3 files changed, 73 insertions, 35 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
index 18ede50f40c..752357998bd 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
@@ -1,14 +1,15 @@
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-OPT %s
-; RUN: llc -O0 -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-NOOPT %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=VI,VI-OPT,PREGFX10,PREGFX10-OPT %s
+; RUN: llc -O0 -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=VI,VI-NOOPT,PREGFX10,PREGFX10-NOOPT %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=VI,VI-OPT %s
 
 ; FIXME: The register allocator / scheduler should be able to avoid these hazards.
 
 ; VI-LABEL: {{^}}dpp_test:
 ; VI: v_mov_b32_e32 v0, s{{[0-9]+}}
 ; VI-NOOPT: v_mov_b32_e32 v1, s{{[0-9]+}}
-; VI-OPT: s_nop 1
-; VI-NOOPT: s_nop 0
-; VI-NOOPT: s_nop 0
+; PREGFX10-OPT: s_nop 1
+; PREGFX10-NOOPT: s_nop 0
+; PREGFX10-NOOPT: s_nop 0
 ; VI-OPT: v_mov_b32_dpp v0, v0 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x00,0x01,0x08,0x11]
 ; VI-NOOPT: v_mov_b32_dpp v0, v1 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x01,0x01,0x08,0x11]
 define amdgpu_kernel void @dpp_test(i32 addrspace(1)* %out, i32 %in) {
@@ -20,14 +21,14 @@ define amdgpu_kernel void @dpp_test(i32 addrspace(1)* %out, i32 %in) {
 ; VI-LABEL: {{^}}dpp_wait_states:
 ; VI-NOOPT: v_mov_b32_e32 [[VGPR1:v[0-9]+]], s{{[0-9]+}}
 ; VI: v_mov_b32_e32 [[VGPR0:v[0-9]+]], s{{[0-9]+}}
-; VI-OPT: s_nop 1
-; VI-NOOPT: s_nop 0
-; VI-NOOPT: s_nop 0
+; PREGFX10-OPT: s_nop 1
+; PREGFX10-NOOPT: s_nop 0
+; PREGFX10-NOOPT: s_nop 0
 ; VI-OPT: v_mov_b32_dpp [[VGPR0]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 ; VI-NOOPT: v_mov_b32_dpp [[VGPR1]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:
-; VI-OPT: s_nop 1
-; VI-NOOPT: s_nop 0
-; VI-NOOPT: s_nop 0
+; PREGFX10-OPT: s_nop 1
+; PREGFX10-NOOPT: s_nop 0
+; PREGFX10-NOOPT: s_nop 0
 ; VI-OPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 ; VI-NOOPT: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 define amdgpu_kernel void @dpp_wait_states(i32 addrspace(1)* %out, i32 %in) {
@@ -39,16 +40,16 @@ define amdgpu_kernel void @dpp_wait_states(i32 addrspace(1)* %out, i32 %in) {
 
 ; VI-LABEL: {{^}}dpp_first_in_bb:
 ; VI: ; %endif
-; VI-OPT: s_mov_b32
-; VI-OPT: s_mov_b32
-; VI-NOOPT: s_waitcnt
-; VI-NOOPT-NEXT: s_nop 0
+; PREGFX10-OPT: s_mov_b32
+; PREGFX10-OPT: s_mov_b32
+; PREGFX10-NOOPT: s_waitcnt
+; PREGFX10-NOOPT-NEXT: s_nop 0
 ; VI: v_mov_b32_dpp [[VGPR0:v[0-9]+]], v{{[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-; VI-OPT: s_nop 1
+; PREGFX10-OPT: s_nop 1
 ; VI: v_mov_b32_dpp [[VGPR1:v[0-9]+]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
-; VI-OPT: s_nop 1
-; VI-NOOPT: s_nop 0
-; VI-NOOPT: s_nop 0
+; PREGFX10-OPT: s_nop 1
+; PREGFX10-NOOPT: s_nop 0
+; PREGFX10-NOOPT: s_nop 0
 ; VI: v_mov_b32_dpp v{{[0-9]+}}, [[VGPR1]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 define amdgpu_kernel void @dpp_first_in_bb(float addrspace(1)* %out, float addrspace(1)* %in, float %cond, float %a, float %b) {
   %cmp = fcmp oeq float %cond, 0.0
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp8.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp8.ll
new file mode 100644
index 00000000000..d77a7a1b38d
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp8.ll
@@ -0,0 +1,26 @@
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GFX10 %s
+
+; GFX10-LABEL: {{^}}dpp8_test:
+; GFX10: v_mov_b32_e32 [[SRC:v[0-9]+]], s{{[0-9]+}}
+; GFX10: v_mov_b32_dpp [[SRC]], [[SRC]]  dpp8:[1,0,0,0,0,0,0,0]{{$}}
+define amdgpu_kernel void @dpp8_test(i32 addrspace(1)* %out, i32 %in) {
+  %tmp0 = call i32 @llvm.amdgcn.mov.dpp8.i32(i32 %in, i32 1) #0
+  store i32 %tmp0, i32 addrspace(1)* %out
+  ret void
+}
+
+; GFX10-LABEL: {{^}}dpp8_wait_states:
+; GFX10-NOOPT: v_mov_b32_e32 [[VGPR1:v[0-9]+]], s{{[0-9]+}}
+; GFX10: v_mov_b32_e32 [[VGPR0:v[0-9]+]], s{{[0-9]+}}
+; GFX10: v_mov_b32_dpp [[VGPR0]], [[VGPR0]] dpp8:[1,0,0,0,0,0,0,0]{{$}}
+; GFX10: v_mov_b32_dpp [[VGPR0]], [[VGPR0]] dpp8:[5,0,0,0,0,0,0,0]{{$}}
+define amdgpu_kernel void @dpp8_wait_states(i32 addrspace(1)* %out, i32 %in) {
+  %tmp0 = call i32 @llvm.amdgcn.mov.dpp8.i32(i32 %in, i32 1) #0
+  %tmp1 = call i32 @llvm.amdgcn.mov.dpp8.i32(i32 %tmp0, i32 5) #0
+  store i32 %tmp1, i32 addrspace(1)* %out
+  ret void
+}
+
+declare i32 @llvm.amdgcn.mov.dpp8.i32(i32, i32) #0
+
+attributes #0 = { nounwind readnone convergent }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
index bfd70e72b39..bfe491d9e8c 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
@@ -1,26 +1,37 @@
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-dpp-combine=false -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-OPT %s
-; RUN: llc -O0 -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-dpp-combine=false -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-NOOPT %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-dpp-combine=false -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX8 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -amdgpu-dpp-combine=false -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10 %s
 
