Mercurial > hg > CbC > CbC_llvm
view llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.dwordx3.ll @ 266:00f31e85ec16 default tip
Added tag current for changeset 31d058e83c98
author | Shinji KONO <kono@ie.u-ryukyu.ac.jp> |
---|---|
date | Sat, 14 Oct 2023 10:13:55 +0900 |
parents | 1f2b6ac9f198 |
children |
line wrap: on
line source
;RUN: llc < %s -march=amdgcn -mcpu=gfx600 -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,SI ;RUN: llc < %s -march=amdgcn -mcpu=gfx700 -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,GCNX3 ;CHECK-LABEL: {{^}}buffer_load_format_immoffs_x3: ;SI: buffer_load_format_xyzw v[0:3], off, s[0:3], 0 offset:42 ;GCNX3: buffer_load_format_xyz v[0:2], off, s[0:3], 0 offset:42 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_load_format_immoffs_x3(<4 x i32> inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.buffer.load.format.v3f32(<4 x i32> %0, i32 0, i32 42, i1 0, i1 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}buffer_load_immoffs_x3: ;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40 ;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_load_immoffs_x3(<4 x i32> inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.buffer.load.v3f32(<4 x i32> %0, i32 0, i32 40, i1 0, i1 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}buffer_raw_load_immoffs_x3: ;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40 ;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_raw_load_immoffs_x3(<4 x i32> inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32> %0, i32 40, i32 0, i32 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}buffer_struct_load_format_immoffs_x3: ;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42 ;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_struct_load_format_immoffs_x3(<4 x i32> inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32> %0, i32 0, i32 42, i32 0, i32 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}struct_buffer_load_immoffs_x3: ;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40 ;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @struct_buffer_load_immoffs_x3(<4 x i32> inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32> %0, i32 0, i32 40, i32 0, i32 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}buffer_raw_ptr_load_immoffs_x3: ;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40 ;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_raw_ptr_load_immoffs_x3(ptr addrspace(8) inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 40, i32 0, i32 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}buffer_struct_ptr_load_format_immoffs_x3: ;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42 ;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @buffer_struct_ptr_load_format_immoffs_x3(ptr addrspace(8) inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8) %0, i32 0, i32 42, i32 0, i32 0) ret <3 x float> %data } ;CHECK-LABEL: {{^}}struct_ptr_buffer_load_immoffs_x3: ;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40 ;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40 ;CHECK: s_waitcnt define amdgpu_ps <3 x float> @struct_ptr_buffer_load_immoffs_x3(ptr addrspace(8) inreg) { main_body: %data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 0, i32 40, i32 0, i32 0) ret <3 x float> %data } declare <3 x float> @llvm.amdgcn.buffer.load.format.v3f32(<4 x i32>, i32, i32, i1, i1) #0 declare <3 x float> @llvm.amdgcn.buffer.load.v3f32(<4 x i32>, i32, i32, i1, i1) #0 declare <3 x float> @llvm.amdgcn.raw.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32>, i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32>, i32, i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0 declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0