diff options
| author | Eric Anholt <[email protected]> | 2013-02-19 17:01:41 -0800 |
|---|---|---|
| committer | Eric Anholt <[email protected]> | 2013-03-11 12:11:54 -0700 |
| commit | 11b8df0c0141c5759025985ba99e782a2dfd720c (patch) | |
| tree | 7424e0529ff34b6ad6d20388e4fdafc8cb4db708 /src/mesa | |
| parent | 6aa3afbfd6b737350351e9ea22ba9de1accda52d (diff) | |
mesa: Reduce memory usage for reg alloc with many graph nodes (part 2).
After the previous fix that almost removes an allocation of 4*n^2
bytes, we can use a bitset to reduce another allocation from n^2 bytes
to n^2/8 bytes.
Between the previous commit and this one, the peak heap size for an
oglconform ARB_fragment_program max instructions test on i965 goes from
4GB to 255MB.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=55825
Reviewed-by: Kenneth Graunke <[email protected]>
Diffstat (limited to 'src/mesa')
| -rw-r--r-- | src/mesa/program/register_allocate.c | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/src/mesa/program/register_allocate.c b/src/mesa/program/register_allocate.c index 5862c78661a..a9064c38ca2 100644 --- a/src/mesa/program/register_allocate.c +++ b/src/mesa/program/register_allocate.c @@ -75,6 +75,7 @@ #include "main/imports.h" #include "main/macros.h" #include "main/mtypes.h" +#include "main/bitset.h" #include "register_allocate.h" #define NO_REG ~0 @@ -118,7 +119,7 @@ struct ra_node { * List of which nodes this node interferes with. This should be * symmetric with the other node. */ - GLboolean *adjacency; + BITSET_WORD *adjacency; unsigned int *adjacency_list; unsigned int adjacency_list_size; unsigned int adjacency_count; @@ -307,7 +308,7 @@ ra_set_finalize(struct ra_regs *regs, unsigned int **q_values) static void ra_add_node_adjacency(struct ra_graph *g, unsigned int n1, unsigned int n2) { - g->nodes[n1].adjacency[n2] = GL_TRUE; + BITSET_SET(g->nodes[n1].adjacency, n2); if (g->nodes[n1].adjacency_count >= g->nodes[n1].adjacency_list_size) { @@ -335,11 +336,14 @@ ra_alloc_interference_graph(struct ra_regs *regs, unsigned int count) g->stack = rzalloc_array(g, unsigned int, count); for (i = 0; i < count; i++) { - g->nodes[i].adjacency = rzalloc_array(g, GLboolean, count); + int bitset_count = ALIGN(count, BITSET_WORDBITS) / BITSET_WORDBITS; + g->nodes[i].adjacency = rzalloc_array(g, BITSET_WORD, bitset_count); + g->nodes[i].adjacency_list_size = 4; g->nodes[i].adjacency_list = ralloc_array(g, unsigned int, g->nodes[i].adjacency_list_size); g->nodes[i].adjacency_count = 0; + ra_add_node_adjacency(g, i, i); g->nodes[i].reg = NO_REG; } @@ -358,7 +362,7 @@ void ra_add_node_interference(struct ra_graph *g, unsigned int n1, unsigned int n2) { - if (!g->nodes[n1].adjacency[n2]) { + if (!BITSET_TEST(g->nodes[n1].adjacency, n2)) { ra_add_node_adjacency(g, n1, n2); ra_add_node_adjacency(g, n2, n1); } |