main

JJan VeselyAdd initial support for half precision builtins

70a270da创建于 2018年5月18日历史提交

文件	最后提交记录	最后更新时间
half_exp.cl	amdgpu/half_exp: Switch implementation to native_exp Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325055	8 年前
half_exp10.cl	amdgpu/half_exp10: Switch implementation to native_exp10 Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325056	8 年前
half_exp2.cl	amdgpu/half_exp2: Switch implementation to native_exp2 Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325057	8 年前
half_log.cl	amdgpu/half_log: Switch implementation to native_log Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325058	8 年前
half_log10.cl	amdgpu/half_log10: Switch implementation to native_log10 Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325059	8 年前
half_log2.cl	amdgpu/half_log2: Switch implementation to native_log2 Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325060	8 年前
half_native_unary.inc	amdgpu/half_rsqrt: Switch implementation to native_rsqrt Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325053	8 年前
half_recip.cl	amdgpu/half_recip: Switch implementation to native_recip Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325061	8 年前
half_rsqrt.cl	amdgpu/half_rsqrt: Switch implementation to native_rsqrt Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325053	8 年前
half_sqrt.cl	amdgpu/half_sqrt: Switch implementation to native_sqrt Reviewer: Tom Stellard <tstellar@redhat.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 325054	8 年前
native_exp.cl	amdgpu: Add workaround for unimplemented llvm.exp intrinsic Reviewer: Jeroen Ketema Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 317935	8 年前
native_exp.inc	amdgpu: Add workaround for unimplemented llvm.exp intrinsic Reviewer: Jeroen Ketema Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 317935	8 年前
native_log.cl	amdgpu/math: Don't use llvm instrinsic for native_log AMDGPU targets don't have insturction for it, so it'll be expanded to C * log2 anyway. v2: use native_log2 instead of the more precise sw implementation v3: move to amdgpu v4: drop old AMD copyright Reviewer: Aaron Watry Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 316587	8 年前
native_log.inc	amdgpu/math: Don't use llvm instrinsic for native_log AMDGPU targets don't have insturction for it, so it'll be expanded to C * log2 anyway. v2: use native_log2 instead of the more precise sw implementation v3: move to amdgpu v4: drop old AMD copyright Reviewer: Aaron Watry Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 316587	8 年前
native_log10.cl	math: Implement native_log10 Use llvm instrinsic by default Provide amdgpu workaround v2: drop old amd copyrights Reviewer: Aaron Watry Reviewed-by: Vedran Miletić <vedran@miletic.net> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 316588	8 年前
native_log10.inc	math: Implement native_log10 Use llvm instrinsic by default Provide amdgpu workaround v2: drop old amd copyrights Reviewer: Aaron Watry Reviewed-by: Vedran Miletić <vedran@miletic.net> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 316588	8 年前
nextafter.cl	Add initial support for half precision builtins v2: fix fmax implementation use consistent checks for __CLC_FP_SIZE add missing TODOs fix whitespace in definitions.h v3: undef ZERO in modf.inc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> reviewer: Jeroen Ketema <j.ketema@xs4all.nl> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 332677	7 年前
sqrt.cl	Add initial support for half precision builtins v2: fix fmax implementation use consistent checks for __CLC_FP_SIZE add missing TODOs fix whitespace in definitions.h v3: undef ZERO in modf.inc Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> reviewer: Jeroen Ketema <j.ketema@xs4all.nl> Reviewed-by: Aaron Watry <awatry@gmail.com> Tested-by: Aaron Watry <awatry@gmail.com> llvm-svn: 332677	7 年前