maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/implicit-def-muse.ll

24 lines
754 B
LLVM
Raw Normal View History

[SelectionDAG] Enhance the simplification of `copyto` from `implicit-def`. Summary: - The current implementation simplifies the case where the source of `copyto` is `implicit-def`ed. However, it only works when that `implicit-def` is single-used since it detects that from `implicit-def` and cannot determine which destination vreg should be used if there are multiple uses. - This patch changes that detection when `copyto` is being emitted. If that `copyto`'s source is defined from `implicit-def`, it simplifies it. Hence, it works even that `implicit-def` is multi-used. - Except it simplifies the internal IR, it won't improve the quality of code generation. However, it helps to detect 'implicit-def` in a straight-forward manner in some passes, such as `si-i1-copies`. A test case is added. Reviewers: sunfish, nhaehnle Subscribers: jvesely, hiraditya, asbirlea, llvm-commits, yaxunl Tags: #llvm Differential Revision: https://reviews.llvm.org/D62342 llvm-svn: 361777
2019-05-28 02:26:29 +08:00
; RUN: llc -march=amdgcn -stop-after=amdgpu-isel -verify-machineinstrs -o - %s | FileCheck %s
; CHECK-LABEL: vcopy_i1_undef
AMDGPU: Decompose all values to 32-bit pieces for calling conventions This is the more natural lowering, and presents more opportunities to reduce 64-bit ops to 32-bit. This should also help avoid issues graphics shaders have had with 64-bit values, and simplify argument lowering in globalisel. llvm-svn: 366578
2019-07-19 21:57:44 +08:00
; CHECK: [[IMPDEF0:%[0-9]+]]:vreg_1 = IMPLICIT_DEF
[SelectionDAG] Enhance the simplification of `copyto` from `implicit-def`. Summary: - The current implementation simplifies the case where the source of `copyto` is `implicit-def`ed. However, it only works when that `implicit-def` is single-used since it detects that from `implicit-def` and cannot determine which destination vreg should be used if there are multiple uses. - This patch changes that detection when `copyto` is being emitted. If that `copyto`'s source is defined from `implicit-def`, it simplifies it. Hence, it works even that `implicit-def` is multi-used. - Except it simplifies the internal IR, it won't improve the quality of code generation. However, it helps to detect 'implicit-def` in a straight-forward manner in some passes, such as `si-i1-copies`. A test case is added. Reviewers: sunfish, nhaehnle Subscribers: jvesely, hiraditya, asbirlea, llvm-commits, yaxunl Tags: #llvm Differential Revision: https://reviews.llvm.org/D62342 llvm-svn: 361777
2019-05-28 02:26:29 +08:00
; CHECK-NOT: COPY
AMDGPU: Decompose all values to 32-bit pieces for calling conventions This is the more natural lowering, and presents more opportunities to reduce 64-bit ops to 32-bit. This should also help avoid issues graphics shaders have had with 64-bit values, and simplify argument lowering in globalisel. llvm-svn: 366578
2019-07-19 21:57:44 +08:00
; CHECK: [[IMPDEF1:%[0-9]+]]:vreg_1 = IMPLICIT_DEF
; CHECK-NOT: COPY [[IMPDEF0]]
; CHECK-NOT: COPY [[IMPDEF1]]
[SelectionDAG] Enhance the simplification of `copyto` from `implicit-def`. Summary: - The current implementation simplifies the case where the source of `copyto` is `implicit-def`ed. However, it only works when that `implicit-def` is single-used since it detects that from `implicit-def` and cannot determine which destination vreg should be used if there are multiple uses. - This patch changes that detection when `copyto` is being emitted. If that `copyto`'s source is defined from `implicit-def`, it simplifies it. Hence, it works even that `implicit-def` is multi-used. - Except it simplifies the internal IR, it won't improve the quality of code generation. However, it helps to detect 'implicit-def` in a straight-forward manner in some passes, such as `si-i1-copies`. A test case is added. Reviewers: sunfish, nhaehnle Subscribers: jvesely, hiraditya, asbirlea, llvm-commits, yaxunl Tags: #llvm Differential Revision: https://reviews.llvm.org/D62342 llvm-svn: 361777
2019-05-28 02:26:29 +08:00
; CHECK: .false:
define <2 x float> @vcopy_i1_undef(<2 x float> addrspace(1)* %p) {
entry:
br i1 undef, label %exit, label %false
false:
%x = load <2 x float>, <2 x float> addrspace(1)* %p
%cmp = fcmp one <2 x float> %x, zeroinitializer
br label %exit
exit:
%c = phi <2 x i1> [ undef, %entry ], [ %cmp, %false ]
%ret = select <2 x i1> %c, <2 x float> <float 2.0, float 2.0>, <2 x float> <float 4.0, float 4.0>
ret <2 x float> %ret
}