Skip to content

[NVPTX] Add support for local volatile memory operations #150099

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
+83 −81
Closed

[NVPTX] Add support for local volatile memory operations #150099

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -645,15 +645,17 @@ getOperationOrderings(MemSDNode *N, const NVPTXSubtarget *Subtarget) {
// Calling "example" in CUDA C++ compiled for sm_60- exhibits undefined
// behavior due to lack of Independent Forward Progress. Lowering these
// to weak memory operations in sm_60- is therefore fine.
//
// TODO: lower atomic and volatile operations to memory locations
// in local, const, and param to two PTX instructions in sm_70+:
// - the "weak" memory instruction we are currently lowering to, and
// - some other instruction that preserves the side-effect, e.g.,
// a dead dummy volatile load.
if (CodeAddrSpace == NVPTX::AddressSpace::Local ||
CodeAddrSpace == NVPTX::AddressSpace::Const ||
CodeAddrSpace == NVPTX::AddressSpace::Param) {

if (CodeAddrSpace == NVPTX::AddressSpace::Const ||
CodeAddrSpace == NVPTX::AddressSpace::Param ||
(CodeAddrSpace == NVPTX::AddressSpace::Local
&& (!N->isVolatile() || Ordering != AtomicOrdering::NotAtomic))) {
// Allow non-atomic local volatile operations
return NVPTX::Ordering::NotAtomic;
}

Expand All @@ -677,12 +679,13 @@ getOperationOrderings(MemSDNode *N, const NVPTXSubtarget *Subtarget) {
// from .generic, .global, or .shared. The behavior of PTX volatile and PTX
// atomics is undefined if the generic address does not refer to a .global or
// .shared memory location.
bool AddrGenericOrGlobalOrShared =
bool AddrGenericOrGlobalOrSharedorLocal =
(CodeAddrSpace == NVPTX::AddressSpace::Generic ||
CodeAddrSpace == NVPTX::AddressSpace::Global ||
CodeAddrSpace == NVPTX::AddressSpace::Shared ||
CodeAddrSpace == NVPTX::AddressSpace::SharedCluster);
if (!AddrGenericOrGlobalOrShared)
CodeAddrSpace == NVPTX::AddressSpace::SharedCluster ||
CodeAddrSpace == NVPTX::AddressSpace::Local);
if (!AddrGenericOrGlobalOrSharedorLocal)
return NVPTX::Ordering::NotAtomic;

