replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[AMDGPU] Add llvm.amdgpu.update.dpp intrinsic 

Summary:
Now that we've made all the necessary backend changes, we can add a new
intrinsic which exposes the new capabilities to IR producers. Since
llvm.amdgpu.update.dpp is a strict superset of llvm.amdgpu.mov.dpp, we
should deprecate the former. We also add tests for all the functionality
that was added in previous changes, now that we can access it via an IR
construct.

Reviewers: tstellar, arsenm

Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye

Differential Revision: https://reviews.llvm.org/D34718

llvm-svn: 310399
This commit is contained in:
Connor Abbott 2017-08-08 18:52:22 +00:00
parent 4d852597f8
commit 249fc7bd2a
3 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/include/llvm/IR/IntrinsicsAMDGPU.td
View File

@ -788,6 +788,15 @@ def int_amdgcn_mov_dpp :
[LLVMMatchType<0>, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty,
llvm_i1_ty], [IntrNoMem, IntrConvergent]>;
// llvm.amdgcn.update.dpp.i32 <old> <src> <dpp_ctrl> <row_mask> <bank_mask> <bound_ctrl>
// Should be equivalent to:
// v_mov_b32 <dest> <old>
// v_mov_b32 <dest> <src> <dpp_ctrl> <row_mask> <bank_mask> <bound_ctrl>
def int_amdgcn_update_dpp :
Intrinsic<[llvm_anyint_ty],
[LLVMMatchType<0>, LLVMMatchType<0>, llvm_i32_ty, llvm_i32_ty,
llvm_i32_ty, llvm_i1_ty], [IntrNoMem, IntrConvergent]>;
def int_amdgcn_s_dcache_wb :
GCCBuiltin<"__builtin_amdgcn_s_dcache_wb">,
Intrinsic<[], [], []>;

8
llvm/lib/Target/AMDGPU/VOP1Instructions.td
View File

@ -663,6 +663,14 @@ def : Pat <
(as_i1imm $bound_ctrl))
>;
def : Pat <
(i32 (int_amdgcn_update_dpp i32:$old, i32:$src, imm:$dpp_ctrl, imm:$row_mask,
imm:$bank_mask, imm:$bound_ctrl)),
(V_MOV_B32_dpp $old, $src, (as_i32imm $dpp_ctrl),
(as_i32imm $row_mask), (as_i32imm $bank_mask),
(as_i1imm $bound_ctrl))
>;
def : Pat<
(i32 (anyext i16:$src)),
(COPY $src)

17
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll Normal file
View File

@ -0,0 +1,17 @@
; 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
; VI-LABEL: {{^}}dpp_test:
; VI: v_mov_b32_e32 v0, s{{[0-9]+}}
; VI: v_mov_b32_e32 v1, s{{[0-9]+}}
; VI: s_nop 1
; 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]
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
store i32 %tmp0, i32 addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1) #0
attributes #0 = { nounwind readnone convergent }