[AMDGPU] Combine add and adde, sub and sube

If one of the arguments of adde/sube is zero we can fold another
add/sub into it.

Differential Revision: https://reviews.llvm.org/D34374

llvm-svn: 305964

1 files changed, 80 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll b/llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll
index 06cc7fcad06..6026a047d88 100644
--- a/llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll
+++ b/llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll
@@ -36,6 +36,86 @@ bb:
   ret void
 }
 
+; GCN-LABEL: {{^}}add_adde:
+; GCN: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_addc_u32_e{{32|64}} v{{[0-9]+}}, {{[^,]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[CC]]
+; GCN-NOT: v_cndmask
+; GCN-NOT: v_add
+
+define amdgpu_kernel void @add_adde(i32 addrspace(1)* nocapture %arg, i32 %a) {
+bb:
+  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %x
+  %v = load i32, i32 addrspace(1)* %gep, align 4
+  %cmp = icmp ugt i32 %x, %y
+  %ext = zext i1 %cmp to i32
+  %adde = add i32 %v, %ext
+  %add2 = add i32 %adde, %a
+  store i32 %add2, i32 addrspace(1)* %gep, align 4
+  ret void
+}
+
+; GCN-LABEL: {{^}}adde_add:
+; GCN: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_addc_u32_e{{32|64}} v{{[0-9]+}}, {{[^,]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[CC]]
+; GCN-NOT: v_cndmask
+; GCN-NOT: v_add
+
+define amdgpu_kernel void @adde_add(i32 addrspace(1)* nocapture %arg, i32 %a) {
+bb:
+  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %x
+  %v = load i32, i32 addrspace(1)* %gep, align 4
+  %cmp = icmp ugt i32 %x, %y
+  %ext = zext i1 %cmp to i32
+  %add = add i32 %v, %a
+  %adde = add i32 %add, %ext
+  store i32 %adde, i32 addrspace(1)* %gep, align 4
+  ret void
+}
+
+; GCN-LABEL: {{^}}sub_sube:
+; GCN: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_subb_u32_e{{32|64}} v{{[0-9]+}}, {{[^,]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[CC]]
+; GCN-NOT: v_cndmask
+; GCN-NOT: v_sub
+
+define amdgpu_kernel void @sub_sube(i32 addrspace(1)* nocapture %arg, i32 %a) {
+bb:
+  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %x
+  %v = load i32, i32 addrspace(1)* %gep, align 4
+  %cmp = icmp ugt i32 %x, %y
+  %ext = sext i1 %cmp to i32
+  %adde = add i32 %v, %ext
+  %sub = sub i32 %adde, %a
+  store i32 %sub, i32 addrspace(1)* %gep, align 4
+  ret void
+}
+
+; GCN-LABEL: {{^}}sube_sub:
+; GCN: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_subb_u32_e{{32|64}} v{{[0-9]+}}, {{[^,]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[CC]]
+; GCN-NOT: v_cndmask
+; GCN-NOT: v_sub
+
+define amdgpu_kernel void @sube_sub(i32 addrspace(1)* nocapture %arg, i32 %a) {
+bb:
+  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %x
+  %v = load i32, i32 addrspace(1)* %gep, align 4
+  %cmp = icmp ugt i32 %x, %y
+  %ext = sext i1 %cmp to i32
+  %sub = sub i32 %v, %a
+  %adde = add i32 %sub, %ext
+  store i32 %adde, i32 addrspace(1)* %gep, align 4
+  ret void
+}
+
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 
 declare i32 @llvm.amdgcn.workitem.id.y() #0