bool UseRelaxedMMIO =
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/forward-ld-param.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ define i32 @test_modify_param(ptr byval([10 x i32]) %a, i32 %b, i32 %c ) {
; CHECK-NEXT: mov.b64 %rd1, test_modify_param_param_0;
; CHECK-NEXT: ld.param.b32 %r1, [test_modify_param_param_1];
; CHECK-NEXT: ld.param.b32 %r2, [test_modify_param_param_2];
; CHECK-NEXT: st.local.b32 [%rd1+2], %r1;
; CHECK-NEXT: st.volatile.local.b32 [%rd1+2], %r1;
; CHECK-NEXT: st.param.b32 [func_retval0], %r2;
; CHECK-NEXT: ret;
%p2 = getelementptr i8, ptr %a, i32 2
Expand Down
24 changes: 12 additions & 12 deletions llvm/test/CodeGen/NVPTX/load-store-scalars.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2643,9 +2643,9 @@ define void @local_volatile_i8(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_i8_param_0];
; CHECK-NEXT: ld.local.b8 %rs1, [%rd1];
; CHECK-NEXT: ld.volatile.local.b8 %rs1, [%rd1];
; CHECK-NEXT: add.s16 %rs2, %rs1, 1;
; CHECK-NEXT: st.local.b8 [%rd1], %rs2;
; CHECK-NEXT: st.volatile.local.b8 [%rd1], %rs2;
; CHECK-NEXT: ret;
%a.load = load volatile i8, ptr addrspace(5) %a
%a.add = add i8 %a.load, 1
Expand All @@ -2661,9 +2661,9 @@ define void @local_volatile_i16(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_i16_param_0];
; CHECK-NEXT: ld.local.b16 %rs1, [%rd1];
; CHECK-NEXT: ld.volatile.local.b16 %rs1, [%rd1];
; CHECK-NEXT: add.s16 %rs2, %rs1, 1;
; CHECK-NEXT: st.local.b16 [%rd1], %rs2;
; CHECK-NEXT: st.volatile.local.b16 [%rd1], %rs2;
; CHECK-NEXT: ret;
%a.load = load volatile i16, ptr addrspace(5) %a
%a.add = add i16 %a.load, 1
Expand All @@ -2679,9 +2679,9 @@ define void @local_volatile_i32(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_i32_param_0];
; CHECK-NEXT: ld.local.b32 %r1, [%rd1];
; CHECK-NEXT: ld.volatile.local.b32 %r1, [%rd1];
; CHECK-NEXT: add.s32 %r2, %r1, 1;
; CHECK-NEXT: st.local.b32 [%rd1], %r2;
; CHECK-NEXT: st.volatile.local.b32 [%rd1], %r2;
; CHECK-NEXT: ret;
%a.load = load volatile i32, ptr addrspace(5) %a
%a.add = add i32 %a.load, 1
Expand All @@ -2696,9 +2696,9 @@ define void @local_volatile_i64(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_i64_param_0];
; CHECK-NEXT: ld.local.b64 %rd2, [%rd1];
; CHECK-NEXT: ld.volatile.local.b64 %rd2, [%rd1];
; CHECK-NEXT: add.s64 %rd3, %rd2, 1;
; CHECK-NEXT: st.local.b64 [%rd1], %rd3;
; CHECK-NEXT: st.volatile.local.b64 [%rd1], %rd3;
; CHECK-NEXT: ret;
%a.load = load volatile i64, ptr addrspace(5) %a
%a.add = add i64 %a.load, 1
Expand All @@ -2714,9 +2714,9 @@ define void @local_volatile_float(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_float_param_0];
; CHECK-NEXT: ld.local.b32 %r1, [%rd1];
; CHECK-NEXT: ld.volatile.local.b32 %r1, [%rd1];
; CHECK-NEXT: add.rn.f32 %r2, %r1, 0f3F800000;
; CHECK-NEXT: st.local.b32 [%rd1], %r2;
; CHECK-NEXT: st.volatile.local.b32 [%rd1], %r2;
; CHECK-NEXT: ret;
%a.load = load volatile float, ptr addrspace(5) %a
%a.add = fadd float %a.load, 1.
Expand All @@ -2731,9 +2731,9 @@ define void @local_volatile_double(ptr addrspace(5) %a) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_double_param_0];
; CHECK-NEXT: ld.local.b64 %rd2, [%rd1];
; CHECK-NEXT: ld.volatile.local.b64 %rd2, [%rd1];
; CHECK-NEXT: add.rn.f64 %rd3, %rd2, 0d3FF0000000000000;
; CHECK-NEXT: st.local.b64 [%rd1], %rd3;
; CHECK-NEXT: st.volatile.local.b64 [%rd1], %rd3;
; CHECK-NEXT: ret;
%a.load = load volatile double, ptr addrspace(5) %a
%a.add = fadd double %a.load, 1.
Expand Down
1 change: 0 additions & 1 deletion llvm/test/CodeGen/NVPTX/load-store-sm-90.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1550,7 +1550,6 @@ define void @shared_seq_cst_volatile_cluster(ptr addrspace(3) %a, ptr addrspace(
}

