forked from OSchip/llvm-project
2248 lines
88 KiB
LLVM
2248 lines
88 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -march=amdgcn -verify-machineinstrs | FileCheck %s -check-prefixes=GCN,SI
|
|
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefixes=GCN,VI
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck %s -check-prefixes=GCN,GFX9
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck %s -check-prefixes=GCN,GFX10
|
|
|
|
; Test that add/sub with a constant is swapped to sub/add with negated
|
|
; constant to minimize code size.
|
|
|
|
define amdgpu_kernel void @v_test_i32_x_sub_64(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_x_sub_64:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v2, vcc, 64, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_x_sub_64:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u32_e32 v0, vcc, 64, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_x_sub_64:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_subrev_u32_e32 v1, 64, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_x_sub_64:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_subrev_nc_u32_e32 v1, 64, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 %x, 64
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_x_sub_64_multi_use(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_x_sub_64_multi_use:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: buffer_load_dword v3, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(1)
|
|
; SI-NEXT: v_subrev_i32_e32 v2, vcc, 64, v2
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 64, v3
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: buffer_store_dword v3, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_x_sub_64_multi_use:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: flat_load_dword v4, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(1)
|
|
; VI-NEXT: v_subrev_u32_e32 v2, vcc, 64, v3
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u32_e32 v3, vcc, 64, v4
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v3
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_x_sub_64_multi_use:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: global_load_dword v2, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX9-NEXT: v_subrev_u32_e32 v1, 64, v1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_subrev_u32_e32 v2, 64, v2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_x_sub_64_multi_use:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_clause 0x1
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: global_load_dword v2, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX10-NEXT: v_subrev_nc_u32_e32 v1, 64, v1
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_subrev_nc_u32_e32 v2, 64, v2
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load volatile i32, i32 addrspace(1)* %gep
|
|
%y = load volatile i32, i32 addrspace(1)* %gep
|
|
%result0 = sub i32 %x, 64
|
|
%result1 = sub i32 %y, 64
|
|
store volatile i32 %result0, i32 addrspace(1)* %gep.out
|
|
store volatile i32 %result1, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_64_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_64_sub_x:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_sub_i32_e32 v2, vcc, 64, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_64_sub_x:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u32_e32 v0, vcc, 64, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_64_sub_x:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_sub_u32_e32 v1, 64, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_64_sub_x:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u32_e32 v1, 64, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 64, %x
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_x_sub_65(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_x_sub_65:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffffffbf, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_x_sub_65:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 0xffffffbf, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_x_sub_65:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_add_u32_e32 v1, 0xffffffbf, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_x_sub_65:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_add_nc_u32_e32 v1, 0xffffffbf, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 %x, 65
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_65_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_65_sub_x:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_sub_i32_e32 v2, vcc, 0x41, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_65_sub_x:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u32_e32 v0, vcc, 0x41, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_65_sub_x:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_sub_u32_e32 v1, 0x41, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_65_sub_x:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u32_e32 v1, 0x41, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 65, %x
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_x_sub_neg16(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_x_sub_neg16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 16, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_x_sub_neg16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 16, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_x_sub_neg16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_add_u32_e32 v1, 16, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_x_sub_neg16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_add_nc_u32_e32 v1, 16, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 %x, -16
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_neg16_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_neg16_sub_x:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_sub_i32_e32 v2, vcc, -16, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_neg16_sub_x:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u32_e32 v0, vcc, -16, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_neg16_sub_x:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_sub_u32_e32 v1, -16, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_neg16_sub_x:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u32_e32 v1, -16, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 -16, %x
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_x_sub_neg17(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_x_sub_neg17:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 17, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_x_sub_neg17:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, 17, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_x_sub_neg17:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_add_u32_e32 v1, 17, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_x_sub_neg17:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_add_nc_u32_e32 v1, 17, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 %x, -17
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i32_neg17_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i32_neg17_sub_x:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_sub_i32_e32 v2, vcc, 0xffffffef, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i32_neg17_sub_x:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u32_e32 v0, vcc, 0xffffffef, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i32_neg17_sub_x:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_sub_u32_e32 v1, 0xffffffef, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i32_neg17_sub_x:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u32_e32 v1, 0xffffffef, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i32, i32 addrspace(1)* %gep
|
|
%result = sub i32 -17, %x
|
|
