AMDGPU: Add baseline test for frame index folding

We currently can increse the instruction count
when a frame index requires materialization.

Author: arsenm

llvm/test/CodeGen/AMDGPU/fold-operands-frame-index.gfx10.mir

@@ -0,0 +1,87 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck %s
+
+---
+name:  fold_frame_index__v_add_u32_e32__const_v_fi
+tracksRegLiveness: true
+frameInfo:
+  maxAlignment:    4
+  localFrameSize:  16384
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_frame_index__v_add_u32_e32__const_v_fi
+    ; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    ; CHECK-NEXT: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, [[V_MOV_B32_e32_]], implicit $exec
+    ; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_U32_e32_]]
+    ; CHECK-NEXT: SI_RETURN implicit $vgpr0
+    %0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    %1:vgpr_32 = V_ADD_U32_e32 128, %0, implicit $exec
+    $vgpr0 = COPY %1
+    SI_RETURN implicit $vgpr0
+...
+
+---
+name:  fold_frame_index__v_add_co_u32_e64__v_fi_const
+tracksRegLiveness: true
+frameInfo:
+  maxAlignment:    4
+  localFrameSize:  16384
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__v_fi_const
+    ; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    ; CHECK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_32 = V_ADD_CO_U32_e64 [[V_MOV_B32_e32_]], 128, 0, implicit $exec
+    ; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
+    ; CHECK-NEXT: SI_RETURN implicit $vgpr0
+    %0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    %1:vgpr_32, %2:sreg_32 = V_ADD_CO_U32_e64 %0, 128, 0, implicit $exec
+    $vgpr0 = COPY %1
+    SI_RETURN implicit $vgpr0
+...
+
+---
+name:  fold_frame_index__v_add_co_u32_e64___fi_const_v
+tracksRegLiveness: true
+frameInfo:
+  maxAlignment:    4
+  localFrameSize:  16384
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64___fi_const_v
+    ; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    ; CHECK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_32 = V_ADD_CO_U32_e64 128, [[V_MOV_B32_e32_]], 0, implicit $exec
+    ; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
+    ; CHECK-NEXT: SI_RETURN implicit $vgpr0
+    %0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    %1:vgpr_32, %2:sreg_32 = V_ADD_CO_U32_e64 128, %0, 0, implicit $exec
+    $vgpr0 = COPY %1
+    SI_RETURN implicit $vgpr0
+...
+
+---
+name:  fold_frame_index__v_add_co_u32_e64__v_fi_imm
+tracksRegLiveness: true
+frameInfo:
+  maxAlignment:    4
+  localFrameSize:  16384
+stack:
+  - { id: 0, size: 16384, alignment: 4, local-offset: 0 }
+body:             |
+  bb.0:
+    ; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__v_fi_imm
+    ; CHECK: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_32 = V_ADD_CO_U32_e64 %stack.0, 64, 0, implicit $exec
+    ; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
+    ; CHECK-NEXT: SI_RETURN implicit $vgpr0
+    %0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
+    %1:vgpr_32, %2:sreg_32 = V_ADD_CO_U32_e64 %0, 64, 0, implicit $exec
+    $vgpr0 = COPY %1
+    SI_RETURN implicit $vgpr0
+...
+