LOKI: add support for scc-hoist transformation

ecmwf-ifs · Mar 28, 2024 · d0b3687 · d0b3687
1 parent a5028a4
commit d0b3687
Show file tree

Hide file tree

Showing 5 changed files with 13 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -217,15 +217,18 @@ there are following options:
 
 Note that only `ecwam-run-model` currently supports MPI.
 
+
 Running with source-term computation offloaded to the GPU
 =========================================================
-The calculation of the source-terms in ecWam, i.e. the physics, can be offloaded for GPU execution. GPU optimised code is 
-generated at build-time using ECMWF's source-to-source translation toolchain Loki. Currently, two Loki transformations are supported 
-(in ascending order of performance):
+The calculation of the source-terms in ecWam, i.e. the physics, can be offloaded for GPU execution.
+GPU optimised code is generated at build-time using ECMWF's source-to-source translation toolchain Loki. Currently,
+three Loki transformations are supported:
 - Single-column-coalesced (scc): Fuse vector loops and promote to the outermost level to target the SIMT execution model
-- scc-stack: The scc transformation with a pool allocator used to allocate temporary arrays (the default)
+- scc-hoist: The scc transformation with temporary arrays hoisted to the driver-layer
+- scc-stack: The scc transformation with a pool allocator used to allocate temporary arrays
 
-Currently, only the OpenACC programming model is supported.
+The scc-hoist and scc-stack transformations offer superior performance to the scc transformation. Currently, only the
+OpenACC programming model on Nvidia GPUs is supported.
 
 Building
 --------

diff --git a/src/ecwam/airsea.F90 b/src/ecwam/airsea.F90
@@ -58,6 +58,7 @@ SUBROUTINE AIRSEA (KIJS, KIJL, &
 
       USE PARKIND_WAVE, ONLY : JWIM, JWRB, JWRU
 
+      USE YOWFRED  , ONLY : NWAV_GC ! needed for Loki
       USE YOWPARAM, ONLY : NANG     ,NFRE
       USE YOWPHYS,  ONLY : XKAPPA, XNLEV
       USE YOWTEST,  ONLY : IU06

diff --git a/src/ecwam/implsch.F90 b/src/ecwam/implsch.F90
@@ -88,6 +88,8 @@ SUBROUTINE IMPLSCH (KIJS, KIJL, FL1,                         &
       USE YOWPCONS , ONLY : WSEMEAN_MIN, ROWATERM1 
       USE YOWSTAT  , ONLY : IDELT    ,LBIWBK
       USE YOWWNDG  , ONLY : ICODE    ,ICODE_CPL
+      USE YOWINDN  , ONLY : MLSTHG  ! needed for Loki
+      USE YOWFRED  , ONLY : NWAV_GC ! needed for Loki
 
       USE YOMHOOK  , ONLY : LHOOK,   DR_HOOK, JPHOOK
 

diff --git a/src/ecwam/sinflx.F90 b/src/ecwam/sinflx.F90
@@ -29,6 +29,7 @@ SUBROUTINE SINFLX (ICALL, NCALL, KIJS, KIJL,  &
 
       USE PARKIND_WAVE, ONLY : JWIM, JWRB, JWRU
 
+      USE YOWFRED  , ONLY : NWAV_GC ! needed for Loki
       USE YOWCOUP  , ONLY : LWCOU    ,LLCAPCHNK , LLGCBZ0, LLNORMAGAM
       USE YOWPARAM , ONLY : NANG     ,NFRE
       USE YOWPHYS  , ONLY : DTHRN_A  ,DTHRN_U 

diff --git a/src/ecwam/taut_z0.F90 b/src/ecwam/taut_z0.F90
@@ -68,6 +68,7 @@ SUBROUTINE TAUT_Z0(KIJS, KIJL, IUSFG,          &
 
       USE PARKIND_WAVE, ONLY : JWIM, JWRB, JWRU
 
+      USE YOWFRED  , ONLY : NWAV_GC ! needed for Loki
       USE YOWCOUP  , ONLY : LLCAPCHNK, LLGCBZ0
       USE YOWPARAM , ONLY : NANG     ,NFRE
       USE YOWPCONS , ONLY : G, GM1, EPSUS, EPSMIN, ACD, BCD, CDMAX