R600/SI: Fix B64 VALU shifts on VI

SI only has standard versions. VI only has REV versions.

Tested-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 228037

4 files changed, 44 insertions, 40 deletions

diff --git a/llvm/test/CodeGen/R600/rotl.i64.ll b/llvm/test/CodeGen/R600/rotl.i64.ll
index f094ecef98f..6da17a4fea9 100644
--- a/llvm/test/CodeGen/R600/rotl.i64.ll
+++ b/llvm/test/CodeGen/R600/rotl.i64.ll
@@ -1,12 +1,12 @@
-; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=BOTH %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=BOTH %s
 
-; FUNC-LABEL: {{^}}s_rotl_i64:
-; SI-DAG: s_lshl_b64
-; SI-DAG: s_sub_i32
-; SI-DAG: s_lshr_b64
-; SI: s_or_b64
-; SI: s_endpgm
+; BOTH-LABEL: {{^}}s_rotl_i64:
+; BOTH-DAG: s_lshl_b64
+; BOTH-DAG: s_sub_i32
+; BOTH-DAG: s_lshr_b64
+; BOTH: s_or_b64
+; BOTH: s_endpgm
 define void @s_rotl_i64(i64 addrspace(1)* %in, i64 %x, i64 %y) {
 entry:
   %0 = shl i64 %x, %y
@@ -17,13 +17,15 @@ entry:
   ret void
 }
 
-; FUNC-LABEL: {{^}}v_rotl_i64:
+; BOTH-LABEL: {{^}}v_rotl_i64:
 ; SI-DAG: v_lshl_b64
-; SI-DAG: v_sub_i32
+; VI-DAG: v_lshlrev_b64
+; BOTH-DAG: v_sub_i32
 ; SI: v_lshr_b64
-; SI: v_or_b32
-; SI: v_or_b32
-; SI: s_endpgm
+; VI: v_lshrrev_b64
+; BOTH: v_or_b32
+; BOTH: v_or_b32
+; BOTH: s_endpgm
 define void @v_rotl_i64(i64 addrspace(1)* %in, i64 addrspace(1)* %xptr, i64 addrspace(1)* %yptr) {
 entry:
   %x = load i64 addrspace(1)* %xptr, align 8
diff --git a/llvm/test/CodeGen/R600/rotr.i64.ll b/llvm/test/CodeGen/R600/rotr.i64.ll
index a637f71921e..f1d1d265f36 100644
--- a/llvm/test/CodeGen/R600/rotr.i64.ll
+++ b/llvm/test/CodeGen/R600/rotr.i64.ll
@@ -1,11 +1,11 @@
-; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
-; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=BOTH %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=BOTH %s
 
-; FUNC-LABEL: {{^}}s_rotr_i64:
-; SI-DAG: s_sub_i32
-; SI-DAG: s_lshr_b64
-; SI-DAG: s_lshl_b64
-; SI: s_or_b64
+; BOTH-LABEL: {{^}}s_rotr_i64:
+; BOTH-DAG: s_sub_i32
+; BOTH-DAG: s_lshr_b64
+; BOTH-DAG: s_lshl_b64
+; BOTH: s_or_b64
 define void @s_rotr_i64(i64 addrspace(1)* %in, i64 %x, i64 %y) {
 entry:
   %tmp0 = sub i64 64, %y
@@ -16,12 +16,14 @@ entry:
   ret void
 }
 
-; FUNC-LABEL: {{^}}v_rotr_i64:
-; SI-DAG: v_sub_i32
+; BOTH-LABEL: {{^}}v_rotr_i64:
+; BOTH-DAG: v_sub_i32
 ; SI-DAG: v_lshr_b64
 ; SI-DAG: v_lshl_b64
-; SI: v_or_b32
-; SI: v_or_b32
+; VI-DAG: v_lshrrev_b64
+; VI-DAG: v_lshlrev_b64
+; BOTH: v_or_b32
+; BOTH: v_or_b32
 define void @v_rotr_i64(i64 addrspace(1)* %in, i64 addrspace(1)* %xptr, i64 addrspace(1)* %yptr) {
 entry:
   %x = load i64 addrspace(1)* %xptr, align 8
@@ -34,7 +36,7 @@ entry:
   ret void
 }
 
-; FUNC-LABEL: {{^}}s_rotr_v2i64:
+; BOTH-LABEL: {{^}}s_rotr_v2i64:
 define void @s_rotr_v2i64(<2 x i64> addrspace(1)* %in, <2 x i64> %x, <2 x i64> %y) {
 entry:
   %tmp0 = sub <2 x i64> <i64 64, i64 64>, %y
@@ -45,7 +47,7 @@ entry:
   ret void
 }
 
-; FUNC-LABEL: {{^}}v_rotr_v2i64:
+; BOTH-LABEL: {{^}}v_rotr_v2i64:
 define void @v_rotr_v2i64(<2 x i64> addrspace(1)* %in, <2 x i64> addrspace(1)* %xptr, <2 x i64> addrspace(1)* %yptr) {
 entry:
   %x = load <2 x i64> addrspace(1)* %xptr, align 8
diff --git a/llvm/test/CodeGen/R600/shl.ll b/llvm/test/CodeGen/R600/shl.ll
index ff2f0960b65..c6a18bf8e54 100644
--- a/llvm/test/CodeGen/R600/shl.ll
+++ b/llvm/test/CodeGen/R600/shl.ll
@@ -66,7 +66,7 @@ define void @shl_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in
 ;SI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK: {{^}}shl_i64:
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @shl_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %in) {
   %b_ptr = getelementptr i64 addrspace(1)* %in, i64 1
@@ -104,8 +104,8 @@ define void @shl_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %in) {
 ;SI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK: {{^}}shl_v2i64:
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @shl_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in) {
   %b_ptr = getelementptr <2 x i64> addrspace(1)* %in, i64 1
@@ -165,10 +165,10 @@ define void @shl_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in
 ;SI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK: {{^}}shl_v4i64:
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_lshl_b64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_lshlrev_b64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @shl_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> addrspace(1)* %in) {
   %b_ptr = getelementptr <4 x i64> addrspace(1)* %in, i64 1
diff --git a/llvm/test/CodeGen/R600/sra.ll b/llvm/test/CodeGen/R600/sra.ll
index 44c11013056..7b461caa755 100644
--- a/llvm/test/CodeGen/R600/sra.ll
+++ b/llvm/test/CodeGen/R600/sra.ll
@@ -85,7 +85,7 @@ entry:
 ;SI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK-LABEL: {{^}}ashr_i64_2:
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @ashr_i64_2(i64 addrspace(1)* %out, i64 addrspace(1)* %in) {
 entry:
@@ -128,8 +128,8 @@ entry:
 ;SI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK-LABEL: {{^}}ashr_v2i64:
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @ashr_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in) {
   %b_ptr = getelementptr <2 x i64> addrspace(1)* %in, i64 1
@@ -197,10 +197,10 @@ define void @ashr_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %i
 ;SI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
 
 ;VI-CHECK-LABEL: {{^}}ashr_v4i64:
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
-;VI-CHECK: v_ashr_i64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v[0-9]+}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
+;VI-CHECK: v_ashrrev_i64 {{v\[[0-9]+:[0-9]+\], v[0-9]+, v\[[0-9]+:[0-9]+\]}}
 
 define void @ashr_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> addrspace(1)* %in) {
   %b_ptr = getelementptr <4 x i64> addrspace(1)* %in, i64 1