@@ -4459,13 +4459,33 @@ (define_insn "*<optab><ALLX:mode>_shft_<GPI:mode>"
;; XXX We should match (any_extend (ashift)) here, like (and (ashift)) below
-(define_insn "*andim_ashift<mode>_bfiz"
- [(set (match_operand:GPI 0 "register_operand" "=r")
- (and:GPI (ashift:GPI (match_operand:GPI 1 "register_operand" "r")
+(define_insn "*andim_ashiftsi_bfiz"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (and:SI (ashift:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand 2 "const_int_operand" "n"))
+ (match_operand 3 "const_int_operand" "n")))]
+ "aarch64_mask_and_shift_for_ubfiz_p (SImode, operands[3], operands[2])"
+ "ubfiz\\t%w0, %w1, %2, %P3"
+ [(set_attr "type" "bfx")]
+)
+
+(define_insn_and_split "*andim_ashiftdi_bfiz"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (and:DI (ashift:DI (match_operand:DI 1 "register_operand" "r")
(match_operand 2 "const_int_operand" "n"))
(match_operand 3 "const_int_operand" "n")))]
- "aarch64_mask_and_shift_for_ubfiz_p (<MODE>mode, operands[3], operands[2])"
- "ubfiz\\t%<w>0, %<w>1, %2, %P3"
+ "aarch64_mask_and_shift_for_ubfiz_p (DImode, operands[3], operands[2])"
+ "ubfiz\\t%x0, %x1, %2, %P3"
+ ;; When the bitposition and width of the equivalent extraction add up to 32
+ ;; we can use a W-reg LSL instruction taking advantage of the implicit
+ ;; zero-extension of the X-reg.
+ "&& (INTVAL (operands[2]) + popcount_hwi (INTVAL (operands[3])))
+ == GET_MODE_BITSIZE (SImode)"
+ [(set (match_dup 0)
+ (zero_extend:DI (ashift:SI (match_dup 4) (match_dup 2))))]
+ {
+ operands[4] = gen_lowpart (SImode, operands[1]);
+ }
[(set_attr "type" "bfx")]
)
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+/* Check that an X-reg UBFIZ can be simplified into a W-reg LSL. */
+
+long long
+f2 (long long x)
+{
+ return (x << 5) & 0xffffffff;
+}
+
+/* { dg-final { scan-assembler "lsl\tw" } } */
+/* { dg-final { scan-assembler-not "ubfiz\tx" } } */
Hi all, Similar to the previous patch this transforms X-reg UBFIZ instructions into W-reg LSL instructions when the UBFIZ operands add up to 32, so we can take advantage of the implicit zero-extension to DImode when writing to a W-register. This is done by splitting the existing *andim_ashift<mode>_bfi pattern into its two SImode and DImode specialisations and changing the DImode pattern into a define_insn_and_split that splits into a zero-extended SImode ashift when the operands match up. So for the code in the testcase we generate: LSL W0, W0, 5 instead of: UBFIZ X0, X0, 5, 27 Bootstrapped and tested on aarch64-none-linux-gnu. Since we're in stage 3 perhaps this is not for GCC 6, but it is fairly low risk. I'm happy for it to wait for the next release if necessary. Thanks, Kyrill 2016-12-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> * config/aarch64/aarch64.md (*andim_ashift<mode>_bfiz): Split into... (*andim_ashiftsi_bfiz): ...This... (*andim_ashiftdi_bfiz): ...And this. Add split to ashift when possible. 2016-12-08 Kyrylo Tkachov <kyrylo.tkachov@arm.com> * gcc.target/aarch64/ubfiz_lsl_1.c: New test.