remove the matmul hang workaround from conv and matmul kernels

tenstorrent · Feb 27, 2025 · cad363d · cad363d
1 parent fdcade2
commit cad363d
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 15 deletions.
diff --git a/ttnn/cpp/ttnn/operations/conv/conv2d/device/kernels/conv_bmm_tilize_col_major_out_blocks.cpp b/ttnn/cpp/ttnn/operations/conv/conv2d/device/kernels/conv_bmm_tilize_col_major_out_blocks.cpp
@@ -259,13 +259,6 @@ void MAIN {
                             // matmul outer product of (out_subblock_h x out_subblock_w) tiles that fill dst
                             // accumulation is done by iterating matmul_block across inner dim
                             // in0_block_w is passed as innder dim (kt) to matmul_block, interally used to stride in0
-#ifdef ARCH_BLACKHOLE
-                            // FIXME: This is a temporary workaround to avoid hangs on blackhole.
-                            // https://github.com/tenstorrent/tt-metal/issues/16439
-                            for (uint32_t i = 0; i < 10; i++) {
-                                asm volatile("nop");
-                            }
-#endif
                             matmul_block(
                                 mm_in0_cb_id,
                                 in1_cb_id,

diff --git a/...tnn/operations/matmul/device/kernels/compute/bmm_large_block_zm_fused_bias_activation.cpp b/...tnn/operations/matmul/device/kernels/compute/bmm_large_block_zm_fused_bias_activation.cpp
@@ -198,14 +198,6 @@ void MAIN {
                                 // accumulation is done by iterating matmul_block across inner dim
                                 // in0_block_w is passed as innder dim (kt) to matmul_block, interally used to stride
                                 // in0
-
-#ifdef ARCH_BLACKHOLE
-                                // FIXME: This is a temporary workaround to avoid hangs on blackhole.
-                                // https://github.com/tenstorrent/tt-metal/issues/16439
-                                for (uint32_t i = 0; i < 100; i++) {
-                                    asm volatile("nop");
-                                }
-#endif
                                 matmul_block(
                                     in0_cb_id,
                                     in1_cb_id,