mirror of
https://github.com/libjpeg-turbo/libjpeg-turbo
synced 2025-03-28 21:13:18 +00:00
Build: Set FLOATTEST more intelligently
The "32bit" vs. "64bit" floating point test results actually have
nothing to do with the FPU. That was a fallacious assumption based on
the observation that, with multiple CPU types, 32-bit and 64-bit builds
produce different floating point test results. It seems that this is,
in fact, due to differing compiler behavior-- more specifically, whether
fused multiply-add (FMA) instructions are used to combine multiple
floating point operations into a single instruction ("floating point
expression contraction".) GCC does this by default if the target
supports FMA instructions, which PowerPC and AArch64 targets both do.
Fixes #468
This commit is contained in:
DRC
parent
42f7c78fe3
commit
88bf1d1678
@ -51,6 +51,11 @@ matrix:
|
||||
CFLAGS_RELWITHDEBINFO="-O3 -g -fsanitize=memory -fPIE"
|
||||
CMAKE_FLAGS="-DWITH_SIMD=0"
|
||||
CTEST_OUTPUT_ON_FAILURE=1
|
||||
- os: linux
|
||||
compiler: clang
|
||||
arch: arm64
|
||||
env:
|
||||
CTEST_OUTPUT_ON_FAILURE=1
|
||||
|
||||
before_install:
|
||||
- if [ "$TRAVIS_OS_NAME" = "osx" ]; then
|
||||
@ -106,7 +111,7 @@ script:
|
||||
! "${CMAKE_FLAGS[0]}" =~ "WITH_SIMD" &&
|
||||
"$TRAVIS_CPU_ARCH" = "amd64" ]]; then
|
||||
JSIMD_FORCESSE2=1 make test &&
|
||||
cmake -DFLOATTEST=32bit .. &&
|
||||
cmake -DFLOATTEST=no-fp-contract .. &&
|
||||
JSIMD_FORCENONE=1 make test;
|
||||
fi &&
|
||||
popd;
|
||||
|
||||
@ -709,10 +709,11 @@ if(WITH_12BIT)
|
||||
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_SSE a8c17daf77b457725ec929e215b603f8)
|
||||
set(MD5_PPM_3x2_FLOAT_SSE 42876ab9e5c2f76a87d08db5fbd57956)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_32BIT a8c17daf77b457725ec929e215b603f8)
|
||||
set(MD5_PPM_3x2_FLOAT_32BIT ${MD5_PPM_3x2_FLOAT_SSE})
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_64BIT ${MD5_JPEG_3x2_FLOAT_PROG_32BIT})
|
||||
set(MD5_PPM_3x2_FLOAT_64BIT ${MD5_PPM_3x2_FLOAT_SSE})
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_NO_FP_CONTRACT a8c17daf77b457725ec929e215b603f8)
|
||||
set(MD5_PPM_3x2_FLOAT_NO_FP_CONTRACT ${MD5_PPM_3x2_FLOAT_SSE})
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_FP_CONTRACT
|
||||
${MD5_JPEG_3x2_FLOAT_PROG_NO_FP_CONTRACT})
|
||||
set(MD5_PPM_3x2_FLOAT_FP_CONTRACT ${MD5_PPM_3x2_FLOAT_SSE})
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_387 bc6dbbefac2872f6b9d6c4a0ae60c3c0)
|
||||
set(MD5_PPM_3x2_FLOAT_387 bcc5723c61560463ac60f772e742d092)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_MSVC e27840755870fa849872e58aa0cd1400)
|
||||
@ -761,10 +762,11 @@ else()
|
||||
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_SSE 343e3f8caf8af5986ebaf0bdc13b5c71)
|
||||
set(MD5_PPM_3x2_FLOAT_SSE 1a75f36e5904d6fc3a85a43da9ad89bb)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_32BIT 9bca803d2042bd1eb03819e2bf92b3e5)
|
||||
set(MD5_PPM_3x2_FLOAT_32BIT f6bfab038438ed8f5522fbd33595dcdc)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_64BIT ${MD5_JPEG_3x2_FLOAT_PROG_32BIT})
|
||||
set(MD5_PPM_3x2_FLOAT_64BIT 0e917a34193ef976b679a6b069b1be26)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_NO_FP_CONTRACT 9bca803d2042bd1eb03819e2bf92b3e5)
|
||||
set(MD5_PPM_3x2_FLOAT_NO_FP_CONTRACT f6bfab038438ed8f5522fbd33595dcdc)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_FP_CONTRACT
|
||||
${MD5_JPEG_3x2_FLOAT_PROG_NO_FP_CONTRACT})
|
||||
set(MD5_PPM_3x2_FLOAT_FP_CONTRACT 0e917a34193ef976b679a6b069b1be26)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_387 1657664a410e0822c924b54f6f65e6e9)
|
||||
set(MD5_PPM_3x2_FLOAT_387 cb0a1f027f3d2917c902b5640214e025)
|
||||
set(MD5_JPEG_3x2_FLOAT_PROG_MSVC 7999ce9cd0ee9b6c7043b7351ab7639d)
|
||||
@ -874,11 +876,16 @@ endif()
|
||||
#
|
||||
# sse = validate against the expected results from the libjpeg-turbo SSE SIMD
|
||||
# extensions
|
||||
# 32bit = validate against the expected results from the C code when running on
|
