Revision 3657cf5f363fd64aeaf06432e62e3960800927b0 authored by Andrew Adams on 26 January 2024, 17:26:12 UTC, committed by GitHub on 26 January 2024, 17:26:12 UTC
* Fix bounds_of_nested_lanes bounds_of_nested_lanes assumed that one layer of nested vectorization could be removed at a time. When faced with the expression: min(ramp(x8(a), x8(b), 5), x40(27)) It panicked, because on the left hand side it reduced the bounds to x8(a) ... x8(a) + x8(b) * 4, and on the right hand side it reduced the bounds to 27. It then attempted to take a min of mismatched types. In general we can't assume that binary operators on nested vectors have the same nesting structure on both sides, so I just rewrote it to reduce directly to a scalar. Fixes #8038
1 parent 4590a09
LLVM_Output.h
#ifndef HALIDE_LLVM_OUTPUTS_H
#define HALIDE_LLVM_OUTPUTS_H
/** \file
*
*/
#include <memory>
#include <string>
#include <vector>
namespace llvm {
class Module;
class TargetOptions;
class LLVMContext;
class raw_fd_ostream;
class raw_pwrite_stream;
class raw_ostream;
} // namespace llvm
namespace Halide {
class Module;
struct Target;
namespace Internal {
typedef llvm::raw_pwrite_stream LLVMOStream;
}
/** Generate an LLVM module. */
std::unique_ptr<llvm::Module> compile_module_to_llvm_module(const Module &module, llvm::LLVMContext &context);
/** Construct an llvm output stream for writing to files. */
std::unique_ptr<llvm::raw_fd_ostream> make_raw_fd_ostream(const std::string &filename);
/** Compile an LLVM module to native targets (objects, native assembly). */
// @{
void compile_llvm_module_to_object(llvm::Module &module, Internal::LLVMOStream &out);
void compile_llvm_module_to_assembly(llvm::Module &module, Internal::LLVMOStream &out);
// @}
/** Compile an LLVM module to LLVM targets (bitcode, LLVM assembly). */
// @{
void compile_llvm_module_to_llvm_bitcode(llvm::Module &module, Internal::LLVMOStream &out);
void compile_llvm_module_to_llvm_assembly(llvm::Module &module, Internal::LLVMOStream &out);
// @}
/**
* Concatenate the list of src_files into dst_file, using the appropriate
* static library format for the given target (e.g., .a or .lib).
* If deterministic is true, emit 0 for all GID/UID/timestamps, and 0644 for
* all modes (equivalent to the ar -D option).
*/
void create_static_library(const std::vector<std::string> &src_files, const Target &target,
const std::string &dst_file, bool deterministic = true);
} // namespace Halide
#endif
Computing file changes ...