Fix fptrunc Float64 -> Float16 rounding through Float32 (#57809)

Widening from Float32 to Float64 and then rounding to Float16 will not
introduce any error, but going from Float64 -> Float32 -> Float16 will
round incorrectly if the intermediate Float32 is halfway between two
Float16s.

Fixes #57805.

Thanks to @vtjnash for suggesting the fix.

Co-authored-by: Jameson Nash <[email protected]>

Author: xal-0

src/runtime_intrinsics.c

@@ -1629,8 +1629,8 @@ cvt_iintrinsic(LLVMFPtoUI, fptoui)
 #define fintrinsic_read_float32(p)   *(float *)p
 #define fintrinsic_read_float64(p)   *(double *)p
 
-#define fintrinsic_write_float16(p, x)  *(uint16_t *)p = float_to_half(x)
-#define fintrinsic_write_bfloat16(p, x) *(uint16_t *)p = float_to_bfloat(x)
+#define fintrinsic_write_float16(p, x)  *(uint16_t *)p = double_to_half(x)
+#define fintrinsic_write_bfloat16(p, x) *(uint16_t *)p = double_to_bfloat(x)
 #define fintrinsic_write_float32(p, x)  *(float *)p = x
 #define fintrinsic_write_float64(p, x)  *(double *)p = x
 

test/intrinsics.jl

@@ -304,6 +304,17 @@ end
     @test_intrinsic Core.Intrinsics.fptrunc Float16 Float32(3.3) Float16(3.3)
     @test_intrinsic Core.Intrinsics.fptrunc Float16 Float64(3.3) Float16(3.3)
 
+    # #57805 - cases where rounding Float64 -> Float32 -> Float16 would fail
+    #     2^-25 * 0b1.0000000000000000000000000000000000000001 binary
+    #   0 01111100110 0000000000000000000000000000000000000001000000000000
+    #     2^-25 * 0b1.0                                        binary
+    #   0    01100110 00000000000000000000000
+    #     2^-14 * 0b0.0000000001 (subnormal)
+    #   0       00000 0000000001 (correct)
+    #   0       00000 0000000000 (incorrect)
+    @test_intrinsic Core.Intrinsics.fptrunc Float16 0x1.0000000001p-25 Float16(6.0e-8)
+    @test_intrinsic Core.Intrinsics.fptrunc Float16 -0x1.0000000001p-25 Float16(-6.0e-8)
+
     # float_to_half/bfloat_to_float special cases
     @test_intrinsic Core.Intrinsics.fptrunc Float16 Inf32 Inf16
     @test_intrinsic Core.Intrinsics.fptrunc Float16 -Inf32 -Inf16