Skip to content

[AMDGPU][Clang] Builtin for GLOBAL_LOAD_LDS on GFX940 #92962

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

Merged
merged 1 commit into from
May 22, 2024
Merged

[AMDGPU][Clang] Builtin for GLOBAL_LOAD_LDS on GFX940 #92962

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
1 change: 1 addition & 0 deletions clang/include/clang/Basic/BuiltinsAMDGPU.def
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,7 @@ TARGET_BUILTIN(__builtin_amdgcn_flat_atomic_fadd_v2bf16, "V2sV2s*0V2s", "t", "at
TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fadd_v2bf16, "V2sV2s*1V2s", "t", "atomic-global-pk-add-bf16-inst")
TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_v2bf16, "V2sV2s*3V2s", "t", "atomic-ds-pk-add-16-insts")
TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_v2f16, "V2hV2h*3V2h", "t", "atomic-ds-pk-add-16-insts")
TARGET_BUILTIN(__builtin_amdgcn_global_load_lds, "vv*1v*3UiiUi", "t", "gfx940-insts")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

clang should really be enforcing the valid immediate values for the size


//===----------------------------------------------------------------------===//
// Deep learning builtins.
Expand Down
52 changes: 52 additions & 0 deletions clang/test/CodeGenOpenCL/builtins-amdgcn-gfx940.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -triple amdgcn-unknown-unknown -target-cpu gfx940 -emit-llvm -o - %s | FileCheck %s
// REQUIRES: amdgpu-registered-target

typedef unsigned int u32;
typedef unsigned short u16;
typedef unsigned char u8;

// CHECK-LABEL: @test_global_load_lds_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 4, i32 0, i32 0)
// CHECK-NEXT: ret void
//
void test_global_load_lds_u32(global u32* src, local u32 *dst) {
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/4, /*offset=*/0, /*aux=*/0);
}

// CHECK-LABEL: @test_global_load_lds_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 2, i32 0, i32 0)
// CHECK-NEXT: ret void
//
void test_global_load_lds_u16(global u16* src, local u16 *dst) {
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/2, /*offset=*/0, /*aux=*/0);
}

// CHECK-LABEL: @test_global_load_lds_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 1, i32 0, i32 0)
// CHECK-NEXT: ret void
//
void test_global_load_lds_u8(global u8* src, local u8 *dst) {
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/1, /*offset=*/0, /*aux=*/0);
}
31 changes: 14 additions & 17 deletions llvm/include/llvm/IR/IntrinsicsAMDGPU.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2466,23 +2466,20 @@ def int_amdgcn_perm :
// GFX9 Intrinsics
//===----------------------------------------------------------------------===//

class AMDGPUGlobalLoadLDS : Intrinsic <
[],
[LLVMQualPointerType<1>, // Base global pointer to load from
LLVMQualPointerType<3>, // LDS base pointer to store to
llvm_i32_ty, // Data byte size: 1/2/4
llvm_i32_ty, // imm offset (applied to both global and LDS address)
llvm_i32_ty], // auxiliary data (imm, cachepolicy (bit 0 = glc/sc0,
// bit 1 = slc/sc1,
// bit 2 = dlc on gfx10/gfx11))
// bit 4 = scc/nt on gfx90a+))
// gfx12+:
// cachepolicy (bits [0-2] = th,
// bits [3-4] = scope)
// swizzled buffer (bit 6 = swz),
[IntrWillReturn, NoCapture<ArgIndex<0>>, NoCapture<ArgIndex<1>>,
ImmArg<ArgIndex<2>>, ImmArg<ArgIndex<3>>, ImmArg<ArgIndex<4>>, IntrNoCallback, IntrNoFree],
"", [SDNPMemOperand]>;
class AMDGPUGlobalLoadLDS :
ClangBuiltin<"__builtin_amdgcn_global_load_lds">,
Intrinsic <
[],
[LLVMQualPointerType<1>, // Base global pointer to load from
LLVMQualPointerType<3>, // LDS base pointer to store to
llvm_i32_ty, // Data byte size: 1/2/4 (/12/16 for gfx950)
llvm_i32_ty, // imm offset (applied to both global and LDS address)
llvm_i32_ty], // auxiliary data (imm, cachepolicy (bit 0 = sc0,
// bit 1 = sc1,
// bit 4 = scc))
[IntrWillReturn, NoCapture<ArgIndex<0>>, NoCapture<ArgIndex<1>>,
ImmArg<ArgIndex<2>>, ImmArg<ArgIndex<3>>, ImmArg<ArgIndex<4>>, IntrNoCallback, IntrNoFree],
"", [SDNPMemOperand]>;
def int_amdgcn_global_load_lds : AMDGPUGlobalLoadLDS;

//===----------------------------------------------------------------------===//
Expand Down
Loading