llvm · arsenm · Nov 19, 2024 · Jan 18, 2024
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -1674,7 +1674,7 @@ class AMDGPURawBufferLoadLDS : Intrinsic <
   [],
   [llvm_v4i32_ty,             // rsrc(SGPR)
    LLVMQualPointerType<3>,    // LDS base offset
-   llvm_i32_ty,               // Data byte size: 1/2/4
+   llvm_i32_ty,               // Data byte size: 1/2/4 (/12/16 for gfx950)
    llvm_i32_ty,               // voffset(VGPR, included in bounds checking and swizzling)
    llvm_i32_ty,               // soffset(SGPR/imm, excluded from bounds checking and swizzling)
    llvm_i32_ty,               // imm offset(imm, included in bounds checking and swizzling)
@@ -1693,7 +1693,7 @@ class AMDGPURawPtrBufferLoadLDS : Intrinsic <
   [],
   [AMDGPUBufferRsrcTy,        // rsrc(SGPR)
    LLVMQualPointerType<3>,    // LDS base offset
-   llvm_i32_ty,               // Data byte size: 1/2/4
+   llvm_i32_ty,               // Data byte size: 1/2/4 (/12/16 for gfx950)
    llvm_i32_ty,               // voffset(VGPR, included in bounds checking and swizzling)
    llvm_i32_ty,               // soffset(SGPR/imm, excluded from bounds checking and swizzling)
    llvm_i32_ty,               // imm offset(imm, included in bounds checking and swizzling)
@@ -1715,7 +1715,7 @@ class AMDGPUStructBufferLoadLDS : Intrinsic <
   [],
   [llvm_v4i32_ty,             // rsrc(SGPR)
    LLVMQualPointerType<3>,    // LDS base offset
-   llvm_i32_ty,               // Data byte size: 1/2/4
+   llvm_i32_ty,               // Data byte size: 1/2/4 (/12/16 for gfx950)
    llvm_i32_ty,               // vindex(VGPR)
    llvm_i32_ty,               // voffset(VGPR, included in bounds checking and swizzling)
    llvm_i32_ty,               // soffset(SGPR/imm, excluded from bounds checking and swizzling)
@@ -1735,7 +1735,7 @@ class AMDGPUStructPtrBufferLoadLDS : Intrinsic <
   [],
   [AMDGPUBufferRsrcTy,        // rsrc(SGPR)
    LLVMQualPointerType<3>,    // LDS base offset
-   llvm_i32_ty,               // Data byte size: 1/2/4
+   llvm_i32_ty,               // Data byte size: 1/2/4 (/12/16 for gfx950)
    llvm_i32_ty,               // vindex(VGPR)
    llvm_i32_ty,               // voffset(VGPR, included in bounds checking and swizzling)
    llvm_i32_ty,               // soffset(SGPR/imm, excluded from bounds checking and swizzling)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
@@ -3240,6 +3240,24 @@ bool AMDGPUInstructionSelector::selectBufferLoadLds(MachineInstr &MI) const {
                     : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORD_LDS_OFFEN
                                  : AMDGPU::BUFFER_LOAD_DWORD_LDS_OFFSET;
     break;
+  case 12:
+    if (!Subtarget->hasLDSLoadB96_B128())
+      return false;
+
+    Opc = HasVIndex ? HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX3_LDS_BOTHEN
+                                 : AMDGPU::BUFFER_LOAD_DWORDX3_LDS_IDXEN
+                    : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX3_LDS_OFFEN
+                                 : AMDGPU::BUFFER_LOAD_DWORDX3_LDS_OFFSET;
+    break;
+  case 16:
+    if (!Subtarget->hasLDSLoadB96_B128())
+      return false;
+
+    Opc = HasVIndex ? HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX4_LDS_BOTHEN
+                                 : AMDGPU::BUFFER_LOAD_DWORDX4_LDS_IDXEN
+                    : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX4_LDS_OFFEN
+                                 : AMDGPU::BUFFER_LOAD_DWORDX4_LDS_OFFSET;
+    break;
   }
 
   MachineBasicBlock *MBB = MI.getParent();

diff --git a/llvm/lib/Target/AMDGPU/BUFInstructions.td b/llvm/lib/Target/AMDGPU/BUFInstructions.td
@@ -573,9 +573,17 @@ multiclass MUBUF_Pseudo_Loads<string opName, ValueType load_vt = i32,
   }
 }
 
