derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
1a182e2dac58879f215c0fad0f5f78c76dcafe56
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/load-d16.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

417 lines
15 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck --check-prefixes=GFX12,GFX12-TRUE16 %s
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck --check-prefixes=GFX12,GFX12-FAKE16 %s
define amdgpu_ps void @load_P0_B16_D16(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: load_P0_B16_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_b16 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(0) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 0
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @load_P0_B16_D16_Hi(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: load_P0_B16_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_hi_b16 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(0) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 1
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @sextload_P0_i8_D16(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: sextload_P0_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_i8 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @sextload_P0_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: sextload_P0_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_hi_i8 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @zextload_P0_i8_D16(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: zextload_P0_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_u8 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @zextload_P0_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(0) %ptra, ptr addrspace(0) %out) {
; GFX12-LABEL: zextload_P0_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: flat_load_d16_hi_u8 v0, v[1:2]
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: flat_store_b32 v[3:4], v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(0) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(0) %out
ret void
}
define amdgpu_ps void @load_P1_B16_D16(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: load_P1_B16_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_b16 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(1) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @load_P1_B16_D16_Hi(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: load_P1_B16_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_b16 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(1) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P1_i8_D16(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P1_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_i8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P1_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P1_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_i8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P1_i8_D16(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P1_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_u8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P1_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(1) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P1_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_u8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(1) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @load_P3_B16_D16(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: load_P3_B16_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u16_d16 v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(3) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 0
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @load_P3_B16_D16_Hi(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: load_P3_B16_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u16_d16_hi v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(3) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 1
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @sextload_P3_i8_D16(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: sextload_P3_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_i8_d16 v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @sextload_P3_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: sextload_P3_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_i8_d16_hi v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @zextload_P3_i8_D16(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: zextload_P3_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u8_d16 v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @zextload_P3_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(3) %ptra, ptr addrspace(3) %out) {
; GFX12-LABEL: zextload_P3_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: ds_load_u8_d16_hi v0, v1
; GFX12-NEXT: s_wait_dscnt 0x0
; GFX12-NEXT: ds_store_b32 v2, v0
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(3) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(3) %out
ret void
}
define amdgpu_ps void @load_P4_B16_D16(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: load_P4_B16_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_b16 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(4) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @load_P4_B16_D16_Hi(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: load_P4_B16_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_b16 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(4) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P4_i8_D16(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P4_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_i8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @sextload_P4_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: sextload_P4_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_i8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P4_i8_D16(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P4_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_u8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @zextload_P4_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(4) %ptra, ptr addrspace(1) %out) {
; GFX12-LABEL: zextload_P4_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: global_load_d16_hi_u8 v0, v[1:2], off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_store_b32 v[3:4], v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(4) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(1) %out
ret void
}
define amdgpu_ps void @load_P5_B16_D16(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: load_P5_B16_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_b16 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(5) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 0
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @load_P5_B16_D16_Hi(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: load_P5_B16_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_hi_b16 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i16, ptr addrspace(5) %ptra
%res = insertelement <2 x i16> %vec, i16 %a, i32 1
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @sextload_P5_i8_D16(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: sextload_P5_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_i8 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @sextload_P5_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: sextload_P5_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_hi_i8 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a16 = sext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @zextload_P5_i8_D16(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: zextload_P5_i8_D16:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_u8 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 0
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
define amdgpu_ps void @zextload_P5_i8_D16_Hi(<2 x i16> %vec, ptr addrspace(5) %ptra, ptr addrspace(5) %out) {
; GFX12-LABEL: zextload_P5_i8_D16_Hi:
; GFX12: ; %bb.0:
; GFX12-NEXT: scratch_load_d16_hi_u8 v0, v1, off
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: scratch_store_b32 v2, v0, off
; GFX12-NEXT: s_endpgm
%a = load i8, ptr addrspace(5) %ptra
%a16 = zext i8 %a to i16
%res = insertelement <2 x i16> %vec, i16 %a16, i32 1
store <2 x i16> %res, ptr addrspace(5) %out
ret void
}
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GFX12-FAKE16: {{.*}}
; GFX12-TRUE16: {{.*}}
Reference in new issue View Git Blame Copy Permalink