Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/load-zero-and-sign-extending-divergent.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

303 lines
9.7 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12 %s
define amdgpu_ps void @sextload_P0_i8(ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: sextload_P0_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_i8 v0, v[0:1]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: flat_store_b32 v[2:3], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a32 = sext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @sextload_P0_i16(ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: sextload_P0_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_i16 v0, v[0:1]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: flat_store_b32 v[2:3], v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(0) %ptra
%a32 = sext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @zextload_P0_i8(ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: zextload_P0_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_u8 v0, v[0:1]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: flat_store_b32 v[2:3], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a32 = zext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @zextload_P0_i16(ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: zextload_P0_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_u16 v0, v[0:1]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: flat_store_b32 v[2:3], v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(0) %ptra
%a32 = zext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @sextload_P1_i8(ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P1_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_i8 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a32 = sext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P1_i16(ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P1_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_i16 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(1) %ptra
%a32 = sext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P1_i8(ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P1_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_u8 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a32 = zext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P1_i16(ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P1_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_u16 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(1) %ptra
%a32 = zext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P3_i8(ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: sextload_P3_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_i8 v0, v0
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: ds_store_b32 v1, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a32 = sext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @sextload_P3_i16(ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: sextload_P3_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_i16 v0, v0
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: ds_store_b32 v1, v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(3) %ptra
%a32 = sext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @zextload_P3_i8(ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: zextload_P3_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u8 v0, v0
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: ds_store_b32 v1, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a32 = zext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @zextload_P3_i16(ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: zextload_P3_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u16 v0, v0
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: ds_store_b32 v1, v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(3) %ptra
%a32 = zext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @sextload_P4_i8(ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P4_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_i8 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a32 = sext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P4_i16(ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P4_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_i16 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(4) %ptra
%a32 = sext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P4_i8(ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P4_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_u8 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a32 = zext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P4_i16(ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P4_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_u16 v0, v[0:1], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: global_store_b32 v[2:3], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(4) %ptra
%a32 = zext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P5_i8(ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: sextload_P5_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_i8 v0, v0, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: scratch_store_b32 v1, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a32 = sext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @sextload_P5_i16(ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: sextload_P5_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_i16 v0, v0, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: scratch_store_b32 v1, v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(5) %ptra
%a32 = sext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @zextload_P5_i8(ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: zextload_P5_i8:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_u8 v0, v0, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: scratch_store_b32 v1, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a32 = zext i8 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @zextload_P5_i16(ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: zextload_P5_i16:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_u16 v0, v0, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: v_add_nc_u32_e32 v0, v0, v0
; GFX12-NEXT: scratch_store_b32 v1, v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(5) %ptra
%a32 = zext i16 %a to i32
%res = add i32 %a32, %a32
store i32 %res, ptr addrspace(5) %out
ret void
}