mirror of
https://github.com/RPCSX/llvm.git
synced 2026-01-31 01:05:23 +01:00
d019e8638a
This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292982 91177308-0d34-0410-b5e6-96231b3b80d8
39 lines
1.7 KiB
LLVM
39 lines
1.7 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
|
|
|
|
; GCN-LABEL: {{^}}reduce_i64_load_align_4_width_to_i32:
|
|
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; GCN: v_and_b32_e32 v{{[0-9]+}}, 0x12d687, [[VAL]]
|
|
; GCN: buffer_store_dwordx2
|
|
define void @reduce_i64_load_align_4_width_to_i32(i64 addrspace(1)* %out, i64 addrspace(1)* %in) #0 {
|
|
%a = load i64, i64 addrspace(1)* %in, align 4
|
|
%and = and i64 %a, 1234567
|
|
store i64 %and, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt0:
|
|
; GCN: buffer_load_dword [[VAL:v[0-9]+]]
|
|
; GCN: buffer_store_dword [[VAL]]
|
|
define void @reduce_i64_align_4_bitcast_v2i32_elt0(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 {
|
|
%a = load i64, i64 addrspace(1)* %in, align 4
|
|
%vec = bitcast i64 %a to <2 x i32>
|
|
%elt0 = extractelement <2 x i32> %vec, i32 0
|
|
store i32 %elt0, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt1:
|
|
; GCN: buffer_load_dword [[VAL:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:4
|
|
; GCN: buffer_store_dword [[VAL]]
|
|
define void @reduce_i64_align_4_bitcast_v2i32_elt1(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 {
|
|
%a = load i64, i64 addrspace(1)* %in, align 4
|
|
%vec = bitcast i64 %a to <2 x i32>
|
|
%elt0 = extractelement <2 x i32> %vec, i32 1
|
|
store i32 %elt0, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|