Skip to content

Commit

Permalink
[NFI]: Reduce lit tests (#1187)
Browse files Browse the repository at this point in the history 
Simplify the lit tests to make them easier to maintain.

---------

Signed-off-by: Tiotto, Ettore <ettore.tiotto@intel.com>
  • Loading branch information
@etiotto
etiotto authored May 28, 2024
1 parent 37366c9 commit 8473632
Show file tree
Hide file tree
Showing 11 changed files with 140 additions and 230 deletions.
8 changes: 4 additions & 4 deletions test/TritonIntelGPU/accelerate-matmul-ats.mlir
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
#blocked = #triton_gpu.blocked<{sizePerThread = [8, 4], threadsPerWarp = [4, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [2, 8], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [4, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
// CHECK: mma_chain_loop
tt.func public @mma_chain_loop(
%170: tensor<128x64xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down Expand Up @@ -43,7 +43,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [2, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [1, 16], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [1, 16], threadsPerWarp = [2, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
// CHECK: chained_dot
tt.func public @chained_dot(
%arg0: tensor<64x128xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand All @@ -67,7 +67,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [4, 2], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [1, 8], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [2, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
// CHECK: mma_chain_loop_ats
tt.func public @mma_chain_loop_ats(
%170: tensor<128x64xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down Expand Up @@ -112,7 +112,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [4, 16], threadsPerWarp = [2, 4], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 16], threadsPerWarp = [1, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [2, 4], warpsPerCTA = [8, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.ATS", "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
// CHECK: chained_dot
tt.func public @chained_dot(
%arg0: tensor<64x128xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down
8 changes: 4 additions & 4 deletions test/TritonIntelGPU/accelerate-matmul-pvc.mlir
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
#blocked = #triton_gpu.blocked<{sizePerThread = [8, 4], threadsPerWarp = [4, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [2, 8], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [4, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
// CHECK: mma_chain_loop
tt.func public @mma_chain_loop(
%170: tensor<128x64xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down Expand Up @@ -49,7 +49,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [2, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 8], threadsPerWarp = [1, 16], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [1, 16], threadsPerWarp = [2, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
// CHECK: chained_dot
tt.func public @chained_dot(
%arg0: tensor<64x128xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand All @@ -75,7 +75,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [4, 2], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [1, 8], warpsPerCTA = [4, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [8, 8], threadsPerWarp = [2, 4], warpsPerCTA = [4, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
// CHECK: mma_chain_loop_ats
tt.func public @mma_chain_loop_ats(
%170: tensor<128x64xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down Expand Up @@ -114,7 +114,7 @@ module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-
#blocked = #triton_gpu.blocked<{sizePerThread = [4, 16], threadsPerWarp = [2, 4], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [4, 16], threadsPerWarp = [1, 8], warpsPerCTA = [8, 1], order = [1, 0]}>
#blocked2 = #triton_gpu.blocked<{sizePerThread = [1, 32], threadsPerWarp = [2, 4], warpsPerCTA = [8, 1], order = [1, 0]}>
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
module attributes {"triton_gpu.target" = "xpu:DEVICE_ARCH.PVC", "triton_gpu.num-warps" = 8 : i32, "triton_gpu.threads-per-warp" = 8 : i32} {
// CHECK: chained_dot
tt.func public @chained_dot(
%arg0: tensor<64x128xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #blocked}>>,
Expand Down
18 changes: 10 additions & 8 deletions test/TritonIntelGPU/backward_combine_dpas_dot_layout.mlir
View file
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// RUN: triton-opt %s -split-input-file -tritonintelgpu-remove-layout-conversions 2>&1 | FileCheck %s
// RUN: triton-opt %s -tritonintelgpu-remove-layout-conversions 2>&1 | FileCheck %s

