DAGCombiner: Combine extract_vector_elt from build_vector

This basic combine was surprisingly missing.
AMDGPU legalizes many operations in terms of 32-bit vector components,
so not doing this results in many extra copies and subregister extracts
that need to be cleaned up later.

InstCombine already does this for the hasOneUse case. The target hook
is to fix a handful of tests which break (e.g. ARM/vmov.ll) which turn
from a vector materialize repeated immediate instruction to a constant
vector load with more scalar copies from it.

llvm-svn: 250129

1 files changed, 25 insertions, 9 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/gep-address-space.ll b/llvm/test/CodeGen/AMDGPU/gep-address-space.ll
index 471b0f6b13e..f5ab390ce68 100644
--- a/llvm/test/CodeGen/AMDGPU/gep-address-space.ll
+++ b/llvm/test/CodeGen/AMDGPU/gep-address-space.ll
@@ -11,24 +11,35 @@ define void @use_gep_address_space([1024 x i32] addrspace(3)* %array) nounwind {
   ret void
 }
 
-define void @use_gep_address_space_large_offset([1024 x i32] addrspace(3)* %array) nounwind {
 ; CHECK-LABEL: {{^}}use_gep_address_space_large_offset:
 ; The LDS offset will be 65536 bytes, which is larger than the size of LDS on
 ; SI, which is why it is being OR'd with the base pointer.
 ; SI: s_or_b32
 ; CI: s_add_i32
 ; CHECK: ds_write_b32
+define void @use_gep_address_space_large_offset([1024 x i32] addrspace(3)* %array) nounwind {
   %p = getelementptr [1024 x i32], [1024 x i32] addrspace(3)* %array, i16 0, i16 16384
   store i32 99, i32 addrspace(3)* %p
   ret void
 }
 
-define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind {
 ; CHECK-LABEL: {{^}}gep_as_vector_v4:
-; CHECK: s_add_i32
-; CHECK: s_add_i32
-; CHECK: s_add_i32
-; CHECK: s_add_i32
+; SI: s_add_i32
+; SI: s_add_i32
+; SI: s_add_i32
+; SI: s_add_i32
+
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CHECK: s_endpgm
+define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind {
   %p = getelementptr [1024 x i32], <4 x [1024 x i32] addrspace(3)*> %array, <4 x i16> zeroinitializer, <4 x i16> <i16 16, i16 16, i16 16, i16 16>
   %p0 = extractelement <4 x i32 addrspace(3)*> %p, i32 0
   %p1 = extractelement <4 x i32 addrspace(3)*> %p, i32 1
@@ -41,10 +52,15 @@ define void @gep_as_vector_v4(<4 x [1024 x i32] addrspace(3)*> %array) nounwind
   ret void
 }
 
-define void @gep_as_vector_v2(<2 x [1024 x i32] addrspace(3)*> %array) nounwind {
 ; CHECK-LABEL: {{^}}gep_as_vector_v2:
-; CHECK: s_add_i32
-; CHECK: s_add_i32
+; SI: s_add_i32
+; SI: s_add_i32
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
+; CHECK: s_endpgm
+define void @gep_as_vector_v2(<2 x [1024 x i32] addrspace(3)*> %array) nounwind {
   %p = getelementptr [1024 x i32], <2 x [1024 x i32] addrspace(3)*> %array, <2 x i16> zeroinitializer, <2 x i16> <i16 16, i16 16>
   %p0 = extractelement <2 x i32 addrspace(3)*> %p, i32 0
   %p1 = extractelement <2 x i32 addrspace(3)*> %p, i32 1