summaryrefslogtreecommitdiff
path: root/tests
diff options
context:
space:
mode:
authorvenkataram-nv <vedavamadath@nvidia.com>2024-06-27 16:09:33 -0700
committerGitHub <noreply@github.com>2024-06-27 16:09:33 -0700
commitf5acb6b987609cc6c1d859120cd327c57c344803 (patch)
tree8ea688558434fae58f080e7a5e67c11c04235bcb /tests
parent8172751f2a27d00ed39b32ba2f2b3fb13f8223ef (diff)
Extend `countbits` intrinsic for vector types (#4499)
* Extend `countbits` intrinsic for vector types This commit implements the overloading function for `countbits` function. Because HLSL has following overloadings, ``` uint count_bits(uint value); uint2 count_bits(uint2 value); uint3 count_bits(uint3 value); uint4 count_bits(uint4 value); ``` https://learn.microsoft.com/en-us/windows/win32/direct3dhlsl/countbits
Diffstat (limited to 'tests')
-rw-r--r--tests/hlsl-intrinsic/countbits.slang27
1 files changed, 27 insertions, 0 deletions
diff --git a/tests/hlsl-intrinsic/countbits.slang b/tests/hlsl-intrinsic/countbits.slang
new file mode 100644
index 000000000..da6828e87
--- /dev/null
+++ b/tests/hlsl-intrinsic/countbits.slang
@@ -0,0 +1,27 @@
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -compute -cpu
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -compute -dx11
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -compute -dx12
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -vk -compute
+//DISABLE_TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -cuda -compute
+//TEST(compute):COMPARE_COMPUTE_EX(filecheck-buffer=CHK):-slang -mtl -compute
+
+//CHK:1
+
+//TEST_INPUT:ubuffer(data=[0], stride=4):out,name=outputBuffer
+RWStructuredBuffer<int> outputBuffer;
+
+[numthreads(1, 1, 1)]
+void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
+{
+ uint r1 = countbits(0b1);
+ uint2 r2 = countbits(uint2(0b0, 0b1));
+ uint3 r3 = countbits(uint3(0b0, 0b1, 0b11));
+ uint4 r4 = countbits(uint4(0b0, 0b1, 0b11, 0b111));
+
+ outputBuffer[0] = true
+ && (r1 == 1)
+ && (r2.x == 0 && r2.y == 1)
+ && (r3.x == 0 && r3.y == 1 && r3.z == 2)
+ && (r4.x == 0 && r4.y == 1 && r4.z == 2 && r4.w == 3)
+ ;
+}