R600/SI: Add global atomicrmw and

v2: Add separate offset/no-offset tests

Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Matt Arsenault <matthew.arsenault@amd.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220105 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/R600/AMDGPUInstructions.td b/lib/Target/R600/AMDGPUInstructions.td
index ef656b93ce04a8cbc3fb83753dff56607e162fe1..972ef1dac97969aa67dc0f870bb00402d78b4291 100644 (file)
--- a/lib/Target/R600/AMDGPUInstructions.td
+++ b/lib/Target/R600/AMDGPUInstructions.td
@@ -387,6 +387,7 @@ class global_binary_atomic_op<SDNode atomic_op> : PatFrag<
 >;
 
 def atomic_add_global : global_binary_atomic_op<atomic_load_add>;
+def atomic_and_global : global_binary_atomic_op<atomic_load_and>;
 def atomic_sub_global : global_binary_atomic_op<atomic_load_sub>;
 
 //===----------------------------------------------------------------------===//

diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td
index 5ef57b8ee61e92645a30b5f4a09ba80a1afdb13d..bc1f8392763dec7e6d8e9ef299e8da823b1c5085 100644 (file)
--- a/lib/Target/R600/SIInstructions.td
+++ b/lib/Target/R600/SIInstructions.td
@@ -908,7 +908,9 @@ defm BUFFER_ATOMIC_SUB : MUBUF_Atomic <
 //def BUFFER_ATOMIC_UMIN : MUBUF_ <0x00000036, "BUFFER_ATOMIC_UMIN", []>;
 //def BUFFER_ATOMIC_SMAX : MUBUF_ <0x00000037, "BUFFER_ATOMIC_SMAX", []>;
 //def BUFFER_ATOMIC_UMAX : MUBUF_ <0x00000038, "BUFFER_ATOMIC_UMAX", []>;
-//def BUFFER_ATOMIC_AND : MUBUF_ <0x00000039, "BUFFER_ATOMIC_AND", []>;
+defm BUFFER_ATOMIC_AND : MUBUF_Atomic <
+  0x00000039, "BUFFER_ATOMIC_AND", VReg_32, i32, atomic_and_global
+>;
 //def BUFFER_ATOMIC_OR : MUBUF_ <0x0000003a, "BUFFER_ATOMIC_OR", []>;
 //def BUFFER_ATOMIC_XOR : MUBUF_ <0x0000003b, "BUFFER_ATOMIC_XOR", []>;
 //def BUFFER_ATOMIC_INC : MUBUF_ <0x0000003c, "BUFFER_ATOMIC_INC", []>;

diff --git a/test/CodeGen/R600/global_atomics.ll b/test/CodeGen/R600/global_atomics.ll
index 9eb06b9200d6242763d44b60417568a1c187dfe3..5feecfc5812f607652c1896a1b67d3d419ef52d5 100644 (file)
--- a/test/CodeGen/R600/global_atomics.ll
+++ b/test/CodeGen/R600/global_atomics.ll
@@ -80,6 +80,86 @@ entry:
   ret void
 }
 
+; FUNC-LABEL: {{^}}atomic_and_i32_offset:
+; SI: BUFFER_ATOMIC_AND v{{[0-9]+}}, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:0x10{{$}}
+define void @atomic_and_i32_offset(i32 addrspace(1)* %out, i32 %in) {
+entry:
+  %gep = getelementptr i32 addrspace(1)* %out, i32 4
+  %0  = atomicrmw volatile and i32 addrspace(1)* %gep, i32 %in seq_cst
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_ret_offset:
+; SI: BUFFER_ATOMIC_AND [[RET:v[0-9]+]], s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:0x10 glc {{$}}
+; SI: BUFFER_STORE_DWORD [[RET]]
+define void @atomic_and_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 and i32 addrspace(1)* %gep, i32 %in seq_cst
+  store i32 %0, i32 addrspace(1)* %out2
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_addr64_offset:
+; SI: BUFFER_ATOMIC_AND v{{[0-9]+}}, v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 offset:0x10{{$}}
+define void @atomic_and_i32_addr64_offset(i32 addrspace(1)* %out, i32 %in, i64 %index) {
+entry:
+  %ptr = getelementptr i32 addrspace(1)* %out, i64 %index
+  %gep = getelementptr i32 addrspace(1)* %ptr, i32 4
+  %0  = atomicrmw volatile and i32 addrspace(1)* %gep, i32 %in seq_cst
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_ret_addr64_offset:
+; SI: BUFFER_ATOMIC_AND [[RET:v[0-9]+]], v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 offset:0x10 glc{{$}}
+; SI: BUFFER_STORE_DWORD [[RET]]
+define void @atomic_and_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 and i32 addrspace(1)* %gep, i32 %in seq_cst
+  store i32 %0, i32 addrspace(1)* %out2
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32:
+; SI: BUFFER_ATOMIC_AND v{{[0-9]+}}, s[{{[0-9]+}}:{{[0-9]+}}], 0{{$}}
+define void @atomic_and_i32(i32 addrspace(1)* %out, i32 %in) {
+entry:
+  %0  = atomicrmw volatile and i32 addrspace(1)* %out, i32 %in seq_cst
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_ret:
+; SI: BUFFER_ATOMIC_AND [[RET:v[0-9]+]], s[{{[0-9]+}}:{{[0-9]+}}], 0 glc
+; SI: BUFFER_STORE_DWORD [[RET]]
+define void @atomic_and_i32_ret(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in) {
+entry:
+  %0  = atomicrmw volatile and i32 addrspace(1)* %out, i32 %in seq_cst
+  store i32 %0, i32 addrspace(1)* %out2
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_addr64:
+; SI: BUFFER_ATOMIC_AND v{{[0-9]+}}, v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64{{$}}
+define void @atomic_and_i32_addr64(i32 addrspace(1)* %out, i32 %in, i64 %index) {
+entry:
+  %ptr = getelementptr i32 addrspace(1)* %out, i64 %index
+  %0  = atomicrmw volatile and i32 addrspace(1)* %ptr, i32 %in seq_cst
+  ret void
+}
+
+; FUNC-LABEL: {{^}}atomic_and_i32_ret_addr64:
+; SI: BUFFER_ATOMIC_AND [[RET:v[0-9]+]], v[{{[0-9]+}}:{{[0-9]+}}], s[{{[0-9]+}}:{{[0-9]+}}], 0 addr64 glc{{$}}
+; SI: BUFFER_STORE_DWORD [[RET]]
+define void @atomic_and_i32_ret_addr64(i32 addrspace(1)* %out, i32 addrspace(1)* %out2, i32 %in, i64 %index) {
+entry:
+  %ptr = getelementptr i32 addrspace(1)* %out, i64 %index
+  %0  = atomicrmw volatile and i32 addrspace(1)* %ptr, i32 %in seq_cst
+  store i32 %0, i32 addrspace(1)* %out2
+  ret void
+}
+
 ; FUNC-LABEL: {{^}}atomic_sub_i32_offset:
 ; SI: BUFFER_ATOMIC_SUB v{{[0-9]+}}, s[{{[0-9]+}}:{{[0-9]+}}], 0 offset:0x10{{$}}
 define void @atomic_sub_i32_offset(i32 addrspace(1)* %out, i32 %in) {