||||
# a 32-bit FPU (or when SSE is being used for floating point math,
|
||||
# which is generally the default with x86-64 compilers)
|
||||
# 64bit = validate against the expected results from the C code when running
|
||||
# on a 64-bit FPU
|
||||
# no-fp-contract = validate against the expected results from the C code when
|
||||
# floating point expression contraction is disabled (the
|
||||
# default with Clang, with GCC when building for platforms
|
||||
# that lack fused multiply-add [FMA] instructions, or when
|
||||
# passing -ffp-contract=off to the compiler)
|
||||
# fp-contract = validate against the expected results from the C code when
|
||||
# floating point expression contraction is enabled (the default
|
||||
# with GCC when building for platforms that have fused multiply-
|
||||
# add [FMA] instructions or when passing -ffp-contract=fast to
|
||||
# the compiler)
|
||||
# 387 = validate against the expected results from the C code when the 387 FPU
|
||||
# is being used for floating point math (which is generally the default
|
||||
# with x86 compilers)
|
||||
@ -889,15 +896,20 @@ if(CPU_TYPE STREQUAL "x86_64" OR CPU_TYPE STREQUAL "i386")
|
||||
if(WITH_SIMD)
|
||||
set(DEFAULT_FLOATTEST sse)
|
||||
elseif(CPU_TYPE STREQUAL "x86_64")
|
||||
set(DEFAULT_FLOATTEST 32bit)
|
||||
set(DEFAULT_FLOATTEST no-fp-contract)
|
||||
elseif(CPU_TYPE STREQUAL "i386" AND MSVC)
|
||||
set(DEFAULT_FLOATTEST msvc)
|
||||
# else we can't really set an intelligent default for i386. The appropriate
|
||||
# value could be 387, no-fp-contract, or fp-contract, depending on the
|
||||
# compiler and compiler options. We leave it to the user to set FLOATTEST
|
||||
# manually.
|
||||
endif()
|
||||
else()
|
||||
if(BITS EQUAL 64)
|
||||
set(DEFAULT_FLOATTEST 64bit)
|
||||
elseif(BITS EQUAL 32)
|
||||
set(DEFAULT_FLOATTEST 32bit)
|
||||
if((CPU_TYPE STREQUAL "powerpc" OR CPU_TYPE STREQUAL "arm64") AND
|
||||
NOT CMAKE_C_COMPILER_ID STREQUAL "Clang")
|
||||
set(DEFAULT_FLOATTEST fp-contract)
|
||||
else()
|
||||
set(DEFAULT_FLOATTEST no-fp-contract)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
@ -908,15 +920,17 @@ if(DEFINED WITH_SIMD_INT AND NOT WITH_SIMD EQUAL WITH_SIMD_INT)
|
||||
endif()
|
||||
set(WITH_SIMD_INT ${WITH_SIMD} CACHE INTERNAL "")
|
||||
set(FLOATTEST ${DEFAULT_FLOATTEST} CACHE STRING
|
||||
"The type of floating point math used by the floating point DCT/IDCT algorithms. This tells the testing system which numerical results it should expect from those tests. [sse = libjpeg-turbo x86/x86-64 SIMD extensions, 32bit = generic 32-bit FPU or SSE, 64bit = generic 64-bit FPU, 387 = 387 FPU, msvc = 32-bit Visual Studio] (default = ${DEFAULT_FLOATTEST})"
|
||||
"The type of floating point math used by the floating point DCT/IDCT algorithms. This tells the testing system which numerical results it should expect from those tests. [sse = libjpeg-turbo x86/x86-64 SIMD extensions, no-fp-contract = generic FPU with floating point expression contraction disabled, fp-contract = generic FPU with floating point expression contraction enabled, 387 = 387 FPU, msvc = 32-bit Visual Studio] (default = ${DEFAULT_FLOATTEST})"
|
||||
${FORCE_FLOATTEST})
|
||||
message(STATUS "FLOATTEST = ${FLOATTEST}")
|
||||
|
||||
if(FLOATTEST)
|
||||
string(TOUPPER ${FLOATTEST} FLOATTEST_UC)
|
||||
string(REGEX REPLACE "-" "_" FLOATTEST_UC ${FLOATTEST_UC})
|
||||
string(TOLOWER ${FLOATTEST} FLOATTEST)
|
||||
if(NOT FLOATTEST STREQUAL "sse" AND NOT FLOATTEST STREQUAL "32bit" AND
|
||||
NOT FLOATTEST STREQUAL "64bit" AND NOT FLOATTEST STREQUAL "387" AND
|
||||
if(NOT FLOATTEST STREQUAL "sse" AND
|
||||
NOT FLOATTEST STREQUAL "no-fp-contract" AND
|
||||
NOT FLOATTEST STREQUAL "fp-contract" AND NOT FLOATTEST STREQUAL "387" AND
|
||||
NOT FLOATTEST STREQUAL "msvc")
|
||||
message(FATAL_ERROR "\"${FLOATTEST}\" is not a valid value for FLOATTEST.")
|
||||
endif()
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user