summaryrefslogtreecommitdiffstats
path: root/include/asm-generic
diff options
context:
space:
mode:
authorNicolas Pitre <nicolas.pitre@linaro.org>2015-10-30 17:54:56 -0400
committerNicolas Pitre <nicolas.pitre@linaro.org>2015-11-16 14:42:11 -0500
commitf682b27c57aec2f0ca8927f9bb7c267c6165ad5a (patch)
treea84d7fd54c9efe96a466617ed1c325a3e80aef3e /include/asm-generic
parent461a5e51060c93f5844113f4be9dba513cc92830 (diff)
downloadlinux-f682b27c57aec2f0ca8927f9bb7c267c6165ad5a.tar.gz
linux-f682b27c57aec2f0ca8927f9bb7c267c6165ad5a.tar.bz2
linux-f682b27c57aec2f0ca8927f9bb7c267c6165ad5a.zip
__div64_const32(): abstract out the actual 128-bit cross product code
The default C implementation for the 128-bit cross product is abstracted into the __arch_xprod_64() macro that can be overridden to let architectures provide their own assembly optimized implementation. There are many advantages to an assembly version for this operation. Carry bit handling becomes trivial, and 32-bit shifts may be achieved simply by inverting register pairs on some architectures. This has the potential to be quite faster and use much fewer instructions. Signed-off-by: Nicolas Pitre <nico@linaro.org>
Diffstat (limited to 'include/asm-generic')
-rw-r--r--include/asm-generic/div64.h81
1 files changed, 51 insertions, 30 deletions
diff --git a/include/asm-generic/div64.h b/include/asm-generic/div64.h
index 5a1bf1aff502..408856a9aba1 100644
--- a/include/asm-generic/div64.h
+++ b/include/asm-generic/div64.h
@@ -63,7 +63,7 @@
* do the trick here). \
*/ \
uint64_t ___res, ___x, ___t, ___m, ___n = (n); \
- uint32_t ___p, ___bias, ___m_lo, ___m_hi, ___n_lo, ___n_hi; \
+ uint32_t ___p, ___bias; \
\
/* determine MSB of b */ \
___p = 1 << ilog2(___b); \
@@ -138,41 +138,62 @@
* 2) whether or not there might be an overflow in the cross \
* product determined by (___m & ((1 << 63) | (1 << 31))). \
* \
- * Select the best way to do (m_bias + m * n) / (p << 64). \
+ * Select the best way to do (m_bias + m * n) / (1 << 64). \
* From now on there will be actual runtime code generated. \
*/ \
- \
- ___m_lo = ___m; \
- ___m_hi = ___m >> 32; \
- ___n_lo = ___n; \
- ___n_hi = ___n >> 32; \
- \
- if (!___bias) { \
- ___res = ((uint64_t)___m_lo * ___n_lo) >> 32; \
- } else if (!(___m & ((1ULL << 63) | (1ULL << 31)))) { \
- ___res = (___m + (uint64_t)___m_lo * ___n_lo) >> 32; \
- } else { \
- ___res = ___m + (uint64_t)___m_lo * ___n_lo; \
- ___t = (___res < ___m) ? (1ULL << 32) : 0; \
- ___res = (___res >> 32) + ___t; \
- } \
- \
- if (!(___m & ((1ULL << 63) | (1ULL << 31)))) { \
- ___res += (uint64_t)___m_lo * ___n_hi; \
- ___res += (uint64_t)___m_hi * ___n_lo; \
- ___res >>= 32; \
- } else { \
- ___t = ___res += (uint64_t)___m_lo * ___n_hi; \
- ___res += (uint64_t)___m_hi * ___n_lo; \
- ___t = (___res < ___t) ? (1ULL << 32) : 0; \
- ___res = (___res >> 32) + ___t; \
- } \
- \
- ___res += (uint64_t)___m_hi * ___n_hi; \
+ ___res = __arch_xprod_64(___m, ___n, ___bias); \
\
___res /= ___p; \
})
+#ifndef __arch_xprod_64
+/*
+ * Default C implementation for __arch_xprod_64()
+ *
+ * Prototype: uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+ * Semantic: retval = ((bias ? m : 0) + m * n) >> 64
+ *
+ * The product is a 128-bit value, scaled down to 64 bits.
+ * Assuming constant propagation to optimize away unused conditional code.
+ * Architectures may provide their own optimized assembly implementation.
+ */
+static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
+{
+ uint32_t m_lo = m;
+ uint32_t m_hi = m >> 32;
+ uint32_t n_lo = n;
+ uint32_t n_hi = n >> 32;
+ uint64_t res, tmp;
+
+ if (!bias) {
+ res = ((uint64_t)m_lo * n_lo) >> 32;
+ } else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+ /* there can't be any overflow here */
+ res = (m + (uint64_t)m_lo * n_lo) >> 32;
+ } else {
+ res = m + (uint64_t)m_lo * n_lo;
+ tmp = (res < m) ? (1ULL << 32) : 0;
+ res = (res >> 32) + tmp;
+ }
+
+ if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+ /* there can't be any overflow here */
+ res += (uint64_t)m_lo * n_hi;
+ res += (uint64_t)m_hi * n_lo;
+ res >>= 32;
+ } else {
+ tmp = res += (uint64_t)m_lo * n_hi;
+ res += (uint64_t)m_hi * n_lo;
+ tmp = (res < tmp) ? (1ULL << 32) : 0;
+ res = (res >> 32) + tmp;
+ }
+
+ res += (uint64_t)m_hi * n_hi;
+
+ return res;
+}
+#endif
+
extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
/* The unnecessary pointer compare is there