From 096bc0e3f8fb4bfc4d2f3f64a7f219401ffb4c31 Mon Sep 17 00:00:00 2001 From: Sergey Kosukhin Date: Wed, 13 Mar 2024 13:07:13 +0100 Subject: [PATCH] liblzma: Fix building with NVHPC (NVIDIA HPC SDK). NVHPC compiler has several issues that make it impossible to build liblzma: - the compiler cannot handle unions that contain pointers that are not the first members; - the compiler cannot handle the assembler code in range_decoder.h (LZMA_RANGE_DECODER_CONFIG has to be set to zero); - the compiler fails to produce valid code for delta_decode if the vectorization is enabled, which results in failed tests. This introduces NVHPC-specific workarounds that address the issues. --- src/liblzma/common/string_conversion.c | 6 ++++-- src/liblzma/delta/delta_decoder.c | 3 +++ src/liblzma/rangecoder/range_decoder.h | 1 + 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/src/liblzma/common/string_conversion.c b/src/liblzma/common/string_conversion.c index 92d9032b..370857f0 100644 --- a/src/liblzma/common/string_conversion.c +++ b/src/liblzma/common/string_conversion.c @@ -217,12 +217,14 @@ typedef struct { uint16_t offset; union { +// NVHPC has problems with unions that contain pointers that are not the first +// members + const name_value_map *map; + struct { uint32_t min; uint32_t max; } range; - - const name_value_map *map; } u; } option_map; diff --git a/src/liblzma/delta/delta_decoder.c b/src/liblzma/delta/delta_decoder.c index 10d53687..142fe6de 100644 --- a/src/liblzma/delta/delta_decoder.c +++ b/src/liblzma/delta/delta_decoder.c @@ -25,6 +25,9 @@ decode_buffer(lzma_delta_coder *coder, uint8_t *buffer, size_t size) } +#ifdef __NVCOMPILER +# pragma routine novector +#endif static lzma_ret delta_decode(void *coder_ptr, const lzma_allocator *allocator, const uint8_t *restrict in, size_t *restrict in_pos, diff --git a/src/liblzma/rangecoder/range_decoder.h b/src/liblzma/rangecoder/range_decoder.h index b6422247..31a58d1f 100644 --- a/src/liblzma/rangecoder/range_decoder.h +++ b/src/liblzma/rangecoder/range_decoder.h @@ -45,6 +45,7 @@ // and different processors. Overall 0x1F0 seems to be the best choice. #ifndef LZMA_RANGE_DECODER_CONFIG # if defined(__x86_64__) && !defined(__ILP32__) \ + && !defined(__NVCOMPILER) \ && (defined(__GNUC__) || defined(__clang__)) # define LZMA_RANGE_DECODER_CONFIG 0x1F0 # else