mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
d773f533b9
Summary: GCNSchedStrategy re-uses most of GenericScheduler, it's just uses a different method to compute the excess and critical register pressure limits. It's not enabled by default, to enable it you need to pass -misched=gcn to llc. Shader DB stats: 32464 shaders in 17874 tests Totals: SGPRS: 1542846 -> 1643125 (6.50 %) VGPRS: 1005595 -> 904653 (-10.04 %) Spilled SGPRs: 29929 -> 27745 (-7.30 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 36688188 -> 37034900 (0.95 %) bytes LDS: 1913 -> 1913 (0.00 %) blocks Max Waves: 254101 -> 265125 (4.34 %) Wait states: 0 -> 0 (0.00 %) Totals from affected shaders: SGPRS: 1338220 -> 1438499 (7.49 %) VGPRS: 886221 -> 785279 (-11.39 %) Spilled SGPRs: 29869 -> 27685 (-7.31 %) Spilled VGPRs: 334 -> 352 (5.39 %) Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread Code Size: 34315716 -> 34662428 (1.01 %) bytes LDS: 1551 -> 1551 (0.00 %) blocks Max Waves: 188127 -> 199151 (5.86 %) Wait states: 0 -> 0 (0.00 %) Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick Subscribers: arsenm, kzhuravl, llvm-commits Differential Revision: https://reviews.llvm.org/D23688 llvm-svn: 279995
38 lines
1.4 KiB
LLVM
38 lines
1.4 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=kaveri -mtriple=amdgcn-unknown-amdhsa -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Check that when mubuf addr64 instruction is handled in moveToVALU
|
|
; from the pointer, dead register writes are not emitted.
|
|
|
|
; FIXME: We should be able to use the SGPR directly as src0 to v_add_i32
|
|
|
|
; GCN-LABEL: {{^}}clobber_vgpr_pair_pointer_add:
|
|
; GCN-DAG: s_load_dwordx2 s{{\[}}[[ARG1LO:[0-9]+]]:[[ARG1HI:[0-9]+]]{{\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x0{{$}}
|
|
; GCN-DAG: buffer_load_dwordx2 v{{\[}}[[LDPTRLO:[0-9]+]]:[[LDPTRHI:[0-9]+]]{{\]}}
|
|
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: v_mov_b32_e32 v[[VARG1LO:[0-9]+]], s[[ARG1LO]]
|
|
; GCN-NOT: v_mov_b32
|
|
; GCN: v_mov_b32_e32 v[[VARG1HI:[0-9]+]], s[[ARG1HI]]
|
|
; GCN-NOT: v_mov_b32
|
|
|
|
; GCN: v_add_i32_e32 v[[PTRLO:[0-9]+]], vcc, v[[LDPTRLO]], v[[VARG1LO]]
|
|
; GCN: v_addc_u32_e32 v[[PTRHI:[0-9]+]], vcc, v[[LDPTRHI]], v[[VARG1HI]]
|
|
; GCN: buffer_load_ubyte v{{[0-9]+}}, v{{\[}}[[PTRLO]]:[[PTRHI]]{{\]}},
|
|
|
|
define void @clobber_vgpr_pair_pointer_add(i64 %arg1, i8 addrspace(1)* addrspace(1)* %ptrarg, i32 %arg3) #0 {
|
|
bb:
|
|
%tmp = icmp sgt i32 %arg3, 0
|
|
br i1 %tmp, label %bb4, label %bb17
|
|
|
|
bb4:
|
|
%tmp14 = load volatile i8 addrspace(1)*, i8 addrspace(1)* addrspace(1)* %ptrarg
|
|
%tmp15 = getelementptr inbounds i8, i8 addrspace(1)* %tmp14, i64 %arg1
|
|
%tmp16 = load volatile i8, i8 addrspace(1)* %tmp15
|
|
br label %bb17
|
|
|
|
bb17:
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|