[AMDGPU] Rename AMDGPULoadTr intrinsic class. NFC.

[changpeng]

This class is not specific to "Tr"(Transpose). It is
just for a normal load.

[llvmbot]

@llvm/pr-subscribers-llvm-ir

@llvm/pr-subscribers-backend-amdgpu

Author: Changpeng Fang (changpeng)

Changes

This class is not specific to "Tr"(Transpose). It is
just for a normal load.

---

Full diff: https://github.com/llvm/llvm-project/pull/79394.diff

1 Files Affected:

• (modified) llvm/include/llvm/IR/IntrinsicsAMDGPU.td (+2-2)

diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 9eb1ac8e27befb1..1fbaf569c321335 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2755,7 +2755,7 @@ def int_amdgcn_global_atomic_fmax_num : AMDGPUAtomicRtn<llvm_anyfloat_ty>;
 
 def int_amdgcn_atomic_cond_sub_u32 : AMDGPUAtomicRtn<llvm_i32_ty>;
 
-class AMDGPULoadTr<LLVMType ptr_ty>:
+class AMDGPULoadIntrinsic<LLVMType ptr_ty>:
   Intrinsic<
     [llvm_any_ty],
     [ptr_ty],
@@ -2775,7 +2775,7 @@ class AMDGPULoadTr<LLVMType ptr_ty>:
 // <4 x half>   @llvm.amdgcn.global.load.tr.v4f16(ptr addrspace(1))  -> global_load_tr_b128
 // <4 x bfloat> @llvm.amdgcn.global.load.tr.v4bf16(ptr addrspace(1)) -> global_load_tr_b128
 
-def int_amdgcn_global_load_tr : AMDGPULoadTr<global_ptr_ty>;
+def int_amdgcn_global_load_tr : AMDGPULoadIntrinsic<global_ptr_ty>;
 
 //===----------------------------------------------------------------------===//
 // Deep learning intrinsics.