2
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_load_b32 s0, s[0:1], 0x0
|
|
; GFX11-NEXT: s_add_u32 s1, s32, 31
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(SKIP_3) | instid1(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_and_not1_b32 s1, s1, 31
|
|
; GFX11-NEXT: scratch_store_b32 off, v0, s1
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: s_lshl2_add_u32 s0, s0, 15
|
|
; GFX11-NEXT: s_and_b32 s0, s0, -16
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
|
|
; GFX11-NEXT: s_add_u32 s32, s1, s0
|
|
; GFX11-NEXT: s_mov_b32 s32, s34
|
|
; GFX11-NEXT: s_mov_b32 s34, s3
|
|
; GFX11-NEXT: s_setpc_b64 s[30:31]
|
|
%n = load i32, ptr addrspace(4) @gv
|
|
%alloca = alloca i32, i32 %n, align 32, addrspace(5)
|
|
store i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|