AMDGCN/SI: Implement readlane/readfirstlane intrinsics

Summary:
  This patch implements readlane/readfirstlane intrinsics.
TODO: need to define a new register class to consider the case
that the source could be a vector register or M0.

Reviewed by:
  arsenm and tstellarAMD

Differential Revision:
  http://reviews.llvm.org/D22489

llvm-svn: 279660

llvm/include/llvm/IR/IntrinsicsAMDGPU.td

@@ -552,6 +552,14 @@ def int_amdgcn_fcmp :
   Intrinsic<[llvm_i64_ty], [llvm_anyfloat_ty, LLVMMatchType<0>, llvm_i32_ty],
             [IntrNoMem, IntrConvergent]>;
 
+def int_amdgcn_readfirstlane :
+  GCCBuiltin<"__builtin_amdgcn_readfirstlane">,
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrConvergent]>;
+
+def int_amdgcn_readlane :
+  GCCBuiltin<"__builtin_amdgcn_readlane">,
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;
+
 //===----------------------------------------------------------------------===//
 // CI+ Intrinsics
 //===----------------------------------------------------------------------===//

llvm/lib/Target/AMDGPU/SIInstructions.td

@@ -1066,9 +1066,9 @@ let Uses = [EXEC] in {
 def V_READFIRSTLANE_B32 : VOP1 <
   0x00000002,
   (outs SReg_32:$vdst),
-  (ins VS_32:$src0),
+  (ins VGPR_32:$src0),
   "v_readfirstlane_b32 $vdst, $src0",
-  []
+  [(set i32:$vdst, (int_amdgcn_readfirstlane i32:$src0))]
 > {
   let isConvergent = 1;
 }
@@ -1447,8 +1447,9 @@ defm V_READLANE_B32 : VOP2SI_3VI_m <
   vop3 <0x001, 0x289>,
   "v_readlane_b32",
   (outs SReg_32:$vdst),
-  (ins VS_32:$src0, SCSrc_32:$src1),
-  "v_readlane_b32 $vdst, $src0, $src1"
+  (ins VGPR_32:$src0, SCSrc_32:$src1),
+  "v_readlane_b32 $vdst, $src0, $src1",
+  [(set i32:$vdst, (int_amdgcn_readlane i32:$src0, i32:$src1))]
 >;
 
 defm V_WRITELANE_B32 : VOP2SI_3VI_m <

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.readfirstlane.ll

@@ -0,0 +1,35 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+
+declare i32 @llvm.amdgcn.readfirstlane(i32) #0
+
+; CHECK-LABEL: {{^}}test_readfirstlane:
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, v{{[0-9]+}}
+define void @test_readfirstlane(i32 addrspace(1)* %out, i32 %src) #1 {
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %src)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readfirstlane_imm:
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
+define void @test_readfirstlane_imm(i32 addrspace(1)* %out) #1 {
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 32)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; TODO: m0 should be folded.
+; CHECK-LABEL: {{^}}test_readfirstlane_m0:
+; CHECK: s_mov_b32 m0, -1
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
+define void @test_readfirstlane_m0(i32 addrspace(1)* %out) #1 {
+  %m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %m0)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+attributes #0 = { nounwind readnone convergent }
+attributes #1 = { nounwind }

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.readlane.ll

@@ -0,0 +1,43 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+
+declare i32 @llvm.amdgcn.readlane(i32, i32) #0
+
+; CHECK-LABEL: {{^}}test_readlane_sreg:
+; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, s{{[0-9]+}}
+define void @test_readlane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readlane_imm_sreg:
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
+; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
+define void @test_readlane_imm_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 32, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; TODO: m0 should be folded.
+; CHECK-LABEL: {{^}}test_readlane_m0_sreg:
+; CHECK: s_mov_b32 m0, -1
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
+; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
+define void @test_readlane_m0_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
+  %m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %m0, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readlane_imm:
+; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, 32
+define void @test_readlane_imm(i32 addrspace(1)* %out, i32 %src0) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 32) #0
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+attributes #0 = { nounwind readnone convergent }
+attributes #1 = { nounwind }