hip: fix bf16 WMMA operand vector type for gfx11/gfx12 (#30885)
The __builtin_amdgcn_wmma_f32_16x16x16_bf16_w32 (and _gfx12) builtins take their A/B operands as vectors of short (_ExtVector<16, short> / _ExtVector<8, short>), not __bf16. Declaring the fragments as ext_vector_type(N) __bf16 fails to compile: error: cannot initialize a parameter of type 'short __attribute__((ext_vector_type(16)))' with an lvalue of type 'const bf16x16_t' (vector of 16 '__bf16' values) short and __bf16 are both 16-bit and the value is only ever passed to the builtin via reinterpret_cast over raw bytes, so changing the element type is bit-identical. The operand type has been short since the builtin was introduced, so this works across LLVM/ROCm versions without a version gate. Fixes HIP builds for RDNA3 (gfx1150/1151) and RDNA4 (gfx1200/1201). Signed-off-by: Pablo Cholaky <waltercool@slash.cl>
This commit is contained in:
1 parent
1a24df1639
commit
9145ddb955
1 file changed
+2
-2
@@ -1409,14 +1409,14 @@ namespace ggml_cuda_mma {
|
||||
tile<16, 16, float, dl_d> & D, const tile<16, 8, nv_bfloat162, dl_ab> & A, const tile<16, 8, nv_bfloat162, dl_ab> & B) {
|
||||
#if defined(AMD_WMMA_AVAILABLE)
|
||||
#if defined(RDNA4)
|
||||
using bf16x8_t = __attribute__((ext_vector_type(8))) __bf16;
|
||||
using bf16x8_t = __attribute__((ext_vector_type(8))) short;
|
||||
using floatx8_t = __attribute__((ext_vector_type(8))) float;
|
||||
floatx8_t& acc_frag = reinterpret_cast<floatx8_t&>(D.x[0]);
|
||||
const bf16x8_t& a_frag = reinterpret_cast<const bf16x8_t&>(A.x[0]);
|
||||
const bf16x8_t& b_frag = reinterpret_cast<const bf16x8_t&>(B.x[0]);
|
||||
acc_frag = __builtin_amdgcn_wmma_f32_16x16x16_bf16_w32_gfx12(a_frag, b_frag, acc_frag);
|
||||
#elif defined(RDNA3)
|
||||
using bf16x16_t = __attribute__((ext_vector_type(16))) __bf16;
|
||||
using bf16x16_t = __attribute__((ext_vector_type(16))) short;
|
||||
using floatx8_t = __attribute__((ext_vector_type(8))) float;
|
||||
floatx8_t& acc_frag = reinterpret_cast<floatx8_t&>(D.x[0]);
|
||||
const bf16x16_t& a_frag = reinterpret_cast<const bf16x16_t&>(A.x[0]);
|
||||
|
||||
Reference in new issue
Block a user