From bdda8a90cdd44ca822b21233ac988f92d1f20826 Mon Sep 17 00:00:00 2001 From: "Harsh Aggarwal (NVIDIA)" Date: Fri, 1 Aug 2025 14:48:53 +0530 Subject: Fix 7441: CUDA boolean vector layout to use 1-byte elements (#7862) * Fix 7441: CUDA boolean vector layout to use 1-byte elements Boolean vectors (bool1, bool2, bool3, bool4) were incorrectly implemented as integer-based types using 4 bytes per element instead of actual 1-byte boolean elements on CUDA targets. Changes: - Update CUDA prelude to define boolean vectors as structs with bool fields instead of typedef aliases to integer vectors - Implement CUDALayoutRulesImpl::GetVectorLayout to use 1-byte alignment for boolean vectors, matching actual CUDA memory layout behavior - Update make_bool functions to populate struct fields correctly This ensures boolean vectors have the same memory layout as bool[4] arrays: - bool1: 1 byte (was 4 bytes) - bool2: 2 bytes (was 8 bytes) - bool3: 3 bytes (was 12 bytes) - bool4: 4 bytes (was 16 bytes) Fixes memory layout mismatch between Slang reflection API and actual CUDA compilation, achieving 75% memory savings for boolean vector usage. * Fix CI issues - Add and update associated functions and operators * Make boolX same as uchar * Use align construct on struct for boolX * Improve Test case for robust alignment checks * Formatting * Disable selected slangpy tests * add metal check which is slightly different than cuda * Test-1 * Test-2 * Test-3 * Test-4 * ReflectionChange * cleanup and update * _slang_select with plain bool is needed for reverse-loop-checkpoint-test --- .../reflection/parameter-block-explicit-space.slang.expected | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'tests/reflection/parameter-block-explicit-space.slang.expected') diff --git a/tests/reflection/parameter-block-explicit-space.slang.expected b/tests/reflection/parameter-block-explicit-space.slang.expected index 347f0fd5c..9d4d2d609 100644 --- a/tests/reflection/parameter-block-explicit-space.slang.expected +++ b/tests/reflection/parameter-block-explicit-space.slang.expected @@ -23,7 +23,7 @@ standard output = { "scalarType": "float32" } }, - "binding": {"kind": "uniform", "offset": 0, "size": 16} + "binding": {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 4} }, { "name": "at1", @@ -87,7 +87,7 @@ standard output = { "scalarType": "float32" } }, - "binding": {"kind": "uniform", "offset": 0, "size": 16} + "binding": {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 4} }, { "name": "at1", @@ -133,7 +133,7 @@ standard output = { "bindings": [ {"kind": "shaderResource", "index": 0, "count": 2}, {"kind": "samplerState", "index": 0}, - {"kind": "uniform", "offset": 0, "size": 16} + {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 0} ] } } @@ -157,7 +157,7 @@ standard output = { "scalarType": "float32" } }, - "binding": {"kind": "uniform", "offset": 0, "size": 16} + "binding": {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 4} }, { "name": "bt", @@ -205,7 +205,7 @@ standard output = { "scalarType": "float32" } }, - "binding": {"kind": "uniform", "offset": 0, "size": 16} + "binding": {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 4} }, { "name": "bt", @@ -235,7 +235,7 @@ standard output = { "bindings": [ {"kind": "shaderResource", "index": 0}, {"kind": "samplerState", "index": 0}, - {"kind": "uniform", "offset": 0, "size": 16} + {"kind": "uniform", "offset": 0, "size": 16, "elementStride": 0} ] } } -- cgit v1.2.3