// COM: Checks that the loads for the operands of a tt.dot operation are placed
// COM: into registers (have dot layout) rather than shared local memory (via a
Expand All @@ -8,8 +8,10 @@
#blocked = #triton_gpu.blocked<{sizePerThread = [1, 1], threadsPerWarp = [1, 16], warpsPerCTA = [2, 2], order = [1, 0]}>
#blocked1 = #triton_gpu.blocked<{sizePerThread = [1, 1], threadsPerWarp = [1, 16], warpsPerCTA = [1, 4], order = [1, 0]}>
#dpas = #triton_intel_gpu.dpas<{repeatCount = 8, systolicDepth = 8, executionSize = 16, opsPerChan = 2, threadsPerWarp = 16, warpsPerCTA = [1, 4], A = [8, 16], B = [16, 16], C = [8, 16]}>
module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
tt.func public @matmul_kernel_with_block_pointers(%arg0: !tt.ptr<f16>, %arg1: !tt.ptr<f16>, %arg2: !tt.ptr<f16>, %arg3: i32, %arg4: i32, %arg5: i32, %arg6: i32, %arg7: i32, %arg8: i32) {
#dot0 = #triton_gpu.dot_op<{opIdx = 0, parent = #dpas, kWidth=2}>
#dot1 = #triton_gpu.dot_op<{opIdx = 1, parent = #dpas, kWidth=2}>
module attributes {"triton_gpu.num-warps" = 4 : i32, "triton_gpu.threads-per-warp" = 16 : i32} {
tt.func public @matmul_kernel_with_block_pointers(%arg0: !tt.ptr<f16>, %arg1: !tt.ptr<f16>, %arg2: !tt.ptr<f16>, %arg3: i32, %arg4: i32, %arg5: i32, %arg6: i32, %arg7: i32, %arg8: i64) {
%c8_i32 = arith.constant 8 : i32
%c64_i32 = arith.constant 64 : i32
%c1_i64 = arith.constant 1 : i64
Expand Down Expand Up @@ -55,17 +57,17 @@ module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 4 :
%23:3 = scf.for %arg9 = %c0_i32 to %arg5 step %c32_i32 iter_args(%arg10 = %cst, %arg11 = %18, %arg12 = %22) -> (tensor<64x256xf32, #dpas>, !tt.ptr<tensor<64x32xf16, #blocked>>, !tt.ptr<tensor<32x256xf16, #blocked1>>) : i32 {
%28 = tt.load %arg11 {boundaryCheck = array<i32: 0, 1>} : !tt.ptr<tensor<64x32xf16, #blocked>>
%29 = tt.load %arg12 {boundaryCheck = array<i32: 0, 1>} : !tt.ptr<tensor<32x256xf16, #blocked1>>
%30 = triton_gpu.convert_layout %28 : tensor<64x32xf16, #blocked> -> tensor<64x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #dpas, kWidth=2}>>
%31 = triton_gpu.convert_layout %29 : tensor<32x256xf16, #blocked1> -> tensor<32x256xf16, #triton_gpu.dot_op<{opIdx = 1, parent = #dpas, kWidth=2}>>
%32 = tt.dot %30, %31, %arg10, inputPrecision = tf32 : tensor<64x32xf16, #triton_gpu.dot_op<{opIdx = 0, parent = #dpas, kWidth=2}>> * tensor<32x256xf16, #triton_gpu.dot_op<{opIdx = 1, parent = #dpas, kWidth=2}>> -> tensor<64x256xf32, #dpas>
%30 = triton_gpu.convert_layout %28 : tensor<64x32xf16, #blocked> -> tensor<64x32xf16, #dot0>
%31 = triton_gpu.convert_layout %29 : tensor<32x256xf16, #blocked1> -> tensor<32x256xf16, #dot1>
%32 = tt.dot %30, %31, %arg10, inputPrecision = tf32 : tensor<64x32xf16, #dot0> * tensor<32x256xf16, #dot1> -> tensor<64x256xf32, #dpas>
%33 = tt.advance %arg11, [%c0_i32, %c32_i32] : <tensor<64x32xf16, #blocked>>
%34 = tt.advance %arg12, [%c32_i32, %c0_i32] : <tensor<32x256xf16, #blocked1>>
scf.yield %32, %33, %34 : tensor<64x256xf32, #dpas>, !tt.ptr<tensor<64x32xf16, #blocked>>, !tt.ptr<tensor<32x256xf16, #blocked1>>
}
%24 = arith.truncf %23#0 : tensor<64x256xf32, #dpas> to tensor<64x256xf16, #dpas>
%25 = triton_gpu.convert_layout %24 : tensor<64x256xf16, #dpas> -> tensor<64x256xf16, #blocked1>
%26 = arith.extsi %arg8 : i32 to i64
%27 = tt.make_tensor_ptr %arg2, [%15, %20], [%26, %c1_i64], [%14, %19] {order = array<i32: 1, 0>} : <tensor<64x256xf16, #blocked1>>

%27 = tt.make_tensor_ptr %arg2, [%15, %20], [%arg8, %c1_i64], [%14, %19] {order = array<i32: 1, 0>} : <tensor<64x256xf16, #blocked1>>
tt.store %27, %25 {boundaryCheck = array<i32: 0, 1>} : !tt.ptr<tensor<64x256xf16, #blocked1>>
tt.return
}
Expand Down
Loading

0 comments on commit 8473632

Please sign in to comment.