-; VI-LABEL: {{^}}dpp_test:
-; VI: v_mov_b32_e32 v0, s{{[0-9]+}}
-; VI: v_mov_b32_e32 v1, s{{[0-9]+}}
-; VI-OPT: s_nop 1
-; VI-NOOPT: s_nop 0
-; VI-NOOPT: s_nop 0
-; VI: v_mov_b32_dpp v0, v1 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x01,0x01,0x08,0x11]
+; GCN-LABEL: {{^}}dpp_test:
+; GCN:  v_mov_b32_e32 [[DST:v[0-9]+]], s{{[0-9]+}}
+; GCN:  v_mov_b32_e32 [[SRC:v[0-9]+]], s{{[0-9]+}}
+; GFX8: s_nop 1
+; GCN:  v_mov_b32_dpp [[DST]], [[SRC]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1{{$}}
 define amdgpu_kernel void @dpp_test(i32 addrspace(1)* %out, i32 %in1, i32 %in2) {
-  %tmp0 = call i32 @llvm.amdgcn.update.dpp.i32(i32 %in1, i32 %in2, i32 1, i32 1, i32 1, i1 1) #0
+  %tmp0 = call i32 @llvm.amdgcn.update.dpp.i32(i32 %in1, i32 %in2, i32 1, i32 1, i32 1, i1 0) #0
   store i32 %tmp0, i32 addrspace(1)* %out
   ret void
 }
 
+; GCN-LABEL: {{^}}dpp_test_bc:
+; GCN:  v_mov_b32_e32 [[DST:v[0-9]+]], s{{[0-9]+}}
+; GCN:  v_mov_b32_e32 [[SRC:v[0-9]+]], s{{[0-9]+}}
+; GFX8: s_nop 1
+; GCN:  v_mov_b32_dpp [[DST]], [[SRC]] quad_perm:[2,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0{{$}}
+define amdgpu_kernel void @dpp_test_bc(i32 addrspace(1)* %out, i32 %in1, i32 %in2) {
+  %tmp0 = call i32 @llvm.amdgcn.update.dpp.i32(i32 %in1, i32 %in2, i32 2, i32 1, i32 1, i1 1) #0
+  store i32 %tmp0, i32 addrspace(1)* %out
+  ret void
+}
+
+
 ; VI-LABEL: {{^}}dpp_test1:
-; VI-OPT: v_add_u32_e32 [[REG:v[0-9]+]], vcc, v{{[0-9]+}}, v{{[0-9]+}}
-; VI-NOOPT: v_add_u32_e64 [[REG:v[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, v{{[0-9]+}}
-; VI-NOOPT: v_mov_b32_e32 v{{[0-9]+}}, 0
-; VI-NEXT: s_nop 0
-; VI-NEXT: s_nop 0
-; VI-NEXT: v_mov_b32_dpp {{v[0-9]+}}, [[REG]] quad_perm:[1,0,3,2] row_mask:0xf bank_mask:0xf
+; GFX10: v_add_nc_u32_e32 [[REG:v[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8-OPT: v_add_u32_e32 [[REG:v[0-9]+]], vcc, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8-NOOPT: v_add_u32_e64 [[REG:v[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GFX8-NOOPT: v_mov_b32_e32 v{{[0-9]+}}, 0
+; GFX8: s_nop 0
+; GFX8-NEXT: s_nop 0
+; GFX8-OPT-NEXT: v_mov_b32_dpp {{v[0-9]+}}, [[REG]] quad_perm:[1,0,3,2] row_mask:0xf bank_mask:0xf
 @0 = internal unnamed_addr addrspace(3) global [448 x i32] undef, align 4
 define weak_odr amdgpu_kernel void @dpp_test1(i32* %arg) local_unnamed_addr {
 bb: