From 1a94cbb3f54b8f856deacbc366dddd92d1875e36 Mon Sep 17 00:00:00 2001 From: Nicolai Haehnle Date: Thu, 29 Nov 2018 11:06:06 +0000 Subject: AMDGPU/InsertWaitcnts: Untangle some semi-global state Summary: Reduce the statefulness of the algorithm in two ways: 1. More clearly split generateWaitcntInstBefore into two phases: the first one which determines the required wait, if any, without changing the ScoreBrackets, and the second one which actually inserts the wait and updates the brackets. 2. Communicate pre-existing s_waitcnt instructions using an argument to generateWaitcntInstBefore instead of through the ScoreBrackets. To simplify these changes, a Waitcnt structure is introduced which carries the counts of an s_waitcnt instruction in decoded form. There are some functional changes: 1. The FIXME for the VCCZ bug workaround was implemented: we only wait for SMEM instructions as required instead of waiting on all counters. 2. We now properly track pre-existing waitcnt's in all cases, which leads to less conservative waitcnts being emitted in some cases. s_load_dword ... s_waitcnt lgkmcnt(0) <-- pre-existing wait count ds_read_b32 v0, ... ds_read_b32 v1, ... s_waitcnt lgkmcnt(0) <-- this is too conservative use(v0) more code use(v1) This increases code size a bit, but the reduced latency should still be a win in basically all cases. The worst code size regressions in my shader-db are: WORST REGRESSIONS - Code Size Before After Delta Percentage 1724 1736 12 0.70 % shaders/private/f1-2015/1334.shader_test [0] 2276 2284 8 0.35 % shaders/private/f1-2015/1306.shader_test [0] 4632 4640 8 0.17 % shaders/private/ue4_elemental/62.shader_test [0] 2376 2384 8 0.34 % shaders/private/f1-2015/1308.shader_test [0] 3284 3292 8 0.24 % shaders/private/talos_principle/1955.shader_test [0] Reviewers: msearles, rampitec, scott.linder, kanarayan Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam Differential Revision: https://reviews.llvm.org/D54226 llvm-svn: 347848 --- llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp') diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp index c43389a13b8..1cce9812dd1 100644 --- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp +++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp @@ -522,6 +522,14 @@ void decodeWaitcnt(const IsaVersion &Version, unsigned Waitcnt, Lgkmcnt = decodeLgkmcnt(Version, Waitcnt); } +Waitcnt decodeWaitcnt(const IsaVersion &Version, unsigned Encoded) { + Waitcnt Decoded; + Decoded.VmCnt = decodeVmcnt(Version, Encoded); + Decoded.ExpCnt = decodeExpcnt(Version, Encoded); + Decoded.LgkmCnt = decodeLgkmcnt(Version, Encoded); + return Decoded; +} + unsigned encodeVmcnt(const IsaVersion &Version, unsigned Waitcnt, unsigned Vmcnt) { Waitcnt = @@ -552,6 +560,10 @@ unsigned encodeWaitcnt(const IsaVersion &Version, return Waitcnt; } +unsigned encodeWaitcnt(const IsaVersion &Version, const Waitcnt &Decoded) { + return encodeWaitcnt(Version, Decoded.VmCnt, Decoded.ExpCnt, Decoded.LgkmCnt); +} + unsigned getInitialPSInputAddr(const Function &F) { return getIntegerAttribute(F, "InitialPSInputAddr", 0); } -- cgit v1.2.3