idma: Streamline TCDM connection, enable multi-channel operation by gbellocchi · Pull Request #330 · pulp-platform/snitch_cluster

gbellocchi · 2026-08-04T13:21:55Z

Description

This PR updates the iDMA integration within the Snitch cluster, as shown in Figures 1 and 2.
It is a refreshed version of PR #238 , which had fallen behind the main snitch cluster branch due to being open for a long period, and a continuation of PR #322.

New features include:

The wide SoC port directly connects to the TCDM subsystem, allowing external data access while DMA transfers run.
The wide DMA XBAR has been simplified.
The DMA uses the OBI protocol to connect to the TCDM subsystem.
Arbitration between the channels, the superbanks, and the SoC port happens now in TCDM, increasing flexibility and throughput. With minimal changes, it is possible to have multiple DMA cores in the cluster.
Add DMINIT support in Snitch cluster.
Add support for OBI events and performance counters.
Add L1-to-L1 and TLS tests to investigate TCDM deadlock.
Support iDMA after common-cells-v2 update.

Tasks

I have collected the tasks and reviewer comments/suggestions of PR #88:

Figure 1: Old integration of `idma`. The wide AXI4 XBAR interconnect is used for: (i) DMA interfaces to TCDM and SoC; (ii) NoC wide in/out; (iii) I$; (iv) Zero memory; and (v) BootROM.

Figure 2: New integration of `idma`. The wide AXI4 XBAR interconnect is simplified: (i) DMA interfaces to TCDM via OBI and wide AXI4 requests are transmitted to other clusters via the AXI4 XBAR (NoC wide out); (ii) Remove AXI4 TCDM port and directly interface the NoC wide inputs of external DMAs to the TCDM subsystem (bypassing the XBAR); (iii) Remove zero memory as the iDMA now supports memset initialization of TCDM.

* `axi_zero_mem` is removed because the idma can now initialize the memory to a desired value.

* Modify the wide cluster xbar address map based on the removal of the zero memory and the new idma-tcdm integration. * Update the cluster and dma enums in the `snitch_pkg`.

The wide `soc_in_axi_req` is directly interfaced with the tcdm subsystem and bypasses the wide axi cluster xbar.

* `snitch_cluster`: Add memory and obi typedefs. * `snitch_cluster`: Add obi-to-tcdm protocol conversion for dma requests toward the tcdm subsystem. * `snitch_cluster`: Update interface of `snitch_cc` instance. * `snitch_cc`: Instantiate `idma` with obi interfaces.

idma: Fix dminit opcode encoding and add TCDM tests

* Avoid the flattening of arrays in the tcdm dma interconnect.

* Fix deadlock in tcdm-to-tcdm idma transfers, which originates from the absence of p_valid for write transactions. * Add write pipeline shift register (mirroring id_pipeline) for tracking whether an in-flight slot is a write.

* Add GUI version of `vsim` among the `run.py` simulators. * Add `wave-file` argument to specify a corresponding wave file to automatically source when launching the `vsim-gui` simulator. * Add support for wave argument in the generated `snitch_cluster.vsim.gui` script.

* Tie off the `obi_dma_req_o` when no DMA is instantiated in the `snitch_cc`.

* Tie off undriven signals to avoid having undefined behaviors. * Add documentation for the obi-to-tcdm bridge.

* hw: Update hw configuration files and templates. * hw: Remove commented lines in `snitch_cluster.sv` for address remapping after zeromem removal. * sw: Update experiment json configuration files.

* Remove hardcoded reference to DM core as core 8. * Update dma wait api.

* Map arrays to l1 in order to test l1-to-l1 dma transfers. To this end, use `snrt_l1_alloc()` to initialize `src` and `dst` arrays. * Extend the range of traffic sizes to trigger the l1-to-l1 deadlock experienced with other kernels (exp).

* This test assesses proper tls initialization at runtime (sanity check) and modification at application-time (core isolation).

