maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

R600/SI: Add global atomicrmw xor 

v2: Add separate offset/no-offset tests

Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Matt Arsenault <matthew.arsenault@amd.com>
llvm-svn: 220109
This commit is contained in:
Aaron Watry 2014-10-17 23:33:01 +00:00
parent 8a911e6926
commit d672ee2a47
3 changed files with 84 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Target/R600/AMDGPUInstructions.td
View File

@ -394,6 +394,7 @@ def atomic_or_global : global_binary_atomic_op<atomic_load_or>;
def atomic_sub_global : global_binary_atomic_op<atomic_load_sub>;
def atomic_umax_global : global_binary_atomic_op<atomic_load_umax>;
def atomic_umin_global : global_binary_atomic_op<atomic_load_umin>;
def atomic_xor_global : global_binary_atomic_op<atomic_load_xor>;
//===----------------------------------------------------------------------===//
// Misc Pattern Fragments

4
llvm/lib/Target/R600/SIInstructions.td
View File

@ -922,7 +922,9 @@ defm BUFFER_ATOMIC_AND : MUBUF_Atomic <
defm BUFFER_ATOMIC_OR : MUBUF_Atomic <
0x0000003a, "BUFFER_ATOMIC_OR", VReg_32, i32, atomic_or_global
>;
//def BUFFER_ATOMIC_XOR : MUBUF_ <0x0000003b, "BUFFER_ATOMIC_XOR", []>;
defm BUFFER_ATOMIC_XOR : MUBUF_Atomic <
0x0000003b, "BUFFER_ATOMIC_XOR", VReg_32, i32, atomic_xor_global
>;
//def BUFFER_ATOMIC_INC : MUBUF_ <0x0000003c, "BUFFER_ATOMIC_INC", []>;
//def BUFFER_ATOMIC_DEC : MUBUF_ <0x0000003d, "BUFFER_ATOMIC_DEC", []>;
//def BUFFER_ATOMIC_FCMPSWAP : MUBUF_ <0x0000003e, "BUFFER_ATOMIC_FCMPSWAP", []>;

80
llvm/test/CodeGen/R600/global_atomics.ll
View File

@ -639,3 +639,83 @@ entry:
store i32 %0, i32 addrspace(1)* %out2
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_offset:
; SI: BUFFER_ATOMIC_XOR v{{[0-9]+}}, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:0x10{{$}}
define void @atomic_xor_i32_offset(i32 addrspace(1)* %out, i32 %in) {
entry:
%gep = getelementptr i32 addrspace(1)* %out, i32 4
%0 = atomicrmw volatile xor i32 addrspace(1)* %gep, i32 %in seq_cst
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_ret_offset:
; SI: BUFFER_ATOMIC_XOR [[RET:v[0-9]+]], s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:0x10 glc {{$}}
; SI: BUFFER_STORE_DWORD [[RET]]
define void @atomic_xor_i32_ret_offset(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in) {
entry:
%gep = getelementptr i32 addrspace(1)* %out, i32 4
%0 = atomicrmw volatile xor i32 addrspace(1)* %gep, i32 %in seq_cst
store i32 %0, i32 addrspace(1)* %out2
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_addr64_offset:
; SI: BUFFER_ATOMIC_XOR v{{[0-9]+}}, v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 offset:0x10{{$}}
define void @atomic_xor_i32_addr64_offset(i32 addrspace(1)* %out, i32 %in, i64 %index) {
entry:
%ptr = getelementptr i32 addrspace(1)* %out, i64 %index
%gep = getelementptr i32 addrspace(1)* %ptr, i32 4
%0 = atomicrmw volatile xor i32 addrspace(1)* %gep, i32 %in seq_cst
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_ret_addr64_offset:
; SI: BUFFER_ATOMIC_XOR [[RET:v[0-9]+]], v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 offset:0x10 glc{{$}}
; SI: BUFFER_STORE_DWORD [[RET]]
define void @atomic_xor_i32_ret_addr64_offset(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in, i64 %index) {
entry:
%ptr = getelementptr i32 addrspace(1)* %out, i64 %index
%gep = getelementptr i32 addrspace(1)* %ptr, i32 4
%0 = atomicrmw volatile xor i32 addrspace(1)* %gep, i32 %in seq_cst
store i32 %0, i32 addrspace(1)* %out2
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32:
; SI: BUFFER_ATOMIC_XOR v{{[0-9]+}}, s[{{[0-9]+}}:{{[0-9]+}}], 0{{$}}
define void @atomic_xor_i32(i32 addrspace(1)* %out, i32 %in) {
entry:
%0 = atomicrmw volatile xor i32 addrspace(1)* %out, i32 %in seq_cst
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_ret:
; SI: BUFFER_ATOMIC_XOR [[RET:v[0-9]+]], s[{{[0-9]+}}:{{[0-9]+}}], 0 glc
; SI: BUFFER_STORE_DWORD [[RET]]
define void @atomic_xor_i32_ret(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in) {
entry:
%0 = atomicrmw volatile xor i32 addrspace(1)* %out, i32 %in seq_cst
store i32 %0, i32 addrspace(1)* %out2
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_addr64:
; SI: BUFFER_ATOMIC_XOR v{{[0-9]+}}, v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64{{$}}
define void @atomic_xor_i32_addr64(i32 addrspace(1)* %out, i32 %in, i64 %index) {
entry:
%ptr = getelementptr i32 addrspace(1)* %out, i64 %index
%0 = atomicrmw volatile xor i32 addrspace(1)* %ptr, i32 %in seq_cst
ret void
}
; FUNC-LABEL: {{^}}atomic_xor_i32_ret_addr64:
; SI: BUFFER_ATOMIC_XOR [[RET:v[0-9]+]], v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 glc{{$}}
; SI: BUFFER_STORE_DWORD [[RET]]
define void @atomic_xor_i32_ret_addr64(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in, i64 %index) {
entry:
%ptr = getelementptr i32 addrspace(1)* %out, i64 %index
%0 = atomicrmw volatile xor i32 addrspace(1)* %ptr, i32 %in seq_cst
store i32 %0, i32 addrspace(1)* %out2
ret void
}