store i32 %result, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @s_test_i32_x_sub_64(i32 %x) #0 {
|
|
; SI-LABEL: s_test_i32_x_sub_64:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dword s0, s[0:1], 0x9
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_sub_i32 s0, s0, 64
|
|
; SI-NEXT: ;;#ASMSTART
|
|
; SI-NEXT: ; use s0
|
|
; SI-NEXT: ;;#ASMEND
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: s_test_i32_x_sub_64:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dword s0, s[0:1], 0x24
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: s_sub_i32 s0, s0, 64
|
|
; VI-NEXT: ;;#ASMSTART
|
|
; VI-NEXT: ; use s0
|
|
; VI-NEXT: ;;#ASMEND
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: s_test_i32_x_sub_64:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dword s0, s[0:1], 0x24
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: s_sub_i32 s0, s0, 64
|
|
; GFX9-NEXT: ;;#ASMSTART
|
|
; GFX9-NEXT: ; use s0
|
|
; GFX9-NEXT: ;;#ASMEND
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: s_test_i32_x_sub_64:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dword s0, s[0:1], 0x24
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_sub_i32 s0, s0, 64
|
|
; GFX10-NEXT: ;;#ASMSTART
|
|
; GFX10-NEXT: ; use s0
|
|
; GFX10-NEXT: ;;#ASMEND
|
|
; GFX10-NEXT: s_endpgm
|
|
%result = sub i32 %x, 64
|
|
call void asm sideeffect "; use $0", "s"(i32 %result)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i16_x_sub_64(i16 addrspace(1)* %out, i16 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i16_x_sub_64:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_ushort v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v2, vcc, 64, v2
|
|
; SI-NEXT: buffer_store_short v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i16_x_sub_64:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 1, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_ushort v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u16_e32 v0, 64, v0
|
|
; VI-NEXT: flat_store_short v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i16_x_sub_64:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_ushort v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_subrev_u16_e32 v1, 64, v1
|
|
; GFX9-NEXT: global_store_short v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i16_x_sub_64:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_ushort v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u16_e64 v1, v1, 64
|
|
; GFX10-NEXT: global_store_short v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i16, i16 addrspace(1)* %gep
|
|
%result = sub i16 %x, 64
|
|
store i16 %result, i16 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i16_x_sub_64_zext_to_i32(i32 addrspace(1)* %out, i16 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i16_x_sub_64_zext_to_i32:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v1, 1, v0
|
|
; SI-NEXT: v_mov_b32_e32 v2, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_ushort v3, v[1:2], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: v_lshlrev_b32_e32 v1, 2, v0
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v0, vcc, 64, v3
|
|
; SI-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; SI-NEXT: buffer_store_dword v0, v[1:2], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i16_x_sub_64_zext_to_i32:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v1, 1, v0
|
|
; VI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v2, s3
|
|
; VI-NEXT: v_add_u32_e32 v1, vcc, s2, v1
|
|
; VI-NEXT: v_addc_u32_e32 v2, vcc, 0, v2, vcc
|
|
; VI-NEXT: v_add_u32_e32 v3, vcc, s0, v0
|
|
; VI-NEXT: flat_load_ushort v0, v[1:2]
|
|
; VI-NEXT: v_mov_b32_e32 v4, s1
|
|
; VI-NEXT: v_addc_u32_e32 v4, vcc, 0, v4, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u16_e32 v0, 64, v0
|
|
; VI-NEXT: flat_store_dword v[3:4], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i16_x_sub_64_zext_to_i32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v1, 1, v0
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_ushort v1, v1, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_subrev_u16_e32 v1, 64, v1
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i16_x_sub_64_zext_to_i32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v1, 1, v0
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_ushort v1, v1, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u16_e64 v1, v1, 64
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load i16, i16 addrspace(1)* %gep
|
|
%result = sub i16 %x, 64
|
|
%zext = zext i16 %result to i32
|
|
store i32 %zext, i32 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_i16_x_sub_64_multi_use(i16 addrspace(1)* %out, i16 addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_i16_x_sub_64_multi_use:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_ushort v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: buffer_load_ushort v3, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(1)
|
|
; SI-NEXT: v_subrev_i32_e32 v2, vcc, 64, v2
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 64, v3
|
|
; SI-NEXT: buffer_store_short v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: buffer_store_short v3, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_i16_x_sub_64_multi_use:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 1, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_ushort v3, v[0:1]
|
|
; VI-NEXT: flat_load_ushort v4, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(1)
|
|
; VI-NEXT: v_subrev_u16_e32 v2, 64, v3
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u16_e32 v3, 64, v4
|
|
; VI-NEXT: flat_store_short v[0:1], v2
|
|
; VI-NEXT: flat_store_short v[0:1], v3
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_i16_x_sub_64_multi_use:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_ushort v1, v0, s[2:3]
|
|
; GFX9-NEXT: global_load_ushort v2, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX9-NEXT: v_subrev_u16_e32 v1, 64, v1
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_subrev_u16_e32 v2, 64, v2
|
|
; GFX9-NEXT: global_store_short v0, v1, s[0:1]
|
|
; GFX9-NEXT: global_store_short v0, v2, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_i16_x_sub_64_multi_use:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 1, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: s_clause 0x1
|
|
; GFX10-NEXT: global_load_ushort v1, v0, s[2:3]
|
|
; GFX10-NEXT: global_load_ushort v2, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX10-NEXT: v_sub_nc_u16_e64 v1, v1, 64
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_sub_nc_u16_e64 v2, v2, 64
|
|
; GFX10-NEXT: global_store_short v0, v1, s[0:1]
|
|
; GFX10-NEXT: global_store_short v0, v2, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i64 %tid.ext
|
|
%x = load volatile i16, i16 addrspace(1)* %gep
|
|
%y = load volatile i16, i16 addrspace(1)* %gep
|
|
%result0 = sub i16 %x, 64
|
|
%result1 = sub i16 %y, 64
|
|
store volatile i16 %result0, i16 addrspace(1)* %gep.out
|
|
store volatile i16 %result1, i16 addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_64_64(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_64_64:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 64, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffc00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_64_64:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: v_mov_b32_e32 v4, 64
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u16_sdwa v2, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_subrev_u16_e32 v3, 64, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_64_64:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, 64 op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_64_64:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 64 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 64, i16 64>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_7_64(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_7_64:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, -7, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffc00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_7_64:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: v_mov_b32_e32 v4, 64
