diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/sub.v2i16.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/sub.v2i16.ll | 24 |
1 files changed, 13 insertions, 11 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/sub.v2i16.ll b/llvm/test/CodeGen/AMDGPU/sub.v2i16.ll index 42bd2ff..cd1c532 100644 --- a/llvm/test/CodeGen/AMDGPU/sub.v2i16.ll +++ b/llvm/test/CodeGen/AMDGPU/sub.v2i16.ll @@ -1,9 +1,9 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,GFX9 -; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,VI -; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX10 -; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX11,GFX11-TRUE16 -; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX11,GFX11-FAKE16 +; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,GFX9 +; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck %s -enable-var-scope -check-prefixes=GCN,VI +; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX10 +; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=-flat-for-global < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX11,GFX11-TRUE16 +; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=-flat-for-global < %s | FileCheck %s -enable-var-scope -check-prefixes=GFX11,GFX11-FAKE16 ; FIXME: Need to handle non-uniform case for function below (load without gep). define amdgpu_kernel void @v_test_sub_v2i16(ptr addrspace(1) %out, ptr addrspace(1) %in0, ptr addrspace(1) %in1) #1 { @@ -813,7 +813,8 @@ define amdgpu_kernel void @v_test_sub_v2i16_zext_to_v2i64(ptr addrspace(1) %out, ; GFX11-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 ; GFX11-TRUE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34 ; GFX11-TRUE16-NEXT: v_and_b32_e32 v0, 0x3ff, v0 -; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-TRUE16-NEXT: v_mov_b16_e32 v2.l, 0 +; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) ; GFX11-TRUE16-NEXT: v_lshlrev_b32_e32 v0, 2, v0 ; GFX11-TRUE16-NEXT: s_waitcnt lgkmcnt(0) ; GFX11-TRUE16-NEXT: global_load_b32 v1, v0, s[2:3] glc dlc @@ -824,11 +825,12 @@ define amdgpu_kernel void @v_test_sub_v2i16_zext_to_v2i64(ptr addrspace(1) %out, ; GFX11-TRUE16-NEXT: s_mov_b32 s2, -1 ; GFX11-TRUE16-NEXT: v_pk_sub_i16 v0, v1, v0 ; GFX11-TRUE16-NEXT: v_mov_b32_e32 v1, 0 -; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2) -; GFX11-TRUE16-NEXT: v_lshrrev_b32_e32 v2, 16, v0 -; GFX11-TRUE16-NEXT: v_dual_mov_b32 v3, v1 :: v_dual_and_b32 v0, 0xffff, v0 -; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) -; GFX11-TRUE16-NEXT: v_lshl_or_b32 v2, 0, 16, v2 +; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2) +; GFX11-TRUE16-NEXT: v_lshrrev_b32_e32 v3, 16, v0 +; GFX11-TRUE16-NEXT: v_mov_b16_e32 v0.h, v2.l +; GFX11-TRUE16-NEXT: v_lshl_or_b32 v2, v2, 16, v3 +; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_4) +; GFX11-TRUE16-NEXT: v_mov_b32_e32 v3, v1 ; GFX11-TRUE16-NEXT: buffer_store_b128 v[0:3], off, s[0:3], 0 ; GFX11-TRUE16-NEXT: s_endpgm ; |