maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Restored selection of scalar_to_vector (v2x16) 

This works if DAG combiner is enabled, but without combining
we cannot select scalar_to_vector of <2 x half> and <2 x i16>.

Differential Revision: https://reviews.llvm.org/D54718

llvm-svn: 347259
This commit is contained in:
Stanislav Mekhanoshin 2018-11-19 19:58:13 +00:00
parent d677c3fc61
commit 8bafbae889
2 changed files with 34 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/lib/Target/AMDGPU/SIInstructions.td
View File

@ -1537,15 +1537,15 @@ def : GCNPat <
} // End SubtargetPredicate = HasVOP3PInsts
// def : GCNPat <
// (v2f16 (scalar_to_vector f16:$src0)),
// (COPY $src0)
// >;
def : GCNPat <
(v2f16 (scalar_to_vector f16:$src0)),
(COPY $src0)
>;
// def : GCNPat <
// (v2i16 (scalar_to_vector i16:$src0)),
// (COPY $src0)
// >;
def : GCNPat <
(v2i16 (scalar_to_vector i16:$src0)),
(COPY $src0)
>;
def : GCNPat <
(v4i16 (scalar_to_vector i16:$src0)),

26
llvm/test/CodeGen/AMDGPU/scalar_to_vector_v2x16.ll Normal file
View File

@ -0,0 +1,26 @@
; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-OPT %s
; RUN: llc -march=amdgcn -mcpu=fiji -O0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-NOOPT %s
; GCN-LABEL: {{^}}scalar_to_vector_i16:
; GCN-NOOPT: s_mov_b32 [[S:s[0-9]+]], 42
; GCN-NOOPT: v_mov_b32_e32 [[V:v[0-9]+]], [[S]]
; GCN-OPT: v_mov_b32_e32 [[V:v[0-9]+]], 42
; GCN: buffer_store_short [[V]],
define void @scalar_to_vector_i16() {
%tmp = load <2 x i16>, <2 x i16> addrspace(5)* undef
%tmp1 = insertelement <2 x i16> %tmp, i16 42, i64 0
store <2 x i16> %tmp1, <2 x i16> addrspace(5)* undef
ret void
}
; GCN-LABEL: {{^}}scalar_to_vector_f16:
; GCN-NOOPT: s_movk_i32 [[S:s[0-9]+]], 0x3c00
; GCN-NOOPT: v_mov_b32_e32 [[V:v[0-9]+]], [[S]]
; GCN-OPT: v_mov_b32_e32 [[V:v[0-9]+]], 0x3c00
; GCN: buffer_store_short [[V]],
define void @scalar_to_vector_f16() {
%tmp = load <2 x half>, <2 x half> addrspace(5)* undef
%tmp1 = insertelement <2 x half> %tmp, half 1.0, i64 0
store <2 x half> %tmp1, <2 x half> addrspace(5)* undef
ret void
}