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, -7, v3
|
|
; VI-NEXT: v_sub_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_7_64:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0x400007
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_7_64:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 0x400007
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 7, i16 64>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_64_123(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_64_123:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 64, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xff850000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_64_123:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: v_mov_b32_e32 v4, 0xffffff85
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_sdwa v2, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_subrev_u16_e32 v3, 64, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_64_123:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0x7b0040
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_64_123:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 0x7b0040
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 64, i16 123>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
; Can fold 0 and inline immediate in other half.
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_7_0(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_7_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, -7, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v3, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_7_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v2, 0xffff0000, v3
|
|
; VI-NEXT: v_add_u16_e32 v3, -7, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_7_0:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, 7
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_7_0:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 7
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 7, i16 0>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
; Can fold 0 and inline immediate in other half.
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_0_16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_0_16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xfff00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_0_16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, -16
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_0_16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, 16 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_0_16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 16 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 0, i16 16>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_0_1_0(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_0_1_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0x3c000000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_0_1_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, 0x3c00
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_0_1_0:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_brev_b32 s2, 35
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_0_1_0:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 0xc400 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 0, i16 -15360>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_sub_0_neg1_0(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_sub_0_neg1_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xbc000000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_sub_0_neg1_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, 0xffffbc00
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_sub_0_neg1_0:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_brev_b32 s2, 34
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_i16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_sub_0_neg1_0:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_i16 v1, v1, 0x4400 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = sub <2 x i16> %x, <i16 0, i16 17408>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
; -32 isn't an inline immediate, but 32 is
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg32_neg32(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg32_neg32:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 32, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffe00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg32_neg32:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: v_mov_b32_e32 v4, 32
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u16_sdwa v2, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_subrev_u16_e32 v3, 32, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg32_neg32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg32_neg32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -32, i16 -32>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_0_neg32(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_0_neg32:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffe00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_0_neg32:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, 32
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_0_neg32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_0_neg32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 0, i16 -32>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg32_0(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg32_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v3, vcc, 32, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v3, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg32_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v2, 0xffff0000, v3
|
|
; VI-NEXT: v_subrev_u16_e32 v3, 32, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg32_0:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 32
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg32_0:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 32
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -32, i16 0>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
; 16 and -16 are both inline immediates
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg16_neg16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg16_neg16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, -16, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xfff00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg16_neg16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: v_mov_b32_e32 v4, -16
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, -16, v3
|
|
; VI-NEXT: v_add_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg16_neg16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 16 op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg16_neg16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 16 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -16, i16 -16>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_0_neg16(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_0_neg16:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xfff00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_0_neg16:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, -16
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_0_neg16:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 16 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_0_neg16:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 16 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 0, i16 -16>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg16_0(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg16_0:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, -16, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v3, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg16_0:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_and_b32_e32 v2, 0xffff0000, v3
