Auto merge of rust-lang#134245 - Zalathar:rollup-2dhkxya, r=Zalathar

Rollup of 9 pull requests

Successful merges:

 - rust-lang#130060 (Autodiff Upstreaming - rustc_codegen_llvm changes)
 - rust-lang#132038 (Add lint rule for `#[deprecated]` on re-exports)
 - rust-lang#132150 (Fix powerpc64 big-endian FreeBSD ABI)
 - rust-lang#133633 (don't show the full linker args unless `--verbose` is passed)
 - rust-lang#133942 (Clarify how to use `black_box()`)
 - rust-lang#134081 (Try to evaluate constants in legacy mangling)
 - rust-lang#134192 (Remove `Lexer`'s dependency on `Parser`.)
 - rust-lang#134208 (coverage: Tidy up creation of covmap and covfun records)
 - rust-lang#134211 (On Neutrino QNX, reduce the need to set archiver via environment variables)

Failed merges:

 - rust-lang#133099 (forbid toggling x87 and fpregs on hard-float targets)

r? `@ghost`
`@rustbot` modify labels: rollup

Author: bors

compiler/rustc_ast/src/expand/autodiff_attrs.rs

@@ -6,7 +6,6 @@
 use std::fmt::{self, Display, Formatter};
 use std::str::FromStr;
 
-use crate::expand::typetree::TypeTree;
 use crate::expand::{Decodable, Encodable, HashStable_Generic};
 use crate::ptr::P;
 use crate::{Ty, TyKind};
@@ -79,10 +78,6 @@ pub struct AutoDiffItem {
     /// The name of the function being generated
     pub target: String,
     pub attrs: AutoDiffAttrs,
-    /// Describe the memory layout of input types
-    pub inputs: Vec<TypeTree>,
-    /// Describe the memory layout of the output type
-    pub output: TypeTree,
 }
 #[derive(Clone, Eq, PartialEq, Encodable, Decodable, Debug, HashStable_Generic)]
 pub struct AutoDiffAttrs {
@@ -262,22 +257,14 @@ impl AutoDiffAttrs {
         !matches!(self.mode, DiffMode::Error | DiffMode::Source)
     }
 
-    pub fn into_item(
-        self,
-        source: String,
-        target: String,
-        inputs: Vec<TypeTree>,
-        output: TypeTree,
-    ) -> AutoDiffItem {
-        AutoDiffItem { source, target, inputs, output, attrs: self }
+    pub fn into_item(self, source: String, target: String) -> AutoDiffItem {
+        AutoDiffItem { source, target, attrs: self }
     }
 }
 
 impl fmt::Display for AutoDiffItem {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "Differentiating {} -> {}", self.source, self.target)?;
-        write!(f, " with attributes: {:?}", self.attrs)?;
-        write!(f, " with inputs: {:?}", self.inputs)?;
-        write!(f, " with output: {:?}", self.output)
+        write!(f, " with attributes: {:?}", self.attrs)
     }
 }

compiler/rustc_codegen_gcc/src/lib.rs

@@ -93,6 +93,7 @@ use gccjit::{CType, Context, OptimizationLevel};
 #[cfg(feature = "master")]
 use gccjit::{TargetInfo, Version};
 use rustc_ast::expand::allocator::AllocatorKind;
+use rustc_ast::expand::autodiff_attrs::AutoDiffItem;
 use rustc_codegen_ssa::back::lto::{LtoModuleCodegen, SerializedModule, ThinModule};
 use rustc_codegen_ssa::back::write::{
     CodegenContext, FatLtoInput, ModuleConfig, TargetMachineFactoryFn,
@@ -439,6 +440,14 @@ impl WriteBackendMethods for GccCodegenBackend {
     ) -> Result<ModuleCodegen<Self::Module>, FatalError> {
         back::write::link(cgcx, dcx, modules)
     }
+    fn autodiff(
+        _cgcx: &CodegenContext<Self>,
+        _module: &ModuleCodegen<Self::Module>,
+        _diff_fncs: Vec<AutoDiffItem>,
+        _config: &ModuleConfig,
+    ) -> Result<(), FatalError> {
+        unimplemented!()
+    }
 }
 
 /// This is the entrypoint for a hot plugged rustc_codegen_gccjit

compiler/rustc_codegen_llvm/messages.ftl

@@ -1,3 +1,5 @@
+codegen_llvm_autodiff_without_lto = using the autodiff feature requires using fat-lto
+
 codegen_llvm_copy_bitcode = failed to copy bitcode to object file: {$err}
 
 codegen_llvm_dynamic_linking_with_lto =
@@ -47,6 +49,8 @@ codegen_llvm_parse_bitcode_with_llvm_err = failed to parse bitcode for LTO modul
 codegen_llvm_parse_target_machine_config =
     failed to parse target machine config to target machine: {$error}
 
