mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-07 12:30:44 +00:00
4a5c408c28
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 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@279995 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
1.1 KiB
LLVM
31 lines
1.1 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=SI %s
|
|
|
|
@ptr_load = addrspace(3) global i32 addrspace(2)* undef, align 8
|
|
|
|
; Make sure when the load from %ptr2 is folded the chain isn't lost,
|
|
; resulting in losing the store to gptr
|
|
|
|
; FUNC-LABEL: {{^}}missing_store_reduced:
|
|
; SI: s_load_dwordx2
|
|
; SI: ds_read_b64
|
|
; SI-DAG: buffer_store_dword
|
|
; SI-DAG: v_readfirstlane_b32 s[[PTR_LO:[0-9]+]], v{{[0-9]+}}
|
|
; SI: v_readfirstlane_b32 s[[PTR_HI:[0-9]+]], v{{[0-9]+}}
|
|
; SI: s_nop 3
|
|
; SI: s_load_dword s{{[0-9]+}}, s{{\[}}[[PTR_LO]]:[[PTR_HI]]{{\]}}
|
|
; SI: buffer_store_dword
|
|
; SI: s_endpgm
|
|
define void @missing_store_reduced(i32 addrspace(1)* %out, i32 addrspace(1)* %gptr) #0 {
|
|
%ptr0 = load i32 addrspace(2)*, i32 addrspace(2)* addrspace(3)* @ptr_load, align 8
|
|
%ptr2 = getelementptr inbounds i32, i32 addrspace(2)* %ptr0, i64 2
|
|
|
|
store i32 99, i32 addrspace(1)* %gptr, align 4
|
|
%tmp2 = load i32, i32 addrspace(2)* %ptr2, align 4
|
|
|
|
store i32 %tmp2, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
|