WIP add llvm optimisation passes

This commit is contained in:
Luke Boswell 2024-07-31 05:22:40 +10:00
parent 67d7f0a933
commit 4c9610b147
No known key found for this signature in database
GPG key ID: F6DB3C9DB47377B0
3 changed files with 50 additions and 1 deletions

View file

@ -3,5 +3,6 @@
// See github.com/roc-lang/roc/issues/800 for discussion of the large_enum_variant check.
#![allow(clippy::large_enum_variant)]
pub mod link;
mod llvm_passes;
pub mod program;
pub mod target;

View file

@ -0,0 +1,16 @@
use roc_mono::ir::OptLevel;
// generated using "opt --passes="default<Oz>" --print-pipeline-passes example.ll"
pub fn get_llvm_passes_str(opt_level: OptLevel) -> &'static str {
match opt_level {
OptLevel::Development | OptLevel::Normal => {
"always-inline,coro-cond(coro-early,cgscc(coro-split),coro-cleanup,globaldce),function(annotation-remarks),verify"
},
OptLevel::Size => {
"annotation2metadata,forceattrs,inferattrs,coro-early,function<eager-inv>(lower-expect,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;no-switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,sroa<modify-cfg>,early-cse<>),openmp-opt,ipsccp,called-value-propagation,globalopt,function<eager-inv>(mem2reg,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>),always-inline,require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,aggressive-instcombine,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<no-header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<no-nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop(loop-idiom,indvars,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>),function-attrs,function(require<should-not-run-function-passes>),coro-split)),deadargelim,coro-cleanup,globalopt,globaldce,elim-avail-extern,rpo-function-attrs,recompute-globalsaa,function<eager-inv>(float2int,lower-constant-intrinsics,loop(loop-rotate<no-header-duplication;no-prepare-for-lto>,loop-deletion),loop-distribute,inject-tli-mappings,loop-vectorize<no-interleave-forced-only;vectorize-forced-only;>,infer-alignment,loop-load-elim,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,simplifycfg<bonus-inst-threshold=1;forward-switch-cond;switch-range-to-icmp;switch-to-lookup;no-keep-loops;hoist-common-insts;sink-common-insts;speculate-blocks;simplify-cond-branch>,vector-combine,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop-unroll<O2>,transform-warning,sroa<preserve-cfg>,infer-alignment,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop-mssa(licm<allowspeculation>),alignment-from-assumptions,loop-sink,instsimplify,div-rem-pairs,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>),globaldce,constmerge,cg-profile,rel-lookup-table-converter,function(annotation-remarks),verify"
},
OptLevel::Optimize => {
"annotation2metadata,forceattrs,inferattrs,coro-early,function<eager-inv>(lower-expect,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;no-switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,sroa<modify-cfg>,early-cse<>,callsite-splitting),openmp-opt,ipsccp,called-value-propagation,globalopt,function<eager-inv>(mem2reg,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>),always-inline,require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop(loop-idiom,indvars,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;sink-common-insts;speculate-blocks;simplify-cond-branch>,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>),function-attrs,function(require<should-not-run-function-passes>),coro-split)),deadargelim,coro-cleanup,globalopt,globaldce,elim-avail-extern,rpo-function-attrs,recompute-globalsaa,function<eager-inv>(float2int,lower-constant-intrinsics,chr,loop(loop-rotate<header-duplication;no-prepare-for-lto>,loop-deletion),loop-distribute,inject-tli-mappings,loop-vectorize<no-interleave-forced-only;no-vectorize-forced-only;>,infer-alignment,loop-load-elim,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,simplifycfg<bonus-inst-threshold=1;forward-switch-cond;switch-range-to-icmp;switch-to-lookup;no-keep-loops;hoist-common-insts;sink-common-insts;speculate-blocks;simplify-cond-branch>,slp-vectorizer,vector-combine,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop-unroll<O3>,transform-warning,sroa<preserve-cfg>,infer-alignment,instcombine<max-iterations=1;no-use-loop-info;no-verify-fixpoint>,loop-mssa(licm<allowspeculation>),alignment-from-assumptions,loop-sink,instsimplify,div-rem-pairs,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-sink-common-insts;speculate-blocks;simplify-cond-branch>),globaldce,constmerge,cg-profile,rel-lookup-table-converter,function(annotation-remarks),verify"
},
}
}

View file

@ -3,6 +3,10 @@ use crate::link::{
};
use bumpalo::Bump;
use inkwell::memory_buffer::MemoryBuffer;
use inkwell::{
passes::PassBuilderOptions,
targets::{InitializationConfig, TargetMachine},
};
use roc_error_macros::internal_error;
use roc_gen_dev::AssemblyBackendMode;
use roc_gen_llvm::llvm::build::{module_from_builtins, LlvmBackendMode};
@ -259,8 +263,36 @@ fn gen_from_mono_module_llvm<'a>(
// Uncomment this to see the module's optimized LLVM instruction output:
// env.module.print_to_stderr();
//
inkwell::targets::Target::initialize_all(&InitializationConfig::default());
let target_triple = TargetMachine::get_default_triple();
let inkwell_target = inkwell::targets::Target::from_triple(&target_triple).unwrap();
let inkwell_opt_level = match opt_level {
OptLevel::Development | OptLevel::Normal => inkwell::OptimizationLevel::None,
OptLevel::Size => inkwell::OptimizationLevel::Default,
OptLevel::Optimize => inkwell::OptimizationLevel::Aggressive,
};
mpm.run_on(module);
let inkwell_target_machine = inkwell_target
.create_target_machine(
&target_triple,
"generic",
"",
inkwell_opt_level,
inkwell::targets::RelocMode::PIC,
inkwell::targets::CodeModel::Default,
)
.unwrap();
module
.run_passes(
crate::llvm_passes::get_llvm_passes_str(opt_level),
&inkwell_target_machine,
PassBuilderOptions::create(),
)
.expect("valid llvm optimization passes");
// mpm.run_on(module);
// Verify the module
if let Err(errors) = env.module.verify() {