R600/SI: Implement i64 ctpop

[oota-llvm.git] / test / CodeGen / R600 / add.ll

diff --git a/test/CodeGen/R600/add.ll b/test/CodeGen/R600/add.ll
index 3d5506bfa5d2fd0c9d9e026f3f07ca29e6338c19..711a2bc417741b06f2a04f17838c4f8b8307bd99 100644 (file)
--- a/test/CodeGen/R600/add.ll
+++ b/test/CodeGen/R600/add.ll
@@ -1,10 +1,9 @@
-; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
-; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI-CHECK %s
+; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK --check-prefix=FUNC %s
+; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI-CHECK --check-prefix=FUNC %s
 
-;EG-CHECK-LABEL: @test1:
+;FUNC-LABEL: @test1:
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-;SI-CHECK-LABEL: @test1:
 ;SI-CHECK: V_ADD_I32_e32 [[REG:v[0-9]+]], {{v[0-9]+, v[0-9]+}}
 ;SI-CHECK-NOT: [[REG]]
 ;SI-CHECK: BUFFER_STORE_DWORD [[REG]],
@@ -17,11 +16,10 @@ define void @test1(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
   ret void
 }
 
-;EG-CHECK-LABEL: @test2:
+;FUNC-LABEL: @test2:
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-;SI-CHECK-LABEL: @test2:
 ;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 ;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 
@@ -34,13 +32,12 @@ define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
   ret void
 }
 
-;EG-CHECK-LABEL: @test4:
+;FUNC-LABEL: @test4:
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 ;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
 
-;SI-CHECK-LABEL: @test4:
 ;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 ;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
 ;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
@@ -54,3 +51,117 @@ define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
   store <4 x i32> %result, <4 x i32> addrspace(1)* %out
   ret void
 }
+
+; FUNC-LABEL: @test8
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+define void @test8(<8 x i32> addrspace(1)* %out, <8 x i32> %a, <8 x i32> %b) {
+entry:
+  %0 = add <8 x i32> %a, %b
+  store <8 x i32> %0, <8 x i32> addrspace(1)* %out
+  ret void
+}
+
+; FUNC-LABEL: @test16
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; EG-CHECK: ADD_INT
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADD_I32
+define void @test16(<16 x i32> addrspace(1)* %out, <16 x i32> %a, <16 x i32> %b) {
+entry:
+  %0 = add <16 x i32> %a, %b
+  store <16 x i32> %0, <16 x i32> addrspace(1)* %out
+  ret void
+}
+
+; FUNC-LABEL: @add64
+; SI-CHECK: S_ADD_I32
+; SI-CHECK: S_ADDC_U32
+define void @add64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
+entry:
+  %0 = add i64 %a, %b
+  store i64 %0, i64 addrspace(1)* %out
+  ret void
+}
+
+; The V_ADDC_U32 and V_ADD_I32 instruction can't read SGPRs, because they
+; use VCC.  The test is designed so that %a will be stored in an SGPR and
+; %0 will be stored in a VGPR, so the comiler will be forced to copy %a
+; to a VGPR before doing the add.
+
+; FUNC-LABEL: @add64_sgpr_vgpr
+; SI-CHECK-NOT: V_ADDC_U32_e32 s
+define void @add64_sgpr_vgpr(i64 addrspace(1)* %out, i64 %a, i64 addrspace(1)* %in) {
+entry:
+  %0 = load i64 addrspace(1)* %in
+  %1 = add i64 %a, %0
+  store i64 %1, i64 addrspace(1)* %out
+  ret void
+}
+
+; Test i64 add inside a branch.  We don't allow SALU instructions inside of
+; branches.
+; FIXME: We are being conservative here.  We could allow this in some cases.
+; FUNC-LABEL: @add64_in_branch
+; SI-CHECK-NOT: S_ADD_I32
+; SI-CHECK-NOT: S_ADDC_U32
+define void @add64_in_branch(i64 addrspace(1)* %out, i64 addrspace(1)* %in, i64 %a, i64 %b, i64 %c) {
+entry:
+  %0 = icmp eq i64 %a, 0
+  br i1 %0, label %if, label %else
+
+if:
+  %1 = load i64 addrspace(1)* %in
+  br label %endif
+
+else:
+  %2 = add i64 %a, %b
+  br label %endif
+
+endif:
+  %3 = phi i64 [%1, %if], [%2, %else]
+  store i64 %3, i64 addrspace(1)* %out
+  ret void
+}