* This test concerns the traffic patterns used in `snrt_init_tls` at runtime. * Parameters are currently tuned on the specific case of the `exp` kernel.

`obi_to_tcdm` was invoking the `AMONone` parameter from the `reqrsp_pkg`, while this was moved to `snitch_pkg`.

Fix SYNTH_89 warning in spyglass into the `snitch_cluster` and concerning the definition of `enabled_dma_addr_rule`. This is solved similarly to what previously done for `enabled_dma_xbar_rule` in a previous commit.

Since PR pulp-platform#328 excludes the tracer when DEBUG is not defined, then the tests fail. So, the experiments are now built with `DEBUG=ON` so the tracer is built and performance reports are generated.

Fix Spyglass error by breaking comb-loop in `idma`.

* This was initially removed when the `idma` RW interfaces was modified, since it was breaking performance counter tests. * Fix miscellaneous linting errors.

…tich_develop

Cut combinational loop between OBI interface and `idma` by substituing handshake-based flow control with credit-based. This solution substitutes the previously proposed one in the `idma` backend, which was more invasive as it affected all `idma` versions. To this end, the latter was also reverted to an older version.

Waive 'W123' and 'W287a' spyglass violations, which should be handled into `idma`.

Bender.yml iDMA -> __deploy__14dcdf1__devel: devel with common_cells v2 (iDMA #99) on top of the MX compute and the single-sourced compute_op encoding, matching main's common_cells v2 base. The MX tests and compute helpers move to the per-tile macro idiom of the reshaped heterogeneous-tile address map (GW_L2_SPM_*(i), 4 KiB DMA window); the backend instantiation drops testmode_i (cc-v2 iDMA removed the test-mode ports); snitch_cluster is pinned to dk/idma070 (DanielKellerM fork), which threads the obi/init type parameters iDMA 0.7.0 added to idma_inst64_top - an interim shim converging with pulp-platform/snitch_cluster#330, to be dropped when it merges.

* Fix spyglass violation in `cc_stream_fifo_optimal_wrap`.

Bender.yml iDMA -> 0.7.0 (the release carries the merged MX quant/dequant compute, the single-sourced compute_op encoding, and common_cells v2, matching main's common_cells v2 base). The MX tests and compute helpers move to the per-tile macro idiom of the reshaped heterogeneous-tile address map (GW_L2_SPM_*(i), 4 KiB DMA window); the backend instantiation drops testmode_i (cc-v2 iDMA removed the test-mode ports); snitch_cluster is pinned to dk/idma070 (DanielKellerM fork), which threads the obi/init type parameters iDMA 0.7.0 added to idma_inst64_top - an interim shim converging with pulp-platform/snitch_cluster#330, to be dropped when it merges.

colluca

Still need to finish but a first few comments.

colluca · 2026-08-19T19:23:24Z

+  parameter type         obi_a_chan_t       = logic,
+  parameter type         obi_r_chan_t       = logic,
+  parameter type         obi_req_t          = logic,
+  parameter type         obi_rsp_t          = logic,


Can we use the reqrsp interface macros (from the reqrsp_interface repo) to internally derive the req_t and rsp_t types for the OBI and INIT interfaces from the chan_t types? Would simplify the CC parameter list.

colluca · 2026-08-19T19:28:13Z

  output logic                              barrier_o,
  input  logic                              barrier_i,
+  // Address decode map
+  input  addr_rule_t [TCDMAliasEnable:0]    dma_addr_rule_i,


Can we name it dma_addr_map_i to reflect the dma's port name?

colluca · 2026-08-19T19:31:40Z

This file can be deleted. It was probably restored by accident during the merge with the latest CC changes.

colluca · 2026-08-19T19:34:55Z

This file can also be deleted I believe, same as above.

colluca · 2026-08-19T19:35:38Z

Delete, same as above.

