From 05bf7e3fa064295c9512e66f33e979367e4f43ff Mon Sep 17 00:00:00 2001 From: Elias Konstantinidis Date: Sun, 2 Oct 2016 10:08:07 +0300 Subject: [PATCH] Added __mul24 & __umul24 documentation entry [ROCm/hip commit: 0b4b1b7df812439436621c5bb8bfab42eef0cfb2] --- projects/hip/docs/markdown/hip_kernel_language.md | 2 ++ 1 file changed, 2 insertions(+) mode change 100644 => 100755 projects/hip/docs/markdown/hip_kernel_language.md diff --git a/projects/hip/docs/markdown/hip_kernel_language.md b/projects/hip/docs/markdown/hip_kernel_language.md old mode 100644 new mode 100755 index ed9dc2fbe9..4b8762025e --- a/projects/hip/docs/markdown/hip_kernel_language.md +++ b/projects/hip/docs/markdown/hip_kernel_language.md @@ -451,6 +451,8 @@ Following is the list of supported integer intrinsics. Note that intrinsics are | unsigned int __ffsll(long long int x)
Find the position of least signigicant bit set to 1 in a 64 bit signed integer. | | unsigned int __popc ( unsigned int x )
Count the number of bits that are set to 1 in a 32 bit integer. | | int __popcll ( unsigned long long int x )
Count the number of bits that are set to 1 in a 64 bit integer. | +| int __mul24 ( int x, int y )
Multiply two 24bit integers. | +| unsigned int __umul24 ( unsigned int x, unsigned int y )
Multiply two 24bit unsigned integers. | [1] The hcc implementation of __ffs() and __ffsll() contains code to add a constant +1 to produce the ffs result format. For the cases where this overhead is not acceptable and programmer is willing to specialize for the platform,