|
|
; VI-NEXT: v_add_u16_e32 v3, -16, v3
|
|
; VI-NEXT: v_or_b32_e32 v2, v3, v2
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg16_0:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 16
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg16_0:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 16
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -16, i16 0>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg_fpone(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg_fpone:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, 0xffffc400, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xc4000000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg_fpone:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: s_movk_i32 s2, 0xc400
|
|
; VI-NEXT: v_mov_b32_e32 v4, s2
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, s2, v3
|
|
; VI-NEXT: v_add_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg_fpone:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0x3c003c00
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg_fpone:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 0x3c00 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -15360, i16 -15360>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg_negfpone(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg_negfpone:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, 0x4400, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0x44000000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg_negfpone:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: s_movk_i32 s2, 0x4400
|
|
; VI-NEXT: v_mov_b32_e32 v4, s2
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, s2, v3
|
|
; VI-NEXT: v_add_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg_negfpone:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0xbc00bc00
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg_negfpone:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 0xbc00 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 17408, i16 17408>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg_fptwo(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg_fptwo:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, 0x4000, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 2.0, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg_fptwo:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: s_movk_i32 s2, 0x4000
|
|
; VI-NEXT: v_mov_b32_e32 v4, s2
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, s2, v3
|
|
; VI-NEXT: v_add_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg_fptwo:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0xc000c000
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg_fptwo:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 0xc000 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 16384, i16 16384>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg_negfptwo(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg_negfptwo:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_add_i32_e32 v3, vcc, 0xffffc000, v2
|
|
; SI-NEXT: s_mov_b32 s4, 0xffff0000
|
|
; SI-NEXT: v_bfi_b32 v2, s4, v2, v3
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, -2.0, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg_negfptwo:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v3, v[0:1]
|
|
; VI-NEXT: s_movk_i32 s2, 0xc000
|
|
; VI-NEXT: v_mov_b32_e32 v4, s2
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v2
|
|
; VI-NEXT: v_mov_b32_e32 v1, s1
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_add_u16_e32 v2, s2, v3
|
|
; VI-NEXT: v_add_u16_sdwa v3, v3, v4 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: v_or_b32_e32 v2, v2, v3
|
|
; VI-NEXT: flat_store_dword v[0:1], v2
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg_negfptwo:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_mov_b32 s2, 0x40004000
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, s2
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg_negfptwo:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 0x4000 op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -16384, i16 -16384>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_undef_neg32(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_undef_neg32:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
|
|
; SI-NEXT: v_add_i32_e32 v2, vcc, 0xffe00000, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_undef_neg32:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v1, 32
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_sub_u16_sdwa v0, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_undef_neg32:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_undef_neg32:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 32 op_sel:[0,1] op_sel_hi:[1,0]
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 undef, i16 -32>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @v_test_v2i16_x_add_neg32_undef(<2 x i16> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
|
|
; SI-LABEL: v_test_v2i16_x_add_neg32_undef:
|
|
; SI: ; %bb.0:
|
|
; SI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
|
|
; SI-NEXT: s_mov_b32 s7, 0xf000
|
|
; SI-NEXT: s_mov_b32 s6, 0
|
|
; SI-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; SI-NEXT: v_mov_b32_e32 v1, 0
|
|
; SI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SI-NEXT: s_mov_b64 s[4:5], s[2:3]
|
|
; SI-NEXT: buffer_load_dword v2, v[0:1], s[4:7], 0 addr64
|
|
; SI-NEXT: s_mov_b64 s[2:3], s[6:7]
|
|
; SI-NEXT: s_waitcnt vmcnt(0)
|
|
; SI-NEXT: v_subrev_i32_e32 v2, vcc, 32, v2
|
|
; SI-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; SI-NEXT: buffer_store_dword v2, v[0:1], s[0:3], 0 addr64
|
|
; SI-NEXT: s_endpgm
|
|
;
|
|
; VI-LABEL: v_test_v2i16_x_add_neg32_undef:
|
|
; VI: ; %bb.0:
|
|
; VI-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; VI-NEXT: v_lshlrev_b32_e32 v2, 2, v0
|
|
; VI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VI-NEXT: v_mov_b32_e32 v1, s3
|
|
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v2
|
|
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
|
|
; VI-NEXT: flat_load_dword v0, v[0:1]
|
|
; VI-NEXT: v_mov_b32_e32 v3, s1
|
|
; VI-NEXT: v_add_u32_e32 v2, vcc, s0, v2
|
|
; VI-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
|
|
; VI-NEXT: s_waitcnt vmcnt(0)
|
|
; VI-NEXT: v_subrev_u16_e32 v0, 32, v0
|
|
; VI-NEXT: flat_store_dword v[2:3], v0
|
|
; VI-NEXT: s_endpgm
|
|
;
|
|
; GFX9-LABEL: v_test_v2i16_x_add_neg32_undef:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX9-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX9-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: v_pk_sub_u16 v1, v1, 32
|
|
; GFX9-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX9-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: v_test_v2i16_x_add_neg32_undef:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX10-NEXT: v_lshlrev_b32_e32 v0, 2, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-NEXT: global_load_dword v1, v0, s[2:3]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: v_pk_sub_u16 v1, v1, 32
|
|
; GFX10-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-NEXT: s_endpgm
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%gep = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in, i64 %tid.ext
|
|
%gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i64 %tid.ext
|
|
%x = load <2 x i16>, <2 x i16> addrspace(1)* %gep
|
|
%result = add <2 x i16> %x, <i16 -32, i16 undef>
|
|
store <2 x i16> %result, <2 x i16> addrspace(1)* %gep.out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|