forked from OSchip/llvm-project
94 lines
3.3 KiB
LLVM
94 lines
3.3 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}udiv_i32:
|
|
; EG-NOT: SETGE_INT
|
|
; EG: CF_END
|
|
define void @udiv_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
|
|
%a = load i32, i32 addrspace(1) * %in
|
|
%b = load i32, i32 addrspace(1) * %b_ptr
|
|
%result = udiv i32 %a, %b
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}s_udiv_i32:
|
|
|
|
define void @s_udiv_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) {
|
|
%result = udiv i32 %a, %b
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
; The code generated by udiv is long and complex and may frequently
|
|
; change. The goal of this test is to make sure the ISel doesn't fail
|
|
; when it gets a v4i32 udiv
|
|
|
|
; FUNC-LABEL: {{^}}udiv_v2i32:
|
|
; EG: CF_END
|
|
|
|
; SI: s_endpgm
|
|
define void @udiv_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <2 x i32>, <2 x i32> addrspace(1) * %in
|
|
%b = load <2 x i32>, <2 x i32> addrspace(1) * %b_ptr
|
|
%result = udiv <2 x i32> %a, %b
|
|
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}udiv_v4i32:
|
|
; EG: CF_END
|
|
; SI: s_endpgm
|
|
define void @udiv_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <4 x i32>, <4 x i32> addrspace(1) * %in
|
|
%b = load <4 x i32>, <4 x i32> addrspace(1) * %b_ptr
|
|
%result = udiv <4 x i32> %a, %b
|
|
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}udiv_i32_div_pow2:
|
|
; SI: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; SI: v_lshrrev_b32_e32 [[RESULT:v[0-9]+]], 4, [[VAL]]
|
|
; SI: buffer_store_dword [[RESULT]]
|
|
define void @udiv_i32_div_pow2(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
|
|
%a = load i32, i32 addrspace(1)* %in
|
|
%result = udiv i32 %a, 16
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}udiv_i32_div_k_even:
|
|
; SI-DAG: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; SI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0xfabbd9c1
|
|
; SI: v_mul_hi_u32 [[MULHI:v[0-9]+]], [[K]], [[VAL]]
|
|
; SI: v_lshrrev_b32_e32 [[RESULT:v[0-9]+]], 25, [[MULHI]]
|
|
; SI: buffer_store_dword [[RESULT]]
|
|
define void @udiv_i32_div_k_even(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
|
|
%a = load i32, i32 addrspace(1)* %in
|
|
%result = udiv i32 %a, 34259182
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}udiv_i32_div_k_odd:
|
|
; SI-DAG: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; SI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0x7d5deca3
|
|
; SI: v_mul_hi_u32 [[MULHI:v[0-9]+]], [[K]], [[VAL]]
|
|
; SI: v_lshrrev_b32_e32 [[RESULT:v[0-9]+]], 24, [[MULHI]]
|
|
; SI: buffer_store_dword [[RESULT]]
|
|
define void @udiv_i32_div_k_odd(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
|
|
%a = load i32, i32 addrspace(1)* %in
|
|
%result = udiv i32 %a, 34259183
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|