+codegen_llvm_prepare_autodiff = failed to prepare autodiff: src: {$src}, target: {$target}, {$error}
+codegen_llvm_prepare_autodiff_with_llvm_err = failed to prepare autodiff: {$llvm_err}, src: {$src}, target: {$target}, {$error}
 codegen_llvm_prepare_thin_lto_context = failed to prepare thin LTO context
 codegen_llvm_prepare_thin_lto_context_with_llvm_err = failed to prepare thin LTO context: {$llvm_err}
 

compiler/rustc_codegen_llvm/src/back/lto.rs

@@ -604,7 +604,14 @@ pub(crate) fn run_pass_manager(
     debug!("running the pass manager");
     let opt_stage = if thin { llvm::OptStage::ThinLTO } else { llvm::OptStage::FatLTO };
     let opt_level = config.opt_level.unwrap_or(config::OptLevel::No);
-    unsafe { write::llvm_optimize(cgcx, dcx, module, config, opt_level, opt_stage) }?;
+
+    // If this rustc version was build with enzyme/autodiff enabled, and if users applied the
+    // `#[autodiff]` macro at least once, then we will later call llvm_optimize a second time.
+    let first_run = true;
+    debug!("running llvm pm opt pipeline");
+    unsafe {
+        write::llvm_optimize(cgcx, dcx, module, config, opt_level, opt_stage, first_run)?;
+    }
     debug!("lto done");
     Ok(())
 }

compiler/rustc_codegen_llvm/src/back/write.rs

@@ -8,6 +8,7 @@ use libc::{c_char, c_int, c_void, size_t};
 use llvm::{
     LLVMRustLLVMHasZlibCompressionForDebugSymbols, LLVMRustLLVMHasZstdCompressionForDebugSymbols,
 };
+use rustc_ast::expand::autodiff_attrs::AutoDiffItem;
 use rustc_codegen_ssa::back::link::ensure_removed;
 use rustc_codegen_ssa::back::versioned_llvm_target;
 use rustc_codegen_ssa::back::write::{
@@ -28,7 +29,7 @@ use rustc_session::config::{
 use rustc_span::symbol::sym;
 use rustc_span::{BytePos, InnerSpan, Pos, SpanData, SyntaxContext};
 use rustc_target::spec::{CodeModel, RelocModel, SanitizerSet, SplitDebuginfo, TlsModel};
-use tracing::debug;
+use tracing::{debug, trace};
 
 use crate::back::lto::ThinBuffer;
 use crate::back::owned_target_machine::OwnedTargetMachine;
@@ -530,9 +531,38 @@ pub(crate) unsafe fn llvm_optimize(
     config: &ModuleConfig,
     opt_level: config::OptLevel,
     opt_stage: llvm::OptStage,
+    skip_size_increasing_opts: bool,
 ) -> Result<(), FatalError> {
-    let unroll_loops =
-        opt_level != config::OptLevel::Size && opt_level != config::OptLevel::SizeMin;
+    // Enzyme:
+    // The whole point of compiler based AD is to differentiate optimized IR instead of unoptimized
+    // source code. However, benchmarks show that optimizations increasing the code size
+    // tend to reduce AD performance. Therefore deactivate them before AD, then differentiate the code
+    // and finally re-optimize the module, now with all optimizations available.
+    // FIXME(ZuseZ4): In a future update we could figure out how to only optimize individual functions getting
+    // differentiated.
+
+    let unroll_loops;
+    let vectorize_slp;
+    let vectorize_loop;
+
+    // When we build rustc with enzyme/autodiff support, we want to postpone size-increasing
+    // optimizations until after differentiation. FIXME(ZuseZ4): Before shipping on nightly,
+    // we should make this more granular, or at least check that the user has at least one autodiff
+    // call in their code, to justify altering the compilation pipeline.
+    if skip_size_increasing_opts && cfg!(llvm_enzyme) {
+        unroll_loops = false;
+        vectorize_slp = false;
+        vectorize_loop = false;
+    } else {
+        unroll_loops =
+            opt_level != config::OptLevel::Size && opt_level != config::OptLevel::SizeMin;
+        vectorize_slp = config.vectorize_slp;
+        vectorize_loop = config.vectorize_loop;
+    }
+    trace!(
+        "Enzyme: Running with unroll_loops: {}, vectorize_slp: {}, vectorize_loop: {}",
+        unroll_loops, vectorize_slp, vectorize_loop
+    );
     let using_thin_buffers = opt_stage == llvm::OptStage::PreLinkThinLTO || config.bitcode_needed();
     let pgo_gen_path = get_pgo_gen_path(config);
     let pgo_use_path = get_pgo_use_path(config);
@@ -596,8 +626,8 @@ pub(crate) unsafe fn llvm_optimize(
             using_thin_buffers,
             config.merge_functions,
             unroll_loops,
-            config.vectorize_slp,
-            config.vectorize_loop,
+            vectorize_slp,
+            vectorize_loop,
             config.no_builtins,
             config.emit_lifetime_markers,
             sanitizer_options.as_ref(),
@@ -619,6 +649,83 @@ pub(crate) unsafe fn llvm_optimize(
     result.into_result().map_err(|()| llvm_err(dcx, LlvmError::RunLlvmPasses))
 }
 
