The checks for FP_CONTRACT_FAST were in the wrong place for complex_mul.
The location it was in would only block FMA but not MUL. It would also not
really reject the forming of the FMA, it would just create an invalid collection
of nodes which would fail analysis later on.
However complex multiplication is also a contraction, since it's doing
real = a*c - b*d
imag = a*d + b*c
This moves the checks up to earliest possible location and actually just returns
and adds the missing check for FMS.
Bootstrapped Regtested on aarch64-none-linux-gnu,
arm-none-linux-gnueabihf, x86_64-pc-linux-gnu
-m32, -m64 and no issues.
Pushed.
Thanks,
Tamar
gcc/ChangeLog:
PR tree-optimization/125431
* tree-vect-slp-patterns.cc (complex_mul_pattern::matches,
complex_fms_pattern::matches): Gate on FP contraction.
gcc/testsuite/ChangeLog:
PR tree-optimization/125431
* gfortran.dg/vect/pr125431.f90: New test.
---
diff --git a/gcc/testsuite/gfortran.dg/vect/pr125431.f90
b/gcc/testsuite/gfortran.dg/vect/pr125431.f90
new file mode 100644
index
0000000000000000000000000000000000000000..fe11b5eface9978c916783619677a10a7759c43d
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/vect/pr125431.f90
@@ -0,0 +1,16 @@
+! { dg-do compile }
+! { dg-additional-options "-O2 -ffp-contract=off" }
+! { dg-additional-options "-march=armv8.3-a" { target { aarch64*-*-* } } }
+
+subroutine foo(a,b,c)
+
+ complex :: a(6,6)
+ complex :: b(6,6)
+ complex :: c(6,6)
+
+ c = MATMUL(a, b)
+
+end subroutine foo
+
+! { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" { target { vect_float }
} } }
+! { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" } }
diff --git a/gcc/tree-vect-slp-patterns.cc b/gcc/tree-vect-slp-patterns.cc
index
c0031a129a445160998f70bf9c18e1ef70464eed..181281c2154bedfc8e8c6b1bde1226e194ba99e5
100644
--- a/gcc/tree-vect-slp-patterns.cc
+++ b/gcc/tree-vect-slp-patterns.cc
@@ -1038,6 +1038,11 @@ complex_mul_pattern::matches (complex_operation_t op,
if (op != MINUS_PLUS)
return IFN_LAST;
+ /* It's only valid to form FMAs and MUL with -ffp-contract=fast. */
+ if (flag_fp_contract_mode != FP_CONTRACT_FAST
+ && FLOAT_TYPE_P (SLP_TREE_VECTYPE (*node)))
+ return IFN_LAST;
+
auto childs = *ops;
auto l0node = SLP_TREE_CHILDREN (childs[0]);
@@ -1050,11 +1055,8 @@ complex_mul_pattern::matches (complex_operation_t op,
auto_vec<slp_tree> left_op, right_op;
slp_tree add0 = NULL;
- /* Check if we may be a multiply add. It's only valid to form FMAs
- with -ffp-contract=fast. */
+ /* Check if we may be a multiply add. */
if (!mul0
- && (flag_fp_contract_mode == FP_CONTRACT_FAST
- || !FLOAT_TYPE_P (SLP_TREE_VECTYPE (*node)))
&& vect_match_expression_p (l0node[0], PLUS_EXPR))
{
auto vals = SLP_TREE_CHILDREN (l0node[0]);
@@ -1285,6 +1287,11 @@ complex_fms_pattern::matches (complex_operation_t op,
if (!vect_match_expression_p (root, MINUS_EXPR))
return IFN_LAST;
+ /* It's only valid to form FMSs with -ffp-contract=fast. */
+ if (flag_fp_contract_mode != FP_CONTRACT_FAST
+ && FLOAT_TYPE_P (SLP_TREE_VECTYPE (*ref_node)))
+ return IFN_LAST;
+
/* TODO: Support invariants here, with the new layout CADD now
can match before we get a chance to try CFMS. */
auto nodes = SLP_TREE_CHILDREN (root);
--
diff --git a/gcc/testsuite/gfortran.dg/vect/pr125431.f90 b/gcc/testsuite/gfortran.dg/vect/pr125431.f90
new file mode 100644
index 0000000000000000000000000000000000000000..fe11b5eface9978c916783619677a10a7759c43d
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/vect/pr125431.f90
@@ -0,0 +1,16 @@
+! { dg-do compile }
+! { dg-additional-options "-O2 -ffp-contract=off" }
+! { dg-additional-options "-march=armv8.3-a" { target { aarch64*-*-* } } }
+
+subroutine foo(a,b,c)
+
+ complex :: a(6,6)
+ complex :: b(6,6)
+ complex :: c(6,6)
+
+ c = MATMUL(a, b)
+
+end subroutine foo
+
+! { dg-final { scan-tree-dump "LOOP VECTORIZED" "vect" { target { vect_float } } } }
+! { dg-final { scan-tree-dump-not "Found COMPLEX_MUL" "vect" } }
diff --git a/gcc/tree-vect-slp-patterns.cc b/gcc/tree-vect-slp-patterns.cc
index c0031a129a445160998f70bf9c18e1ef70464eed..181281c2154bedfc8e8c6b1bde1226e194ba99e5 100644
--- a/gcc/tree-vect-slp-patterns.cc
+++ b/gcc/tree-vect-slp-patterns.cc
@@ -1038,6 +1038,11 @@ complex_mul_pattern::matches (complex_operation_t op,
if (op != MINUS_PLUS)
return IFN_LAST;
+ /* It's only valid to form FMAs and MUL with -ffp-contract=fast. */
+ if (flag_fp_contract_mode != FP_CONTRACT_FAST
+ && FLOAT_TYPE_P (SLP_TREE_VECTYPE (*node)))
+ return IFN_LAST;
+
auto childs = *ops;
auto l0node = SLP_TREE_CHILDREN (childs[0]);
@@ -1050,11 +1055,8 @@ complex_mul_pattern::matches (complex_operation_t op,
auto_vec<slp_tree> left_op, right_op;
slp_tree add0 = NULL;
- /* Check if we may be a multiply add. It's only valid to form FMAs
- with -ffp-contract=fast. */
+ /* Check if we may be a multiply add. */
if (!mul0
- && (flag_fp_contract_mode == FP_CONTRACT_FAST
- || !FLOAT_TYPE_P (SLP_TREE_VECTYPE (*node)))
&& vect_match_expression_p (l0node[0], PLUS_EXPR))
{
auto vals = SLP_TREE_CHILDREN (l0node[0]);
@@ -1285,6 +1287,11 @@ complex_fms_pattern::matches (complex_operation_t op,
if (!vect_match_expression_p (root, MINUS_EXPR))
return IFN_LAST;
+ /* It's only valid to form FMSs with -ffp-contract=fast. */
+ if (flag_fp_contract_mode != FP_CONTRACT_FAST
+ && FLOAT_TYPE_P (SLP_TREE_VECTYPE (*ref_node)))
+ return IFN_LAST;
+
/* TODO: Support invariants here, with the new layout CADD now
can match before we get a chance to try CFMS. */
auto nodes = SLP_TREE_CHILDREN (root);