colluca · 2026-08-19T19:38:28Z

-	@echo '$(SN_VSIM) +permissive $(SN_VSIM_FLAGS) \
+	@echo 'WAVE_ARGS=()' >> $@.gui
+	@echo '[ -n "$$QUESTA_WAVE_DO" ] && WAVE_ARGS=(-do "do $$QUESTA_WAVE_DO")' >> $@.gui
+	@echo '$(SN_VSIM) +permissive "$${WAVE_ARGS[@]}" $(SN_VSIM_FLAGS) \


I assume you used this for debugging, but I think we can remove it

colluca · 2026-08-19T19:40:51Z

+
+#define R_TYPE_ENCODE(funct7, rs2, rs1, funct3, rd, opcode)                    \
+    ((funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | \
+     (opcode))


Instead of adding all this stuff back, let's add support for DMINIT to the compiler. With the new autogenerated toolchain it should be as trivial as simply bumping riscv-opcodes.

colluca · 2026-08-19T19:42:07Z

+ * @param size The size of the transfer in bytes.
+ * @param channel The index of the channel.
+ */
+inline uint32_t snrt_dma_memset_init_1d(uint64_t ptr, uint8_t value,


What's different from snrt_dma_memset? Can't we just update that function to use DMINIT?

colluca · 2026-08-19T19:42:43Z

No need for deprecating, let's just delete.

gbellocchi and others added 30 commits June 2, 2026 23:12

hw: Add decode support for dminit instruction

58085fa

sw: Add sw support for dminit tests

77cc080

hw: Remove axi_zero_mem from snitch_cluster

8ceb732

* `axi_zero_mem` is removed because the idma can now initialize the memory to a desired value.

hw: Update cluster and dma address map

ac20e15

* Modify the wide cluster xbar address map based on the removal of the zero memory and the new idma-tcdm integration. * Update the cluster and dma enums in the `snitch_pkg`.

hw: Connect wide soc input to tcdm subsystem

57fb5f4

The wide `soc_in_axi_req` is directly interfaced with the tcdm subsystem and bypasses the wide axi cluster xbar.

hw: Add obi-to-tcdm protocol converter

92503d3

hw: Update NrWideMasters in snitch_cluster_pkg template

9a07527

bender: Add obi dependency

7068914

bender: Change idma deploy reference commit

d3c922b

docs: Add documentation for dminit custom instruction

fdccf94

test: Add L1-to-L1 TCDM iDMA copy regression test

96c613d

sw: Fix dminit opcode encoding (funct7 and rd register)

7710da8

test: Fence buffer init before the DMA in dma_dminit

4d0e8c2

Merge pull request #1 from DanielKellerM/dkeller/idma-dminit-fixes

eebedeb

idma: Fix dminit opcode encoding and add TCDM tests

hw: Refactor arrays in tcdm dma interconnect

85c7778

* Avoid the flattening of arrays in the tcdm dma interconnect.

hw: Fix OBI write response deadlock in obi_to_tcdm bridge

f61240c

* Fix deadlock in tcdm-to-tcdm idma transfers, which originates from the absence of p_valid for write transactions. * Add write pipeline shift register (mirroring id_pipeline) for tracking whether an in-flight slot is a write.

hw: Tie off unused obi_dma_req_o if no dma

3bfdc22

* Tie off the `obi_dma_req_o` when no DMA is instantiated in the `snitch_cc`.

hw: Tie off undriven signals in obi-to-tcdm bridge

d787bbc

* Tie off undriven signals to avoid having undefined behaviors. * Add documentation for the obi-to-tcdm bridge.

hw: Update id width on dma master side

d99ab93

Bump idma deploy

49dc326

Remove occurrences of zeromem

6411a68

* hw: Update hw configuration files and templates. * hw: Remove commented lines in `snitch_cluster.sv` for address remapping after zeromem removal. * sw: Update experiment json configuration files.

