[maleadt]

check_eltype runs on every oneArray construction and queried the driver each time (module_properties twice, plus the BFloat16 check). This caches the result per device, like device_limits does for KernelAbstractions.

On an Iris Xe (TGL, NEO 26.35):

	before	after
oneAPI.check_eltype(Float32)	5.2 µs, 32 allocs	89 ns, 0 allocs
unsafe_free!(oneArray{Float32}(undef, 16))	6.6 µs, 46 allocs	0.65 µs, 14 allocs

The issue measured 29 µs on NEO 26.18, where the BFloat16 check went through the full properties query. Since #701, NEO advertises ZE_extension_bfloat16_conversions, so that path is cheaper now, but the remaining queries still made up most of a small allocation.

This also fixes the capability test noted in the issue: fp16flags/fp64flags are ze_device_fp_flags_t (denorm, inf/nan, ...), so masking them with ZE_DEVICE_MODULE_FLAG_FP16/FP64 checked the wrong bits. The checks now use module_properties().flags, in check_eltype, in the compiler configuration (which now reads the same cache), and in test/runtests.jl.

The new test checks that unsupported element types are rejected, and that check_eltype doesn't allocate.

Fixes #690

[github-actions]

Your PR requires formatting changes to meet the project's style guidelines.
Please consider running Runic (git runic main) to apply these changes.

Click here to view the suggested changes.

diff --git a/src/array.jl b/src/array.jl
index f2a8b3b..fea0081 100644
--- a/src/array.jl
+++ b/src/array.jl
@@ -52,33 +52,35 @@ const EltypeSupport = @NamedTuple{float16::Bool, float64::Bool, bfloat16::Bool}
 const eltype_support_cache = Dict{ZeDevice, EltypeSupport}()
 const eltype_support_lock = ReentrantLock()
 
-function eltype_support(dev::ZeDevice=device())
-  Base.@lock eltype_support_lock begin
-    get!(eltype_support_cache, dev) do
-      flags = oneL0.module_properties(dev).flags
-      (; float16 = flags & oneL0.ZE_DEVICE_MODULE_FLAG_FP16 != 0,
-         float64 = flags & oneL0.ZE_DEVICE_MODULE_FLAG_FP64 != 0,
-         bfloat16 = _device_supports_bfloat16(dev))
+function eltype_support(dev::ZeDevice = device())
+    return Base.@lock eltype_support_lock begin
+        get!(eltype_support_cache, dev) do
+            flags = oneL0.module_properties(dev).flags
+            (;
+                float16 = flags & oneL0.ZE_DEVICE_MODULE_FLAG_FP16 != 0,
+                float64 = flags & oneL0.ZE_DEVICE_MODULE_FLAG_FP64 != 0,
+                bfloat16 = _device_supports_bfloat16(dev),
+            )
+        end
     end
-  end
 end
 
 function check_eltype(T)
   Base.allocatedinline(T) || error("oneArray only supports element types that are stored inline")
   Base.isbitsunion(T) && error("oneArray does not yet support isbits-union arrays")
-  support = eltype_support()
-  if !support.float16
+    support = eltype_support()
+    if !support.float16
     contains_eltype(T, Float16) && error("Float16 is not supported on this device")
   end
-  if !support.float64
+    if !support.float64
     contains_eltype(T, Float64) && error("Float64 is not supported on this device")
   end
-  @static if isdefined(Core, :BFloat16)
-    if !support.bfloat16
-      contains_eltype(T, Core.BFloat16) && error("BFloat16 is not supported on this device")
+    @static if isdefined(Core, :BFloat16)
+        if !support.bfloat16
+            contains_eltype(T, Core.BFloat16) && error("BFloat16 is not supported on this device")
     end
-  end
-  return
+    end
+    return
 end
 
 """
diff --git a/test/array.jl b/test/array.jl
index 33d2686..e393740 100644
--- a/test/array.jl
+++ b/test/array.jl
@@ -19,17 +19,17 @@ import Adapt
 end
 
 @testset "element type checks" begin
-  if !float64_supported
-    @test_throws "Float64 is not supported" oneArray{Float64}(undef, 1)
-    @test_throws "Float64 is not supported" oneArray{ComplexF64}(undef, 1)
-  end
-  if !float16_supported
-    @test_throws "Float16 is not supported" oneArray{Float16}(undef, 1)
-  end
+    if !float64_supported
+        @test_throws "Float64 is not supported" oneArray{Float64}(undef, 1)
+        @test_throws "Float64 is not supported" oneArray{ComplexF64}(undef, 1)
+    end
+    if !float16_supported
+        @test_throws "Float16 is not supported" oneArray{Float16}(undef, 1)
+    end
 
-  # every array construction performs this check, so it shouldn't query the device
-  oneAPI.check_eltype(Float32)
-  @test @allocated(oneAPI.check_eltype(Float32)) == 0
+    # every array construction performs this check, so it shouldn't query the device
+    oneAPI.check_eltype(Float32)
+    @test @allocated(oneAPI.check_eltype(Float32)) == 0
 end
 
 @testset "adapt" begin

[codecov]

Codecov Report

❌ Patch coverage is 87.50000% with 2 lines in your changes missing coverage. Please review.
✅ Project coverage is 83.10%. Comparing base (8460d3f) to head (b7e5190).

Files with missing lines	Patch %	Lines
src/array.jl	83.33%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #705      +/-   ##
==========================================
- Coverage   83.70%   83.10%   -0.61%     
==========================================
  Files          52       51       -1     
  Lines        4376     4262     -114     
==========================================
- Hits         3663     3542     -121     
- Misses        713      720       +7     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.