forked from OSchip/llvm-project
92 lines
3.2 KiB
LLVM
Executable File
92 lines
3.2 KiB
LLVM
Executable File
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN %s
|
|
|
|
define amdgpu_kernel void @sext_i16_to_i32_uniform(i32 addrspace(1)* %out, i16 %a, i32 %b) {
|
|
; GCN-LABEL: sext_i16_to_i32_uniform:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GCN-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0xb
|
|
; GCN-NEXT: s_mov_b32 s7, 0xf000
|
|
; GCN-NEXT: s_mov_b32 s6, -1
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: s_sext_i32_i16 s0, s0
|
|
; GCN-NEXT: s_add_i32 s0, s1, s0
|
|
; GCN-NEXT: v_mov_b32_e32 v0, s0
|
|
; GCN-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GCN-NEXT: s_endpgm
|
|
%sext = sext i16 %a to i32
|
|
%res = add i32 %b, %sext
|
|
store i32 %res, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
define amdgpu_kernel void @sext_i16_to_i64_uniform(i64 addrspace(1)* %out, i16 %a, i64 %b) {
|
|
; GCN-LABEL: sext_i16_to_i64_uniform:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GCN-NEXT: s_load_dword s2, s[0:1], 0xb
|
|
; GCN-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0xd
|
|
; GCN-NEXT: s_mov_b32 s7, 0xf000
|
|
; GCN-NEXT: s_mov_b32 s6, -1
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: s_bfe_i64 s[2:3], s[2:3], 0x100000
|
|
; GCN-NEXT: s_add_u32 s0, s0, s2
|
|
; GCN-NEXT: s_addc_u32 s1, s1, s3
|
|
; GCN-NEXT: v_mov_b32_e32 v0, s0
|
|
; GCN-NEXT: v_mov_b32_e32 v1, s1
|
|
; GCN-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GCN-NEXT: s_endpgm
|
|
%sext = sext i16 %a to i64
|
|
%res = add i64 %b, %sext
|
|
store i64 %res, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @sext_i16_to_i32_divergent(i32 addrspace(1)* %out, i16 %a, i32 %b) {
|
|
; GCN-LABEL: sext_i16_to_i32_divergent:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GCN-NEXT: s_load_dword s0, s[0:1], 0xb
|
|
; GCN-NEXT: s_mov_b32 s7, 0xf000
|
|
; GCN-NEXT: s_mov_b32 s6, -1
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: v_add_i32_e32 v0, vcc, s0, v0
|
|
; GCN-NEXT: v_bfe_i32 v0, v0, 0, 16
|
|
; GCN-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GCN-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.truncated = trunc i32 %tid to i16
|
|
%divergent.a = add i16 %a, %tid.truncated
|
|
%sext = sext i16 %divergent.a to i32
|
|
store i32 %sext, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
define amdgpu_kernel void @sext_i16_to_i64_divergent(i64 addrspace(1)* %out, i16 %a, i64 %b) {
|
|
; GCN-LABEL: sext_i16_to_i64_divergent:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x9
|
|
; GCN-NEXT: s_load_dword s0, s[0:1], 0xb
|
|
; GCN-NEXT: s_mov_b32 s7, 0xf000
|
|
; GCN-NEXT: s_mov_b32 s6, -1
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: v_add_i32_e32 v0, vcc, s0, v0
|
|
; GCN-NEXT: v_bfe_i32 v0, v0, 0, 16
|
|
; GCN-NEXT: v_ashrrev_i32_e32 v1, 31, v0
|
|
; GCN-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
|
|
; GCN-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.truncated = trunc i32 %tid to i16
|
|
%divergent.a = add i16 %a, %tid.truncated
|
|
%sext = sext i16 %divergent.a to i64
|
|
store i64 %sext, i64 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone speculatable }
|