+pub(crate) fn differentiate(
+    module: &ModuleCodegen<ModuleLlvm>,
+    cgcx: &CodegenContext<LlvmCodegenBackend>,
+    diff_items: Vec<AutoDiffItem>,
+    config: &ModuleConfig,
+) -> Result<(), FatalError> {
+    for item in &diff_items {
+        trace!("{}", item);
+    }
+
+    let llmod = module.module_llvm.llmod();
+    let llcx = &module.module_llvm.llcx;
+    let diag_handler = cgcx.create_dcx();
+
+    // Before dumping the module, we want all the tt to become part of the module.
+    for item in diff_items.iter() {
+        let name = CString::new(item.source.clone()).unwrap();
+        let fn_def: Option<&llvm::Value> =
+            unsafe { llvm::LLVMGetNamedFunction(llmod, name.as_ptr()) };
+        let fn_def = match fn_def {
+            Some(x) => x,
+            None => {
+                return Err(llvm_err(diag_handler.handle(), LlvmError::PrepareAutoDiff {
+                    src: item.source.clone(),
+                    target: item.target.clone(),
+                    error: "could not find source function".to_owned(),
+                }));
+            }
+        };
+        let target_name = CString::new(item.target.clone()).unwrap();
+        debug!("target name: {:?}", &target_name);
+        let fn_target: Option<&llvm::Value> =
+            unsafe { llvm::LLVMGetNamedFunction(llmod, target_name.as_ptr()) };
+        let fn_target = match fn_target {
+            Some(x) => x,
+            None => {
+                return Err(llvm_err(diag_handler.handle(), LlvmError::PrepareAutoDiff {
+                    src: item.source.clone(),
+                    target: item.target.clone(),
+                    error: "could not find target function".to_owned(),
+                }));
+            }
+        };
+
+        crate::builder::generate_enzyme_call(llmod, llcx, fn_def, fn_target, item.attrs.clone());
+    }
+
+    // FIXME(ZuseZ4): support SanitizeHWAddress and prevent illegal/unsupported opts
+
+    if let Some(opt_level) = config.opt_level {
+        let opt_stage = match cgcx.lto {
+            Lto::Fat => llvm::OptStage::PreLinkFatLTO,
+            Lto::Thin | Lto::ThinLocal => llvm::OptStage::PreLinkThinLTO,
+            _ if cgcx.opts.cg.linker_plugin_lto.enabled() => llvm::OptStage::PreLinkThinLTO,
+            _ => llvm::OptStage::PreLinkNoLTO,
+        };
+        // This is our second opt call, so now we run all opts,
+        // to make sure we get the best performance.
+        let skip_size_increasing_opts = false;
+        trace!("running Module Optimization after differentiation");
+        unsafe {
+            llvm_optimize(
+                cgcx,
+                diag_handler.handle(),
+                module,
+                config,
+                opt_level,
+                opt_stage,
+                skip_size_increasing_opts,
+            )?
+        };
+    }
+    trace!("done with differentiate()");
+
+    Ok(())
+}
+
 // Unsafe due to LLVM calls.
 pub(crate) unsafe fn optimize(
     cgcx: &CodegenContext<LlvmCodegenBackend>,
@@ -641,14 +748,29 @@ pub(crate) unsafe fn optimize(
         unsafe { llvm::LLVMWriteBitcodeToFile(llmod, out.as_ptr()) };
     }
 
+    // FIXME(ZuseZ4): support SanitizeHWAddress and prevent illegal/unsupported opts
+
     if let Some(opt_level) = config.opt_level {
         let opt_stage = match cgcx.lto {
             Lto::Fat => llvm::OptStage::PreLinkFatLTO,
             Lto::Thin | Lto::ThinLocal => llvm::OptStage::PreLinkThinLTO,
             _ if cgcx.opts.cg.linker_plugin_lto.enabled() => llvm::OptStage::PreLinkThinLTO,
             _ => llvm::OptStage::PreLinkNoLTO,
         };
-        return unsafe { llvm_optimize(cgcx, dcx, module, config, opt_level, opt_stage) };
+
+        // If we know that we will later run AD, then we disable vectorization and loop unrolling
+        let skip_size_increasing_opts = cfg!(llvm_enzyme);
+        return unsafe {
+            llvm_optimize(
+                cgcx,
+                dcx,
+                module,
+                config,
+                opt_level,
+                opt_stage,
+                skip_size_increasing_opts,
+            )
+        };
     }
     Ok(())
 }