-multiclass MUBUF_Pseudo_Loads_Lds<string opName, ValueType load_vt = i32> {
+multiclass MUBUF_Pseudo_Loads_Lds<string opName, ValueType load_vt = i32, Predicate LDSPred = TruePredicate> {
   defm NAME : MUBUF_Pseudo_Loads<opName, load_vt>;
-  defm _LDS : MUBUF_Pseudo_Loads<opName, load_vt, 0, 1>;
+
+  if !ne(LDSPred, TruePredicate) then {
+    let SubtargetPredicate = LDSPred in {
+      defm _LDS : MUBUF_Pseudo_Loads<opName, load_vt, 0, 1>;
+    }
+  } else {
+    defm _LDS : MUBUF_Pseudo_Loads<opName, load_vt, 0, 1>;
+  }
+
 }
 
 multiclass MUBUF_Pseudo_Loads_LDSOpc<string opName,
@@ -956,11 +964,11 @@ defm BUFFER_LOAD_DWORD : MUBUF_Pseudo_Loads_Lds <
 defm BUFFER_LOAD_DWORDX2 : MUBUF_Pseudo_Loads <
   "buffer_load_dwordx2", v2i32
 >;
-defm BUFFER_LOAD_DWORDX3 : MUBUF_Pseudo_Loads <
-  "buffer_load_dwordx3", v3i32
+defm BUFFER_LOAD_DWORDX3 : MUBUF_Pseudo_Loads_Lds <
+  "buffer_load_dwordx3", v3i32, /*LDSPred=*/HasGFX950Insts
 >;
-defm BUFFER_LOAD_DWORDX4 : MUBUF_Pseudo_Loads <
-  "buffer_load_dwordx4", v4i32
+defm BUFFER_LOAD_DWORDX4 : MUBUF_Pseudo_Loads_Lds <
+  "buffer_load_dwordx4", v4i32, /*LDSPred=*/HasGFX950Insts
 >;
 
 defm BUFFER_LOAD_LDS_B32 : MUBUF_Pseudo_Loads_LDSOpc <
@@ -3231,8 +3239,8 @@ defm BUFFER_LOAD_USHORT         : MUBUF_Real_AllAddr_Lds_vi <0x12>;
 defm BUFFER_LOAD_SSHORT         : MUBUF_Real_AllAddr_Lds_vi <0x13>;
 defm BUFFER_LOAD_DWORD          : MUBUF_Real_AllAddr_Lds_vi <0x14>;
 defm BUFFER_LOAD_DWORDX2        : MUBUF_Real_AllAddr_vi <0x15>;
-defm BUFFER_LOAD_DWORDX3        : MUBUF_Real_AllAddr_vi <0x16>;
-defm BUFFER_LOAD_DWORDX4        : MUBUF_Real_AllAddr_vi <0x17>;
+defm BUFFER_LOAD_DWORDX3        : MUBUF_Real_AllAddr_Lds_vi <0x16>;
+defm BUFFER_LOAD_DWORDX4        : MUBUF_Real_AllAddr_Lds_vi <0x17>;
 defm BUFFER_STORE_BYTE          : MUBUF_Real_AllAddr_vi <0x18>;
 defm BUFFER_STORE_BYTE_D16_HI   : MUBUF_Real_AllAddr_vi <0x19>;
 defm BUFFER_STORE_SHORT         : MUBUF_Real_AllAddr_vi <0x1a>;

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -9825,6 +9825,22 @@ SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
             : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORD_LDS_OFFEN
                          : AMDGPU::BUFFER_LOAD_DWORD_LDS_OFFSET;
       break;
+    case 12:
+      if (!Subtarget->hasLDSLoadB96_B128())
+        return SDValue();
+      Opc = HasVIndex ? HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX3_LDS_BOTHEN
+                                   : AMDGPU::BUFFER_LOAD_DWORDX3_LDS_IDXEN
+                      : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX3_LDS_OFFEN
+                                   : AMDGPU::BUFFER_LOAD_DWORDX3_LDS_OFFSET;
+      break;
+    case 16:
+      if (!Subtarget->hasLDSLoadB96_B128())
+        return SDValue();
+      Opc = HasVIndex ? HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX4_LDS_BOTHEN
+                                   : AMDGPU::BUFFER_LOAD_DWORDX4_LDS_IDXEN
+                      : HasVOffset ? AMDGPU::BUFFER_LOAD_DWORDX4_LDS_OFFEN
+                                   : AMDGPU::BUFFER_LOAD_DWORDX4_LDS_OFFSET;
+      break;
     }
 
     SDValue M0Val = copyToM0(DAG, Chain, DL, Op.getOperand(3));

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.global.load.lds.gfx950.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.global.load.lds.gfx950.ll
@@ -2,6 +2,14 @@
 ; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950,GFX950-SDAG %s
 ; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950,GFX950-GISEL %s
 
+; RUN: not --crash llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx940 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-SDAG %s
+; RUN: not --crash llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx940 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-GISEL %s
+
+; ERR-SDAG: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.global.load.lds
+
+; ERR-GISEL: LLVM ERROR: cannot select: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.global.load.lds),
+
+
 declare void @llvm.amdgcn.global.load.lds(ptr addrspace(1) nocapture %gptr, ptr addrspace(3) nocapture %lptr, i32 %size, i32 %offset, i32 %aux)
 
