AARCH64_FUSION_PAIR ("alu+branch", ALU_BRANCH)
AARCH64_FUSION_PAIR ("alu+cbz", ALU_CBZ)
AARCH64_FUSION_PAIR ("addsub_2reg_const1", ADDSUB_2REG_CONST1)
+AARCH64_FUSION_PAIR ("cmp+csel", CMP_CSEL)
+AARCH64_FUSION_PAIR ("cmp+cset", CMP_CSET)
#undef AARCH64_FUSION_PAIR
&& reg_referenced_p (SET_DEST (prev_set), PATTERN (curr)))
return true;
+ /* FUSE CMP and CSEL. */
+ if (aarch64_fusion_enabled_p (AARCH64_FUSE_CMP_CSEL)
+ && prev_set && curr_set
+ && GET_CODE (SET_SRC (prev_set)) == COMPARE
+ && GET_CODE (SET_SRC (curr_set)) == IF_THEN_ELSE
+ && REG_P (XEXP (SET_SRC (curr_set), 1))
+ && REG_P (XEXP (SET_SRC (curr_set), 2))
+ && reg_referenced_p (SET_DEST (prev_set), PATTERN (curr)))
+ return true;
+
+ /* Fuse CMP and CSET. */
+ if (aarch64_fusion_enabled_p (AARCH64_FUSE_CMP_CSET)
+ && prev_set && curr_set
+ && GET_CODE (SET_SRC (prev_set)) == COMPARE
+ && GET_RTX_CLASS (GET_CODE (SET_SRC (curr_set))) == RTX_COMPARE
+ && REG_P (SET_DEST (curr_set))
+ && reg_referenced_p (SET_DEST (prev_set), PATTERN (curr)))
+ return true;
+
/* Fuse flag-setting ALU instructions and conditional branch. */
if (aarch64_fusion_enabled_p (AARCH64_FUSE_ALU_BRANCH)
&& any_condjump_p (curr))
2 /* store_pred. */
}, /* memmov_cost. */
5, /* issue_rate */
- (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_CMP_BRANCH), /* fusible_ops */
+ (AARCH64_FUSE_AES_AESMC
+ | AARCH64_FUSE_CMP_BRANCH
+ | AARCH64_FUSE_CMP_CSEL
+ | AARCH64_FUSE_CMP_CSET), /* fusible_ops */
"32:16", /* function_align. */
"4", /* jump_align. */
"32:16", /* loop_align. */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=neoverse-v2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+/*
+** f1:
+** ...
+** cmp w[0-9]+, w[0-9]+
+** csel w[0-9]+, w[0-9]+, w[0-9]+, le
+** ret
+*/
+int f1 (int a, int b, int c)
+{
+ int cmp = a > b;
+ int add1 = c + 3;
+ int add2 = c + 8;
+ return cmp ? add1 : add2;
+}
+
+/*
+** f2:
+** ...
+** cmp x[0-9]+, x[0-9]+
+** csel x[0-9]+, x[0-9]+, x[0-9]+, le
+** ret
+*/
+long long f2 (long long a, long long b, long long c)
+{
+ long long cmp = a > b;
+ long long add1 = c + 3;
+ long long add2 = c + 8;
+ return cmp ? add1 : add2;
+}
+
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=neoverse-v2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+/*
+** f1:
+** cmp w[0-9]+, w[0-9]+
+** cset w[0-9]+, gt
+** ...
+*/
+int g;
+int f1 (int a, int b)
+{
+ int cmp = a > b;
+ g = cmp + 1;
+ return cmp;
+}
+
+/*
+** f2:
+** cmp x[0-9]+, x[0-9]+
+** cset x[0-9]+, gt
+** ...
+*/
+long long h;
+long long f2 (long long a, long long b)
+{
+ long long cmp = a > b;
+ h = cmp + 1;
+ return cmp;
+}