sw: Uodate gemm to use dminit memset

26e011a

sw: Move zero_mem test into deprecated

9ed1c71

sw: Improve dma_dminit portability

1063499

* Remove hardcoded reference to DM core as core 8. * Update dma wait api.

sw: Fix dma_l1l1 to allocate buffers in l1

1b7a926

* Map arrays to l1 in order to test l1-to-l1 dma transfers. To this end, use `snrt_l1_alloc()` to initialize `src` and `dst` arrays. * Extend the range of traffic sizes to trigger the l1-to-l1 deadlock experienced with other kernels (exp).

sw: Add dma test for local-to-remote tcdm transfer

7dcbd40

sw: Add tls test for init and update

d1e4164

* This test assesses proper tls initialization at runtime (sanity check) and modification at application-time (core isolation).

sw: Add test to assess dma traffic pattern of snrt_init_tls

c85aefa

* This test concerns the traffic patterns used in `snrt_init_tls` at runtime. * Parameters are currently tuned on the specific case of the `exp` kernel.

gbellocchi added 11 commits August 5, 2026 15:28

hw: Fix atomic parameter in obi_to_tcdm

fa15ca1

`obi_to_tcdm` was invoking the `AMONone` parameter from the `reqrsp_pkg`, while this was moved to `snitch_pkg`.

spyglass: Fix variable declaration for enabled_dma_addr_rule

7454dae

Fix SYNTH_89 warning in spyglass into the `snitch_cluster` and concerning the definition of `enabled_dma_addr_rule`. This is solved similarly to what previously done for `enabled_dma_xbar_rule` in a previous commit.

ci: Enable debug mode for copift and chaining tests

89ba48e

Since PR pulp-platform#328 excludes the tracer when DEBUG is not defined, then the tests fail. So, the experiments are now built with `DEBUG=ON` so the tracer is built and performance reports are generated.

Bump idma

379af9d

Fix Spyglass error by breaking comb-loop in `idma`.

sw: Add back perf_cnt in frep_xs configuration

6b86a8d

* This was initially removed when the `idma` RW interfaces was modified, since it was breaking performance counter tests. * Fix miscellaneous linting errors.

sw: Fix linting errors

476a892

Merge remote-tracking branch 'pulp-github/main' into gb/idma_tcdm_mul…

4a10de2

…tich_develop

hw: Remove deprecated parameters in obi_to_tcdm

c85aba7

Fix linting errors

99dbf0f

spyglass: Waive idma violations

be1b803

Waive 'W123' and 'W287a' spyglass violations, which should be handled into `idma`.

This was referenced Aug 11, 2026

cc_stream_fifo_optimal_wrap: Assigning unknown state to usage_o pulp-platform/common_cells#356

Open

Spyglass violations in idma_inst64_top pulp-platform/iDMA#172

Open

gbellocchi mentioned this pull request Aug 12, 2026

fix: Drive usage_o low if not supported pulp-platform/common_cells#357

Open

Bump common_cells

71cab48

* Fix spyglass violation in `cc_stream_fifo_optimal_wrap`.

DanielKellerM mentioned this pull request Aug 19, 2026

feat: iDMA 0.7.0 with MX compute in the mem tile pulp-platform/gwaihir#44

Draft

6 tasks

colluca changed the base branch from develop to main August 19, 2026 19:18

colluca requested changes Aug 19, 2026

View reviewed changes

Navigation Menu

Uh oh!

idma: Streamline TCDM connection, enable multi-channel operation - #330

idma: Streamline TCDM connection, enable multi-channel operation#330
gbellocchi wants to merge 64 commits into
pulp-platform:mainfrom
gbellocchi:gb/idma_tcdm_multich_develop

gbellocchi commented Aug 4, 2026 •

edited

Loading

Uh oh!

colluca left a comment

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

colluca Aug 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

gbellocchi commented Aug 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Tasks

Uh oh!

colluca left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

gbellocchi commented Aug 4, 2026 •

edited

Loading