forked from halide/Halide
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Fix bool conversion bug in Vulkan code generator (halide#8067)
* Fix bug in Vulkan code generator that was incorrectly passing the address of a byte vector, instead of its contents to builder.declare_constant() * Add bool_predicate_cast correctness test to verify bool conversion for Vulkan codegen works as expected --------- Co-authored-by: Derek Gerstmann <[email protected]>
- Loading branch information
Showing
3 changed files
with
45 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,39 @@ | ||
#include "Halide.h" | ||
#include <stdio.h> | ||
|
||
using namespace Halide; | ||
|
||
int main(int argc, char **argv) { | ||
|
||
// Test explicit casting of a predicate to an integer as part of a reduction | ||
// NOTE: triggers a convert_to_bool in Vulkan for a SelectOp | ||
Target target = get_jit_target_from_environment(); | ||
Var x("x"), y("y"); | ||
|
||
Func input("input"); | ||
input(x, y) = cast<uint8_t>(x + y); | ||
|
||
Func test("test"); | ||
test(x, y) = cast(UInt(8), input(x, y) >= 32); | ||
|
||
if (target.has_gpu_feature()) { | ||
Var xi("xi"), yi("yi"); | ||
test.gpu_tile(x, y, xi, yi, 8, 8); | ||
} | ||
|
||
Realization result = test.realize({96, 96}); | ||
Buffer<uint8_t> a = result[0]; | ||
for (int y = 0; y < a.height(); y++) { | ||
for (int x = 0; x < a.width(); x++) { | ||
uint8_t correct_a = ((x + y) >= 32) ? 1 : 0; | ||
if (a(x, y) != correct_a) { | ||
printf("result(%d, %d) = (%d) instead of (%d)\n", | ||
x, y, a(x, y), correct_a); | ||
return 1; | ||
} | ||
} | ||
} | ||
|
||
printf("Success!\n"); | ||
return 0; | ||
} |