 ;---------------------------------------------------------------------y

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.buffer.load.lds.gfx950.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.buffer.load.lds.gfx950.ll
@@ -0,0 +1,176 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950,GFX950-SDAG %s
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950,GFX950-GISEL %s
+; RUN: not --crash llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx940 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-SDAG %s
+; RUN: not --crash llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx940 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-GISEL %s
+
+; FIXME: Not a great error
+; ERR-SDAG: LLVM ERROR: Do not know how to expand this operator's operand!
+; ERR-GISEL: LLVM ERROR: cannot select: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.raw.ptr.buffer.load.lds),
+
+declare void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) nocapture, i32 %size, i32 %voffset, i32 %soffset, i32 %offset, i32 %aux)
+
+;---------------------------------------------------------------------y
+; dwordx3
+;---------------------------------------------------------------------
+
+define amdgpu_ps float @buffer_load_lds_dwordx3(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
+; GFX950-LABEL: buffer_load_lds_dwordx3:
+; GFX950:       ; %bb.0: ; %main_body
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 lds
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 offset:4 sc0 lds
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 offset:8 nt lds
+; GFX950-NEXT:    v_mov_b32_e32 v0, s4
+; GFX950-NEXT:    s_waitcnt vmcnt(0)
+; GFX950-NEXT:    ds_read_b32 v0, v0
+; GFX950-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX950-NEXT:    ; return to shader part epilog
+main_body:
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 0, i32 0)
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 4, i32 1)
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 8, i32 2)
+  %res = load float, ptr addrspace(3) %lds
+  ret float %res
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx3_imm_voffset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
+; GFX950-LABEL: buffer_load_lds_dwordx3_imm_voffset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    v_mov_b32_e32 v0, 0x800
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx3 v0, s[0:3], 0 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 2048, i32 0, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx3_v_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx3_v_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx3 v0, s[0:3], 0 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %voffset, i32 0, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx3_s_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx3_s_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx3 off, s[0:3], s5 lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 0, i32 %soffset, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx3_vs_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx3_vs_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx3 v0, s[0:3], s5 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %voffset, i32 %soffset, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx3_vs_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx3_vs_imm_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx3 v0, s[0:3], s5 offen offset:2048 lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %voffset, i32 %soffset, i32 2048, i32 0)
+  ret void
+}
+
+;---------------------------------------------------------------------y
+; dwordx4
+;---------------------------------------------------------------------
+
+define amdgpu_ps float @buffer_load_lds_dwordx4(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
+; GFX950-LABEL: buffer_load_lds_dwordx4:
+; GFX950:       ; %bb.0: ; %main_body
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 lds
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 offset:4 sc0 lds
+; GFX950-NEXT:    buffer_load_dword off, s[0:3], 0 offset:8 nt lds
+; GFX950-NEXT:    v_mov_b32_e32 v0, s4
+; GFX950-NEXT:    s_waitcnt vmcnt(0)
+; GFX950-NEXT:    ds_read_b32 v0, v0
+; GFX950-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX950-NEXT:    ; return to shader part epilog
+main_body:
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 0, i32 0)
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 4, i32 1)
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 4, i32 0, i32 0, i32 8, i32 2)
+  %res = load float, ptr addrspace(3) %lds
+  ret float %res
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx4_imm_voffset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
+; GFX950-LABEL: buffer_load_lds_dwordx4_imm_voffset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    v_mov_b32_e32 v0, 0x800
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx4 v0, s[0:3], 0 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 2048, i32 0, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx4_v_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx4_v_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx4 v0, s[0:3], 0 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %voffset, i32 0, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx4_s_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx4_s_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx4 off, s[0:3], s5 lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 0, i32 %soffset, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx4_vs_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx4_vs_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx4 v0, s[0:3], s5 offen lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %voffset, i32 %soffset, i32 0, i32 0)
+  ret void
+}
+
+define amdgpu_ps void @buffer_load_lds_dwordx4_vs_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %voffset, i32 inreg %soffset) {
+; GFX950-LABEL: buffer_load_lds_dwordx4_vs_imm_offset:
+; GFX950:       ; %bb.0:
+; GFX950-NEXT:    s_mov_b32 m0, s4
+; GFX950-NEXT:    s_nop 0
+; GFX950-NEXT:    buffer_load_dwordx4 v0, s[0:3], s5 offen offset:2048 lds
+; GFX950-NEXT:    s_endpgm
+  call void @llvm.amdgcn.raw.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %voffset, i32 %soffset, i32 2048, i32 0)
+  ret void
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; GFX950-GISEL: {{.*}}
+; GFX950-SDAG: {{.*}}