From 85e2fa44c64e1edd2f675c990ecc60f5fadb4686 Mon Sep 17 00:00:00 2001 From: Jan Vesely Date: Tue, 4 Feb 2020 20:14:04 -0500 Subject: libclc/r600: Use target specific builtins to implement rsqrt and native_rsqrt Fixes OCL CTS rsqrt and half_rsqrt (1 thread, scalaer) tests on AMD Turks. Reviewer: awatry Differential Revision: https://reviews.llvm.org/D74016 --- libclc/r600/lib/SOURCES | 2 ++ libclc/r600/lib/math/native_rsqrt.cl | 10 ++++++++++ libclc/r600/lib/math/rsqrt.cl | 23 +++++++++++++++++++++++ 3 files changed, 35 insertions(+) create mode 100644 libclc/r600/lib/math/native_rsqrt.cl create mode 100644 libclc/r600/lib/math/rsqrt.cl (limited to 'libclc') diff --git a/libclc/r600/lib/SOURCES b/libclc/r600/lib/SOURCES index 4342ac38201c..6e01bbb2b8b9 100644 --- a/libclc/r600/lib/SOURCES +++ b/libclc/r600/lib/SOURCES @@ -1,5 +1,7 @@ math/fmax.cl math/fmin.cl +math/native_rsqrt.cl +math/rsqrt.cl synchronization/barrier.cl workitem/get_global_offset.cl workitem/get_group_id.cl diff --git a/libclc/r600/lib/math/native_rsqrt.cl b/libclc/r600/lib/math/native_rsqrt.cl new file mode 100644 index 000000000000..edf473e8409c --- /dev/null +++ b/libclc/r600/lib/math/native_rsqrt.cl @@ -0,0 +1,10 @@ +#include + +#include "../../../generic/lib/clcmacro.h" + +_CLC_OVERLOAD _CLC_DEF float native_rsqrt(float x) +{ + return __builtin_r600_recipsqrt_ieeef(x); +} + +_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, float, native_rsqrt, float); diff --git a/libclc/r600/lib/math/rsqrt.cl b/libclc/r600/lib/math/rsqrt.cl new file mode 100644 index 000000000000..37a8037902c2 --- /dev/null +++ b/libclc/r600/lib/math/rsqrt.cl @@ -0,0 +1,23 @@ +#include + +#include "../../../generic/lib/clcmacro.h" + +_CLC_OVERLOAD _CLC_DEF float rsqrt(float x) +{ + return __builtin_r600_recipsqrt_ieeef(x); +} + +_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, float, rsqrt, float); + +#ifdef cl_khr_fp64 + +#pragma OPENCL EXTENSION cl_khr_fp64 : enable + +_CLC_OVERLOAD _CLC_DEF double rsqrt(double x) +{ + return __builtin_r600_recipsqrt_ieee(x); +} + +_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, double, rsqrt, double); + +#endif -- cgit v1.2.1