;; local statespace

; CHECK-LABEL: local_unordered_cluster
define void @local_unordered_cluster(ptr addrspace(5) %a, ptr addrspace(5) %b, ptr addrspace(5) %c, ptr addrspace(5) %d, ptr addrspace(5) %e) local_unnamed_addr {
; CHECK-LABEL: local_unordered_cluster(
Expand Down
64 changes: 32 additions & 32 deletions llvm/test/CodeGen/NVPTX/load-store-vectors-256.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1280,11 +1280,11 @@ define void @local_volatile_32xi8(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_32xi8_param_0];
; CHECK-NEXT: ld.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd2, [local_volatile_32xi8_param_1];
; CHECK-NEXT: st.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: ret;
%a.load = load volatile <32 x i8>, ptr addrspace(5) %a
store volatile <32 x i8> %a.load, ptr addrspace(5) %b
Expand All @@ -1299,11 +1299,11 @@ define void @local_volatile_16xi16(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_16xi16_param_0];
; CHECK-NEXT: ld.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd2, [local_volatile_16xi16_param_1];
; CHECK-NEXT: st.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: ret;
%a.load = load volatile <16 x i16>, ptr addrspace(5) %a
store volatile <16 x i16> %a.load, ptr addrspace(5) %b
Expand All @@ -1318,11 +1318,11 @@ define void @local_volatile_16xhalf(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_16xhalf_param_0];
; CHECK-NEXT: ld.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd2, [local_volatile_16xhalf_param_1];
; CHECK-NEXT: st.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: ret;
%a.load = load volatile <16 x half>, ptr addrspace(5) %a
store volatile <16 x half> %a.load, ptr addrspace(5) %b
Expand All @@ -1337,11 +1337,11 @@ define void @local_volatile_16xbfloat(ptr addrspace(5) %a, ptr addrspace(5) %b)
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_16xbfloat_param_0];
; CHECK-NEXT: ld.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd2, [local_volatile_16xbfloat_param_1];
; CHECK-NEXT: st.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: ret;
%a.load = load volatile <16 x bfloat>, ptr addrspace(5) %a
store volatile <16 x bfloat> %a.load, ptr addrspace(5) %b
Expand All @@ -1356,11 +1356,11 @@ define void @local_volatile_8xi32(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_8xi32_param_0];
; CHECK-NEXT: ld.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r1, %r2, %r3, %r4}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v4.b32 {%r5, %r6, %r7, %r8}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd2, [local_volatile_8xi32_param_1];
; CHECK-NEXT: st.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2+16], {%r5, %r6, %r7, %r8};
; CHECK-NEXT: st.volatile.local.v4.b32 [%rd2], {%r1, %r2, %r3, %r4};
; CHECK-NEXT: ret;
%a.load = load volatile <8 x i32>, ptr addrspace(5) %a
store volatile <8 x i32> %a.load, ptr addrspace(5) %b
Expand All @@ -1374,11 +1374,11 @@ define void @local_volatile_4xi64(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_4xi64_param_0];
; CHECK-NEXT: ld.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd6, [local_volatile_4xi64_param_1];
; CHECK-NEXT: st.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: ret;
%a.load = load volatile <4 x i64>, ptr addrspace(5) %a
store volatile <4 x i64> %a.load, ptr addrspace(5) %b
Expand All @@ -1392,11 +1392,11 @@ define void @local_volatile_8xfloat(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_8xfloat_param_0];
; CHECK-NEXT: ld.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd6, [local_volatile_8xfloat_param_1];
; CHECK-NEXT: st.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: ret;
%a.load = load volatile <8 x float>, ptr addrspace(5) %a
store volatile <8 x float> %a.load, ptr addrspace(5) %b
Expand All @@ -1410,11 +1410,11 @@ define void @local_volatile_4xdouble(ptr addrspace(5) %a, ptr addrspace(5) %b) {
; CHECK-EMPTY:
; CHECK-NEXT: // %bb.0:
; CHECK-NEXT: ld.param.b64 %rd1, [local_volatile_4xdouble_param_0];
; CHECK-NEXT: ld.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd2, %rd3}, [%rd1];
; CHECK-NEXT: ld.volatile.local.v2.b64 {%rd4, %rd5}, [%rd1+16];
; CHECK-NEXT: ld.param.b64 %rd6, [local_volatile_4xdouble_param_1];
; CHECK-NEXT: st.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6+16], {%rd4, %rd5};
; CHECK-NEXT: st.volatile.local.v2.b64 [%rd6], {%rd2, %rd3};
; CHECK-NEXT: ret;
%a.load = load volatile <4 x double>, ptr addrspace(5) %a
store volatile <4 x double> %a.load, ptr addrspace(5) %b
Expand Down
Loading
Loading